![Construction of tourist trajectories from geo-tagged photos. Retrieved from [29].](https://www.researchgate.net/profile/Kwan-Hui-Lim/publication/329570549/figure/fig3/AS:728777445371911@1550765491672/Construction-of-tourist-trajectories-from-geo-tagged-photos-Retrieved-from-29_Q320.jpg)
Content uploaded by Kwan Hui Lim
Author content
All content in this area was uploaded by Kwan Hui Lim on Feb 21, 2019
Content may be subject to copyright.
Accepted for publication in Knowledge and Information Systems
Tour Recommendation and Trip
Planning using Location-based Social
Media: A Survey
Kwan Hui Lim*, Jeffrey Chan‡†, Shanika Karunasekera†, Christopher Leckie†
*Information Systems Technology and Design Pillar, Singapore University of Technology and Design
†School of Computing and Information Systems, The University of Melbourne, Australia
‡School of Science, RMIT University, Australia
kwanhui lim@sutd.edu.sg, jeffrey.chan@rmit.edu.au, {karus, caleckie}@unimelb.edu.au
Abstract. Tourism is both an important industry and popular leisure activity un-
dertaken by millions around the world. One important task for tourists is to plan
and schedule tour itineraries that comprise multiple captivating Points-of-Interests
(POIs) based on the unique interest preferences of the tourist. The complex task of
tour itinerary recommendation is further complicated by the need to incorporate var-
ious real-life constraints such as limited time for touring, uncertain traffic conditions,
inclement weather, group travel, queuing times and crowdedness. In this survey, we
conduct a comprehensive literature review of studies on tour itinerary recommenda-
tion and present a general taxonomy for touring-related research. We discuss the entire
process of tour itinerary recommendation research including: (i) data collection and
types of datasets; (ii) problem formulations and proposed algorithms/systems for indi-
vidual travellers, groups of tourists and various real-life considerations; (iii) evaluation
methodologies for comparing tour itinerary recommendation algorithms; and (iv) future
directions and open problems in tour itinerary recommendation research.
Keywords: Tour Recommendation, Itinerary Planning, Group Recommendation, User
Interests, Personalization, Location-based Social Networks
1. Introduction
Tourism is a popular leisure activity undertaken by more than 1.18 billion inter-
national tourists per annum [97]. Economically, tourism is an important industry,
Received 15 Nov 2017
Revised 12 Jun 2018
Accepted 03 Oct 2018
2 K. H. Lim et al.
Challenges of Tour Planning
Preferred
starting
point Preferred
ending
point
15min
1.5hr 1hr
1hr 2hr
3hr
1.5hr
0.5hr
Beaches Entertainment Cultural Gardens Historical Buildings
Legend (POI Categories)
Fig. 1. Example of the tour recommendation problem.
generating more than 284 million jobs and accounting for more than US$7.2 tril-
lion in revenue annually [105]. Despite its importance and popularity, planning
a tour itinerary in a foreign city is both challenging and time-consuming due
to the need to identify captivating Places-of-Interest (POIs) and plan visits to
these POIs as a connected itinerary. Adding to these challenges are the need to
personalize the recommended itinerary according to the interest preferences of
tourists, and to schedule the itinerary based on relevant temporal and spatial
constraints, such as having limited time to complete the tour and needing to
start and end near certain locations (e.g., the tourist’s hotel). Figure 1 shows an
example of the tour recommendation problem, where there are multiple POIs of
different categories, and the tourist has to find an itinerary that optimizes the
time taken and number of POIs visited, while satisfying various trip constraints.
Although tourism-related information can be obtained from the Internet
and travel guides, these resources simply recommend popular POIs or generic
itineraries but otherwise do not address the unique interest preferences of in-
dividual tourists or adhere to their various temporal and spatial constraints.
Moreover, the large amount of information available increases the challenge of
identifying the relevant information for the tourist. One popular alternative is
to engage the services of tour agencies, but likewise, these tour agencies nor-
mally only recommend standard package tours that may not address the interest
preferences or trip constraints of all tourists.
To address these issues, many researchers have studied tour itinerary recom-
mendation problems and proposed various algorithms for solving these problems.
These problems originated from the operations research community where the
main focus is to schedule an optimal path, where the measure of optimality is
typically based on a global metric such as POI popularity, and thus there is
no personalization based on unique user interests. With the prevalence of smart
phones and location-based social media, there has been an increased emphasis
on data-driven approaches to tour itinerary recommendation to better model
the interest preferences of tourists, and recommend personalized tour itineraries
that satisfy these interest preferences as well as other trip constraints. In this
survey paper, we focus on such data-driven tour recommendation research, par-
Tour Recommendation and Trip Planning Survey 3
Taxonomy of State-of-the-Art
Touring-related ResearchTouring-related Research
Orienteering
Problem
Orienteering
Problem
Operations ResearchOperations Research
Travelling
Salesman Prob.
Travelling
Salesman Prob.
RecommendationsRecommendations
Vehicle Routing
Problem
Vehicle Routing
Problem
Top-k POIs Recom.Top-k POIs Recom.
Next POI Recom.Next POI Recom.POI Package Recom.POI Package Recom.
Tour Itinerary
Recommendation
Tour Itinerary
Recommendation
User
Interests
User
Interests
Transport
Modes
Transport
Modes
Traffic
Conditions
Traffic
Conditions
Time
Constraints
Time
Constraints
User
Demographic
User
Demographic
POI
Popularity
POI
Popularity
Individual
Traveller
Individual
Traveller
Area of Interest
Groups of
Tourists
Groups of
Tourists
Different Considerations
Fig. 2. Taxonomy of touring-related research.
ticularly on the types of data sources used, the problem variants formulated, the
algorithms proposed and the evaluation methodology used.
Closely related to the field of tour itinerary recommendation are the fields
of next-location prediction/recommendation [76, 6, 41, 91, 66], top-k location
recommendation [108, 112, 65, 107, 103, 62] and travel package/region recom-
mendation [8, 7, 95, 82]. Although these fields are related to tour itinerary rec-
ommendation, there are distinct differences in terms of the problem studied.
Next-location prediction and recommendation aim to identify the next location
that a user is likely to visit based on his/her previous trajectories, whereas tour
itinerary recommendation aims to recommend multiple POIs or locations in the
form of a trajectory. Top-k location recommendation and travel package/region
recommendation do fulfill the criterion of recommending multiple POIs as part
of a ranked list or travel package, but they do not structure these POIs as a con-
nected itinerary. In contrast, tour itinerary recommendation has the additional
challenges of planning an itinerary of connected POIs that appeal to the interest
preferences of the users, while adhering to the temporal and spatial constraints
in the form of a limited time budget for touring and having to start and end at
specific POIs.
In this survey, we focus on works related to tour itinerary recommendation
and the different real-life considerations incorporated into this problem. Figure 2
illustrates a taxonomy of the general area of touring-related research, which is
further divided into the sub-areas of operations research and recommendations.
1.1. Related Surveys and Reviews
There exist a variety of survey and review articles that cover different aspects
of the tour recommendation problem. In this section, we discuss these related
articles and highlight the differences between this paper and the earlier articles.
The tour recommendation problem is closely related to the tourist trip design
problem covered in the operations research community, and consequently, there
have been various survey papers [88, 45] focusing on the aspects of problem for-
mulation, algorithmic design and the complexity of this problem. Similarly, many
tour recommendation problems are based on variants of the Orienteering Prob-
4 K. H. Lim et al.
lem (OP), and [101, 48] provide in-depth discussions on the OP. Researchers such
as [11] performed a review of tour recommendation systems, focusing on applica-
tions and systems aspects such as the types of interface, the system functionali-
ties, the recommendation techniques and the artificial intelligence methods used.
Others studied recommendations in general on location-based social networks [5]
and the general types of research utilizing Flickr photos [90], with a small portion
of their survey covering tourism-related applications. While these articles offer
interesting discussions into different aspects of tour recommendation, this paper
differs from the earlier articles in the following ways: (i) First, we review tour
recommendation research as a holistic problem, covering the whole process from
data collection, data pre-processing, tour itinerary recommendation, experimen-
tation and evaluation; and (ii) Second, we provide a comprehensive review of the
current state-of-the-art in tour recommendation research.
1.2. Structure and Organization
The rest of the paper is structured as follows. Section 2 discusses the different
sources and methods for obtaining tourist visit data. Section 3 describes various
tour recommendation algorithms targetted at the individual traveller. Section 4
examines the problem of recommending tours to groups of tourists and exam-
ines various algorithms and applications that aim to fulfill this task. Section 5
studies the various methodologies that can be used to evaluate the performance
of tour recommendation algorithms. Section 6 summarizes this review paper and
discusses research directions for future work.
2. Methods for Retrieving Tourist Visit Data
In all tour recommendation works, one of the initial steps is to identify an appro-
priate data source that is representative of real-life tourist trajectories. This data
source is mainly used to infer the implicit preferences of users and to evaluate the
proposed tour recommendation algorithms. Typical data sources are geo-tagged
photos or other social media, location-based social networks, or GPS-trajectory
traces. In this section, we discuss these three types of datasets with the main
focus on geo-tagged photos, which is also the most prevalent data source used in
tour recommendation works.
Mining Tourist Trajectories using Geo-tagged Photos. We first discuss
the mining of users’ past trajectories, and cover optimization-based approaches
to itinerary recommendation in the subsequent sections. Choudhury et al. [29]
was one of the earliest works to study both itinerary recommendation using an
optimization-based approach and the mining of users’ past trajectories based on
geo-tagged photos (Figure 3). Using geo-tagged Flickr photos, Choudhury et al.
construct these past trajectories using the following steps:
1. Constructing an Ordered Sequence of Relevant Photos. The entire set of photos
are first filtered to remove those that are: (i) not taken in the specific city, based
on user tags containing city names; (ii) taken in the specific city but not by
a tourist, based on the photo taking time-frame; and (iii) stamped with an
inaccurate time taken, based on comparison between taken time and upload
time. The remaining photos are then ordered in a temporal sequence.
Tour Recommendation and Trip Planning Survey 5
Fig. 3. Construction of tourist trajectories from geo-tagged photos. Retrieved from [29].
2. Mapping Photos to Popular POIs. Using a list of POIs and their the lati-
tude/longitude coordinates, the authors map the photos to a POI if either: (i)
the locations of the photo and POI differ by ≤100m; or (ii) the trigram set
similarity between the photo tags and POI name is above a threshold of 0.3.
3. Generating Timed Sequences of POI Visits. After Step 2, the authors then
determine POI visit duration and POI-to-POI travel duration based on the
photo timestamps, and the sequence of POI visits are divided into smaller sub-
sequences if two consecutive photos are taken more than eight hours apart.
Other authors such as [78, 15, 17, 20, 69, 71, 73, 72, 60, 61, 80] also adopted
variations of this approach in their tour recommendation works. Similarly, this
approach can be easily adapted to other forms of social media with a geo-tagged
location such as Tweets or Facebook posts. Apart from mining tourist trajec-
tories, many authors further refine this trajectory mining problem by assigning
categories to POIs and using these POI categories to determine the interests of
tourists. Many of these approaches are discussed later in Section 3.2.
Mining Tourist Visits on Location-based Social Networks. Another source
for obtaining tourist trajectories or visits is from Location-based Social Networks
(LBSNs) such as FourSquare or JiePang. LBSNs users are able to follow one an-
other and form friendship links, and are able to explicitly check-in to locations
or venues that they have visited. These check-in locations include POIs, restau-
rants, businesses or general venues, which can be further divided into categories
such as Food, Coffee, Nightlife, Fun and Shopping. LBSNs provide another pop-
ular source of data and have been used by numerous researchers in their tour
recommendation and path planning problems [47, 59, 37, 115, 114, 110].
GPS-based Tra jectory Traces. GPS-based trajectory traces are another pop-
ular data source commonly used for tour recommendation and path planning
problems [117, 109, 27, 119]. These traces are typically recorded based on GPS-
enabled devices such as today’s smart phones and dedicated GPS trackers. With
the advent of smart phones, such GPS-based trajectory traces are increasingly
common but privacy issues prevent such datasets from being publicly shared on
a large-scale, unlike datasets based on public geo-tagged photos and LBSNs. De-
spite the restrictions on GPS-based trajectory traces, these datasets provide a
very detailed record of a user’s movement trajectory based on fine-grained GPS
locations, in contrast to geo-tagged photos and LBSNs that only record visits to
specific POIs or locations.
3. Tour Recommendation for Individual Travellers
In this section, we first review optimization-based approaches to tour recom-
mendation that do not include any user personalization. Thereafter, we discuss
6 K. H. Lim et al.
Table 1. Survey of tour recommendation for individual travellers
Paper Popularity Interest Determines Constructs Considers Transport/
Reference -based -based Interest Itinerary Time Traffic
[24, 115, 114] Yes Yes Yes Yes Yes Yes
[15, 17, 28, 71, 73, 70, 104, 110, 54] Yes Yes Yes Yes Yes No
[100, 98] Yes Yes No Yes Yes No
[106] Yes Yes No Yes No No
[69] Yes Partly Partly Yes Yes No
[78] Yes Partly Partly No No No
[47] Yes Partly No Yes Yes No
[30, 29] Yes No No Yes Yes No
[38] Yes No No Yes Yes Yes
[44] Partly Yes No Yes Yes Yes
[60, 61] Partly Yes Yes Yes Yes Yes
[79] Partly Yes Yes Yes Yes No
[21] No Yes Partly Yes Yes Yes
[85, 9] No Yes No Yes Yes No
[40] No No No Yes Partly No
[83] No No No Yes No No
data-driven tour recommendation approaches that include personalization based
on user interests, traffic conditions, and travelling uncertainty. Table 1 presents
an overview of various works on tour recommendation for individual travellers.
3.1. Optimization-based Approaches (without Personalization)
Tour recommendation has its roots in the OP and similar variants, where a key
feature is that they do not incorporate any personalization for individual users.
As a result, the same tour itinerary is recommended to all users, given the same
starting/ending POIs and time budget as inputs.
Orienteering Problem (OP). The OP originated from a sport of the same
name, where participants visit check-points with pre-determined scores, in an
attempt to maximize their total score within a specific time. In recent years,
many tour recommendation studies have modelled tour recommendation based
on the OP and its many variants. Similarly, there have been many web applica-
tions [98, 75] developed based on variants of the OP. We first describe the original
OP [96, 101, 48] and how it is applied to the field of tour recommendation.
Many tour recommendation works are focused on individual cities, each of
which comprises a set of POIs P. For a tourist visiting a particular city, he/she
will have considerations of a certain time or distance budget B, and preferred
starting and ending POIs p1and pN, respectively. The budget typically repre-
sents the amount of time that a tourist would want to spend on a tour or the
distance that he/she is willing to travel. Similarly, the starting and ending POIs
reflect the preferences of the tourist to start the tour near a particular point (e.g.,
the tourist’s hotel) and end the tour at another point (e.g., near a restaurant
for dinner). Thus, given the set of POIs P, a budget B, starting POI p1∈P,
destination POI pN∈P, our main goal is to recommend a tour itinerary that
maximizes a particular score, while adhering to the constraints of the budget,
starting and destination POIs. We formally define this as recommending a tour
itinerary I= (p1, ..., pN) that optimizes the following objective:
Max
N−1
X
i=2
N
X
j=2
xi,j Score(i) (1)
Tour Recommendation and Trip Planning Survey 7
where xi,j = 1 if the itinerary involves travelling from POI ito j, and 0 otherwise.
Such that:
N
X
j=2
x1,j =
N−1
X
i=1
xi,N = 1 (2)
N−1
X
i=1
xi,k =
N
X
j=2
xk,j ≤1,∀k= 2, ..., N −1 (3)
N−1
X
i=1
N
X
j=2
Cost(i, j )xi,j ≤B(4)
Equation 1 aims to maximize a certain score that is allocated to POIs in the
recommended tour itinerary. This score is typically based on POI popularity,
POI alignment to user interests, or some variation of the two. Constraint 2
ensures the tour starts and ends at specific POIs, while Constraint 3 ensures
that the recommended tour itinerary comprises POIs connected as a trajectory
and no POIs are re-visited. Finally, Constraint 4 ensures that all POIs in the tour
itinerary can be visited within the budget B, where the function Cost(px, py)
determines the travelling time or distance between POI pxand POI py.
Itinerary Mining Problem. Based on the OP, [29] proposed the Itinerary
Mining Problem (IMP), which aims to find an itinerary that maximizes POI
popularity while ensuring that touring time is within a pre-determined budget.
They model POI Popularity based on the visit count by distinct tourists, transit
times between POIs based on the median transit time by all tourists, and POI
visit times based on the 75th percentile of visit time by all tourists. A recursive
greedy algorithm [22] is used to solve the IMP, where it tries to estimate the
middle node of the itinerary and the associated utility (popularity) gained and
cost (time) incurred, then recursively calls itself on both halves of the itinerary.
Tour Recommendation with Specific POI Category Sequence. Gionis et
al. [47] approached tour recommendation in a similar fashion as the OP, except
that they: (i) consider the POI categories in their tour recommendation; and (ii)
recommend tours with a specific visit order over all POI categories, e.g., Cafe →
Parks →Beach. Apart from this constraint of a POI category visit order, the
authors also consider variations of this ordering constraint, such as:
–Partial Ordering of POI Categories. Instead of a total ordering, this relaxed
constraint allows for a partial ordering of POI categories, e.g., Cafe →Parks
is a partial ordering of Cafe →Parks →Museum →Shopping.
–Subset Grouping of POI Categories. Instead of a specific order, this relaxed
constraint allows for a subset of the ordering of POI categories, e.g., a visit
order would be Cafe OR Restaurants →Beach OR Parks, instead of the
specific order Cafe →Beach →Parks.
–Skipping of POI Categories. Instead of having to visit all POI categories at
least once, this relaxed constraint allows for one or more POI categories to be
skipped, i.e., not visited in the recommended tour.
The authors proposed two schemes for evaluating the utility of each tour,
namely: (i) an additive satisfaction function on the perceived benefit from visiting
8 K. H. Lim et al.
a particular POI, based on either a general measure (e.g., POI popularity) or
personalized measure (e.g., personal satisfaction); and (ii) a coverage satisfaction
function that determines the number of additional, nearby POIs that can be
visited during the tour, i.e., POIs within a certain distance from the tour. To solve
this tour recommendation problem and the different variations of the relaxed
constraints, the authors used a dynamic programming approach.
Tour Recommendation with POI Category Visit Constraints. One pos-
sible issue with typical tour recommendations is that it may include excessive
visits to the same POI categories (e.g., visiting 10 museums for a tour), result-
ing in a “sensory overload”. To overcome this issue, Bolzoni et al. [9] proposed
the CLuster Itinerary Planning (CLIP) algorithm that aims to recommend tour
itineraries with constraints on the maximum number of times that each POI
category can be recommended. The proposed CLIP algorithm makes extensive
use of clustering and pruning techniques to reduce the search time required to
generate a tour itinerary, with the following steps:
1. CLIP first uses agglomerative clustering to group POIs into kclusters using a
bottom-up approach, based on the proximity of POIs.
2. To recommend a tour, CLIP generates a path starting from POI S, followed
by POI cluster C1,C2, ..., CN, ending at POI D, with the assumption that
the travel costs within a POI cluster are negligible.
3. After Step 2, CLIP selects a subset of individual POIs from each POI cluster,
with the aim of maximizing the obtained utility score. This selection problem
is modelled as a multi-dimensional knapsack problem.
3.2. Personalization-based Approaches
After discussing optimization-based approaches, we now review data-driven ap-
proaches to tour recommendation that include personalization to recommend a
customized and unique tour itinerary to each tourist based on their interest pref-
erences. In such personalization-based approaches, the key research challenges
are: (i) implicitly inferring the interest preferences of tourists; and (ii) incorpo-
rating these interests as part of the recommended tour itinerary.
Tour Recommendation based on Gender, Age and Race. Cheng et al. [28]
aim to recommend tours based on the current location of a user and his/her de-
mographic details such as gender, age and race, which are automatically detected
from Flickr photos using a facial detection algorithm [102]. Their tour recom-
mendation then takes two forms, namely:
1. Recommending Next POI. Using the user demographic details, the recom-
mender utilizes a Bayesian learning model that also considers the user’s cur-
rent location and their learned tourist travel model based on travel sequences
by other users with similar demographic attributes.
2. Recommending Tour Itinerary. They modelled tour recommendation as a short-
est path problem from a starting POI to destination POI, while also including
Nother POIs with POI scores based on popularity and alignment to the user
demographic profile. While there is no time or distance budget (like in typical
OPs), the authors implemented a penalty function that favours shorter paths.
A later work [26] extended upon [28] by considering the size of the group
Tour Recommendation and Trip Planning Survey 9
in which a user is travelling, i.e., individuals, friends, couples or families. They
perform this consideration by using facial recognition techniques to detect the
number of faces in a photo, thus identifying the number of travellers in a group.
TripBuilder Algorithm. Brilhante et al. [15, 17] developed the TripBuilder
algorithm for planning personalized tour itineraries for tourists based on the
Generalized Maximum Coverage problem [31]. TripBuilder aims to plan a
tour comprising POIs that maximize tourists’ personal interests while adhering
to a specific visiting time budget. TripBuilder comprises two steps:
1. Selection of Sub-trajectories. As part of the Trip Cover problem, the authors
use an approximation algorithm to select a set of sub-trajectories among POIs
that best satisfies the tourist interests and is within the specified time con-
straint.
2. Joining of Sub-trajectories. As part of the Trajectory Scheduling Problem, the
sub-trajectories found in Step 1 are then joined together to form a complete
tour itinerary using a local search algorithm.
The TripBuilder algorithm has also been developed as a web-based appli-
cation with the same name [16].
TourRecInt Algorithm. The TourRecInt algorithm [69] aims to recom-
mend tour itineraries with a mandatory-visit POI category cm. In turn, this
mandatory-visit POI category is based on the POI category that the tourist
is most interested in, which the author defined as the most frequently visited
POI category. TourRecInt is based on an OP variant with the addition of the
mandatory-visit category, which is formally defined as:
N−1
X
i=1
N
X
j=2
xi,j δ(Cati=cm)≥1,∀cm∈C(5)
where δ(Cati=cm) = 1 if Cati=cm(POI iis of category cm), and 0 otherwise.
The optimization function and other constraints are the same as the basic OP.
Other works have also studied problem variants with must-visit POIs [93].
PersTour Algorithm. The PersTour algorithm [71, 73] recommends tour
itineraries with POIs and visit durations tailored to the interest preferences of
individual tourists. This personalization is based on both POI popularity and
time-based user interests, which is a relative measure of user interest in a POI
category based on how long a tourist visits a POI compared to the average visit
duration by other tourists. Given that Suis the POI visit history of tourist u,
the time-based user interest of tourist uin POI category cis formally defined as:
IntT ime
u(c) = X
px∈Su
¯
Vu(px)
1
|T|P
t∈T
¯
Vt(px)δ(Catpx=c),∀c∈C(6)
where δ(Catpx=c) = 1 if Catpx=c, and 0 otherwise.
The function ¯
Vt(px) indicates the average amount of time spent by tourist t
at POI px, based on all the travel history of tourist t. Thereafter, the PersTour
algorithm attempts to recommend tour itineraries similar to that of the OP, with
two main differences, namely: (i) PersTour optimizes for POI popularity and
10 K. H. Lim et al.
Fig. 4. Example of an itinerary generated by Aurigo, with the Pop Radius feature (blue circle)
that allows users to add/delete POIs that are in close proximity. Retrieved from [106].
time-based user interest; and (ii) PersTour uses a time budget based on both
travelling time and a personalized POI visit duration based on user interest.
Aurigo System. Aurigo is a recommendation system that recommends person-
alized itineraries via an End-to-End mode and a Step-by-Step mode [106]. The
End-to-End mode, like the OP, aims to recommend tours with specific starting
and ending points, while maximizing POI popularity and user interests. POI
popularity is determined based on Yelp review counts and ratings, while interest
preferences are explicitly provided by users in the form of 1-5 star ratings on
each POI category. For the Step-by-Step mode, the user first chooses a starting
point then iteratively chooses the next POI to visit until he/she is satisfied with
the self-constructed itinerary. The tourist is able to modify the itinerary via a
Pop Radius feature (Figure 4), which shows all POIs within a specific radius to
a selected POI and allows for fine-tuning the recommended itinerary.
Photo2Trip System. Lu et al. [77] developed the Photo2Trip system that
utilizes 20 million geo-tagged photos and 0.2 million travelogues for the main
purposes of identifying popular POIs, POI-to-POI path discovery and tour rec-
ommendation. More specifically, Photo2Trip achieves these functions by:
1. Identifying popular attractions. Photo2Trip used MeanShift clustering to group
photos into clusters based on their location. They then picked the top 10%
largest clusters and named them based on the nearest POI in the travelogues.
2. POI-to-POI path discovery. As a single user may not post all photos of his/her
entire trajectory, Photo2Trip combine multiple fragments of photo-to-photo
paths from different users into a single POI-to-POI path based on the density
of the photo fragments and their actual distance.
3. Tour recommendation. Using the list of POIs and paths (from Steps 1 and 2),
Photo2Trip then uses Dynamic programming to find an optimal (popular and
interesting) tour that can be completed within a specific time budget.
Context-aware Tour Recommendation. Instead of mapping photos to known
POIs, Majid et al. [79] infer the location of POIs and their semantic meaning
using clustering approaches on geo-tagged photos. Their approach also infers
popular travel sequences between POIs and considers the context of the tour
recommendation, i.e., time, day and weather. In summary, [79] performs this
context-aware tour recommendation in the following steps:
Tour Recommendation and Trip Planning Survey 11
1. Inferring POI Locations. The P-DBSCAN algorithm [57] is first used to cluster
geo-tagged photos into a set of POI locations in a city. Thereafter, user tags
and Google Places data are used to determine the semantic meaning of POI.
2. Mining frequent travel sequences. Next, they mapped geo-tagged photos to
the discovered POIs to construct travel sequences and used the re-fixSpan
algorithm (partially based on [49]) for mining frequent travel patterns.
3. Determining Weather Conditions. Using the Wunderground API, the authors
then associate each POI visit with the weather conditions (temperature, wind
chill, humidity, pressure and wind speed) when the visit took place.
4. POI and Tour Recommendation. Finally, they utilized user-based collaborative
filtering to determine POI interest scores for users, then used the joint proba-
bility of POI interest scores, time and weather to determine the likelihood of
including a POI in a recommended list.
Tour Recommendation with Time-variant Interests. Instead of the OP,
Yu et al. [110] proposed a tour recommendation problem with a starting POI and
touring time budget, but with no consideration of a specific destination POI. One
key difference between this work and others is how Yu et al. proposed the idea
of time-variant interest preferences, e.g., visit tourist attractions in the morning
and have lunch at a restaurant at noon. This work uses the following steps:
1. Modelling User Interest Preferences. Interest preferences are modelled based
on six time periods throughout the day (except sleeping time from midnight
to 8am), and interest levels are based on visit frequency to POI categories.
2. Modelling POI Scores. POI scores are derived from a combination of POI
popularity (based on the number of visits to that POI in a specific month)
and the POI rating (as assigned by JiePang users to that POI).
3. POI Recommendations. This next step involves identifying POIs that are in-
teresting to the user and near the specific starting location, then ranking them
using user-based collaborative filtering [116].
4. Construction of Tour Itinerary. The final step includes constructing a tree
rooted starting at a specific POI and subsequent levels based on a list of top-N
POIs [119] for each time period. The recommended tour itinerary is determined
based on a tree traversal, where the POI-to-POI transition probability is based
on user interests, POI popularity, touring time and POI-to-POI distances.
Tour Recommendation based on Time and Seasons. Compared to other
tour recommendation systems, Jiang et al. [54] proposed a system that considers
interest preferences, POI admission costs, POI opening hours and the visiting
seasons, which they automatically obtain from geo-tagged photos and travelogue
websites. Their tour recommendation system comprises the following steps:
1. Extracting POI Statistics from Travelogues and Photos. The authors utilize
tags and description of travelogue articles to determine the various categories,
admission cost and opening hours of POIs. Photo timestamps are also used to
determine the visiting distribution at the POIs during the different seasons.
2. Determining User Interest, Cost, Time and Season Preferences. Using users’
posted photos as travel sequences, the authors determine their interest pref-
erences based on the associated tags, and cost, time and season preferences
based on photo timestamps.
12 K. H. Lim et al.
3. Tour Itinerary Recommendation. The recommended tour is personalized to
individual users based on popular routes, which are filtered to match the in-
terest, cost, time and season preferences of individual user. Using these pop-
ular routes, the authors then replace POIs with those that better match user
preferences based on a variant of collaborative filtering [64, 118].
3.3. Consideration for Situational Awareness
The consideration of user interest preferences (in the previous section) is an at-
tempt to make tour recommendations more personalized and there are various
works that incorporate other real-life considerations. Other practical consider-
ations that raise novel optimization challenges include incorporating forms of
situational awareness such as multiple modes of transport, considering traffic
conditions, POI crowdedness and queuing times and including uncertainty in
travelling times, which we discuss next.
Recommending Tours with Consideration for Traffic Conditions. Trip-
Planner [24] is a traffic-aware route planning system that recommends person-
alized routes comprising a set of must-visit POIs while considering the traffic
conditions at different POIs and times based on Foursquare check-ins and taxi
GPS traces. TripPlanner operates based on three main steps:
1. Generating a Dynamic POI Network Model. TripPlanner uses FourSquare to
determine the popularity, category, location, opening hours and visit duration
at POIs. Similarly, taxi GPS traces are used to derive the travelling time
between POIs based on a time-dependent traffic condition.
2. Searching for Possible Routes. Based on user-specified starting/destination
POIs, must-visit POIs and touring time, TripPlanner searches for valid routes
that satisfy these constraints. If no valid routes can be found, iteratively sug-
gests removals from the must-see POIs, until a valid route can be found.
3. Augmenting Routes with Preferred POIs. If the route found in Step 2 has
unused time budget, TripPlanner augments the original route with additional
POIs to maximize user satisfaction based on their interest preferences.
There have also been applications that consider time-varying travelling times
between POIs based on the traffic conditions as well as transport modes at the
time of POI departure, such as the eCOMPASS tourist tour planner [44].
In the field of Operations Research, there are also route planning works that
consider multiple transport modes and uncertain travelling times [36, 13, 12].
While these works present interesting results, they differ from our tour recom-
mendation problem as they are mainly concerned with finding the shortest path
between a starting and ending location. Similarly, researchers such as [67, 68]
incorporate traffic flow predictions into their route planning problem, enabling
them to recommend routes that avoid traffic congestion and hazards in advance.
Recommending Tours based on Interests and Different Transport Types.
Kurashima et al. [60, 61] proposed a method for tour recommendation that con-
siders the current location of the user, his/her interest preferences, available time
for touring and available means of transport. The authors use a combined topic
and Markov model to recommend POIs that are based on a user’s interest and
current location. They used Probabilistic Latent Semantic Analysis (PLSA) [51]
Tour Recommendation and Trip Planning Survey 13
as the topic model, which considers the interests of a user and models the prob-
ability of this user visiting a POI pgiven a travel history h, that is:
P(p|h) = X
z∈Z
P(z|h)P(p|z) (7)
where Zis the set of topics for the POIs, P(z|h) is the probability of a user
being interested in topic z, and P(p|z) is the probability that POI pis selected
from topic z.
For the Markov model, the authors employ a first-order Markov model, where
the probability of visiting a POI ptdepends on a previous POI visit pt−1. This
is formally defined as:
P(pt|pt−1) = N(pt−1, pt)
N(pt−1)(8)
where N(pt−1, pt) is the frequency that POI ptis visited after a prior visit to
POI pt−1, and N(pt−1) is the total visit count at POI pt−1.
The authors then combine the topic and Markov models as one single model,
using the following formula:
P(pt|pt−1, h) = P(pt|pt−1)
C(pt−1|h)
P(pt|h)
P(pt)(9)
where C(pt−1|h) is a normalization factor based on unigram rescaling [46]. This
combined topic and Markov model then recommends the next POI to visit based
on the user’s current location and his/her interest preferences. To recommend
a tour itinerary, the authors use a best-first search algorithm to select tour
itineraries with the highest probability and adhere to the available touring time.
Recommending Tours with Transport-cost Awareness. Unlike other works
that consider transportation based on traffic conditions or transport modes, [38]
included the consideration for the transport cost associated with a recommended
tour. The authors utilized geo-tagged photos to determine the popularity of POIs,
visit durations, opening hours and appropriate visual scenes to display at differ-
ent times of the day. They modelled their tour recommendation problem based
on a variant of the NP-hard Vehicle Routing Problem with Time Window [14].
In this problem, their main aim is to visit the largest number of popular POIs
and ensure that the routes taken are minimal and smooth (i.e., no long detours),
while adhering to the available touring time and transportation cost budget.
Recommending Tours based on Interests, POI Opening Hours and
Travel Time Uncertainty. Zhang et al. [115, 114] studied tour recommenda-
tion with the goal of recommending personalized itineraries based on the interest
preferences of users and available touring time, while considering opening hours
of POIs and uncertainty in travelling time. Their work involves the following:
–Modelling User Interest Preferences. The authors modelled interest preferences
based on user ratings on POI features, instead of specific POIs, using their
proposed feature-centric collaborative filtering approach [115].
–Modelling Travel Time Uncertainty. Uncertainty in travelling time is repre-
sented as a random variable associated with a particular probability distribu-
tion. This work aims to recommend tours with a high completion probability,
i.e., the likelihood of completing an itinerary within the time budget.
14 K. H. Lim et al.
E
D C
B
A
Itinerary 1 (Queue-aware)
Itinerary 2 (Non-queue)
Missed attraction
visit due to time
budget exceeded
t=1
t=2 t=3
t=4
t=5
t=1
t=2
t=3
t=4
0
500
1000
1500
2000
2500
3000
t=0 t=1 t=2 t=3 t=4 t=5 t=6
Queuing Times
at Attraction B
0
500
1000
1500
2000
2500
3000
t=0 t=1 t=2 t=3 t=4 t=5 t=6
Queuing Times
at Attraction D
Fig. 5. Example of queue-aware tour itinerary recommendation. Retrieved from [70].
–Modelling POI Opening Hours. The authors consider POI opening hours by
implementing a POI availability constraint, and adopt a tour recommenda-
tion approach by iteratively adding a POI to an itinerary if it satisfies this
constraint, along with the total time budget constraint.
Personalized Tours with Queuing Time Awareness. In tourist attractions
like theme parks, the queuing times are an important considerations when rec-
ommending a tour itinerary. Figure 5 illustrates an example where Itinerary 2
results in incomplete visits due to excessive queuing times, while Itinerary 1 is
able to complete all visits due to considering for queuing times. [70] studied
this queue-aware tour recommendation problem based on an OP variant with
time-dependent queuing times, and travel costs comprising queue times, ride du-
rations and travel times. To solve this problem, the authors proposed the PersQ
algorithm, adapted from Monte Carlo Tree Search [33, 18], which involves:
–Selection.PersQ initializes at a starting POI sand iteratively selects a
next POI nto expand based on a strategy of exploring unvisited POIs and
exploiting POIs with high reward, where the reward is based on a heuristic of
most popular/interesting POIs with the shortest distance/queuing-time.
–Expansion. If selected POI nis not the destination POI or exceeds the total
time budget, expand POI nand randomly select one of the unvisited POIs.
–Simulation. Steps 1 and 2 are then iteratively simulated until either the total
time budget is exhausted or the specified destination POI is reached.
–Back-propagation. During this step, the current itinerary is the set of all
POIs visited and the reward for this itinerary is calculated then back-propagated
to all the visited POI during this iteration.
Steps 1 to 4 are considered one iteration of PersQ, and PersQ is then
repeated for either a fixed number of iterations or for a fixed time period. At the
end of these multiple iterations, there will be multiple itineraries being explored
and the recommended itinerary is the one with the highest reward.
Personalized Crowd-aware Tour Recommendation. Wang et al. [104] stud-
ied personalized crowd-aware tour recommendation, with the main objective
of planning itineraries that optimize the conflicting objectives of POI popular-
ity, user interests and POI crowdedness. The authors determine POI popularity
Tour Recommendation and Trip Planning Survey 15
based on past visit frequency, user interests using user-based collaborative fil-
tering [113], and POI crowdedness from a pedestrian sensor dataset. Using a
variant of the Ant Colony Optimization algorithm [34], the authors proposed
the PersCT algorithm for solving this problem. PersCT utilizes a number of
agents and works in two main steps:
1. Route Initialization. Agents start at a specific POI and iteratively visit next
POIs until reaching the destination POI. The selection of next POI favours
those with higher profits, nearer to the destination, and recently selected.
2. Route Update. After the previous step and all agents have generated itineraries,
the itinerary with the highest profit (based on POI popularity, user interests
and POI crowdedness) is recorded before being de-emphasized over time.
Steps 1 and 2 are repeated a fixed number of times and PersCT will lean
towards itineraries with high profits that were recently used by agents. Eventu-
ally, the recommended tour itinerary is the one with the highest profit based on
the joint objectives of POI popularity, user interests and POI crowdedness.
3.4. Other Approaches
While user personalization and real-life traffic/transport considerations are im-
portant, there are tourists that emphasize different aspects of travelling, such as
recommending routes that may not be the most popular but are the most scenic
or safest. In the following sections, we present some of these works.
Recommending beautiful, quiet and happy routes. Instead of popular or
personalized routes, [83] recommended routes that are emotionally pleasing, i.e.,
beautiful, quiet and happy. They use crowd-sourcing to identify photos that are
beautiful, quiet or happy, with photos corresponding to specific locations with
their perceived scores. Thereafter, they recommend tours as follows:
1. Given a starting point sand destination d, use Eppstein’s algorithm [35] to
recommend the Mshortest routes from sto d, where Mis set to be arbitrarily
large (e.g., 1 million) such that it covers all possible routes.
2. Given k≤M, calculate the average beauty, quietness or happiness rank for
each of the top-kroutes and record the route with the best rank. Instead of
all Mroutes, the intuition is to iteratively explore a smaller set of kroutes.
3. Repeat Step 2 for the next kroutes and identify the route with the best rank.
This step repeats until the improvement is less than a threshold , and the
last route is recommended as the most beautiful, quietest or happiest route.
Quercia et al. also utilized the user tags of photos to determine how beautiful,
quiet and happy each photo is, based on the Linguistic Inquiry Word Count
dictionary [81]. Similarly, the ScenicPlanner system [23] also used Flickr photos
and FourSquare check-ins to determine scenic scores for individual road segments
as part of a larger scenic route planning problem. Other researchers have also
focused on other aspects of non-touristic tour recommendations, such as [40, 39,
55] who used crime statistics for recommending short but safe paths.
Random Walks with Restart. Also using geo-tagged photos, Lucchese et
al. [78] recommended POI visits using random walks on a graph-based represen-
tation of past tourist trajectories. This algorithm comprises the following steps:
16 K. H. Lim et al.
1. The authors first construct an itinerary graph G= (P, E , W ), where Pis the
set of all POIs, Eis the set of edges representing co-visits to two POIs, and
Wis the edge weight based on unique visitors of that POI pair.
2. Itinerary graph Gis then transformed into an itinerary transition matrix, with
the transition probability between POIs. The authors then use the Random
Walk with Restart algorithm [94] to compute the steady-state probability dis-
tribution for the set of POIs previously visited by the tourist.
3. Using the itinerary transition matrix, tourist POI visit history and its steady-
state probability distribution, they calculate the scores of the unvisited POIs
based on the product of entries in the steady-state probability distribution. Fi-
nally, the algorithm then recommends the top-kPOIs with the highest scores,
which can be constructed as a connected itinerary.
3.5. Web and Mobile-based Applications
In this section, we examine various web and mobile-based applications for rec-
ommending personalized tours. Unlike the personalization-based approaches that
infer interest preferences (previous section), these applications employ user in-
terfaces to explicitly solicit interest preferences from tourists before using these
interest preferences to recommend personalized tour itineraries.
City Trip Planner. This system was proposed by Vansteenwegen et al. [100] for
recommending personalized tours in five cities in Flanders, Belgium (Antwerp,
Bruges, Ghent, Leuven and Mechlin) based on user-provided interest preferences.
The City Trip Planner works in the following steps: (i) soliciting trip constraints
such as the trip duration, starting/ending locations and break timings; (ii) esti-
mating user interests using the Vector Space Model [4, 89] on the user-provided
interest levels in various POI categories; (iii) recommending tours using a Greedy
Randomised Adaptive Search Procedure [99]; and (iv) altering the recommended
tour based on user feedback, i.e., removing specific POIs.
myVisitPlannerGR.myVisitPlannerGR is a web-based application that is tar-
getted at recommending touristic activities to visitors of Northern Greece [85].
There are three main steps to using the myVisitPlannerGR system, namely: (i)
getting users to provide their demographics details and trip constraints; (ii) sug-
gesting activities using a hybrid recommender based on a variant of collaborative
filtering on user-rated activities; and (iii) recommending an itinerary of suggested
activities using the scheduling engine of SelfPlanner [84, 86]. This system uses
an ontological approach to represent activities where there are multiple hierar-
chical levels. Activity providers have the flexibility to describe their activity at a
higher, more general hierarchical level or a lower, more specific level. In addition,
the system keeps track of the ratings that users assign to the various activities
and uses these ratings as input to their hybrid recommender system.
SAMAP System. The authors of [21] proposed the SAMAP system for recom-
mending and planning a personalized daily itinerary that considers his/her user
profile and available touring time. SAMAP was designed for mobile devices such
as smart phones and operates as a multi-agent system, comprising the following
agents: (i) first, an interface agent that solicits interests, trip preferences and
personal information from the tourist; (ii) next, a user modelling agent builds a
Tour Recommendation and Trip Planning Survey 17
Table 2. Survey of Tour Recommendation for Groups of Tourists
Paper Popularity Interest Determines Constructs Considers Transport/ Tour
Reference -based -based Interest Itinerary Time Traffic Guides
[72] Yes Yes Yes Yes Yes No Yes
[26] Yes Yes Yes Yes Yes No No
[2, 87] Yes Yes Yes Yes Yes No No
[42, 43] Yes Yes Partly Yes Yes No No
[3] No Yes No Yes Yes Yes No
[53] No Yes No No No No No
model of the user to pass to the next agent; (iii) a case-based reasoning agent then
identifies a set of POIs that are aligned to the user’s interest, based on the pref-
erences of similar users; and (iv) finally, a planning agent schedules an itinerary
comprising a subset of the earlier POIs that maximizes the tourist’s utility score,
while accounting for POI opening hours and transport modes between POIs.
Thus far, we have examined tour itinerary recommendation for individual
travellers and covered optimization-based approaches, personalization-based ap-
proaches, and web and mobile-based applications. In real-life, people frequently
travel in groups of varying sizes, such as couples, family and friends, and we
discuss such works in the next section.
4. Tour Recommendation for Groups of Tourists
Tour recommendation research typically focus on the single traveller, as seen in
Section 3. In real-life however, tours frequently involve multiple travellers such
as couples, friends or families, which are challenging due to the need to appeal
to multiple travellers within the same group. In the next section, we examine
some early efforts on resolving this group tour recommendation problem. Table 2
presents a broad overview of the various group tour recommendation works.
Group Tours with Tour Guides. Lim et al. introduced the Group Tour
Recommendation (GroupTourRec) problem, where the main aim is to recom-
mend tours that satisfy groups of tourists with diverse interest preferences [72].
They solve the GroupTourRec problem by decomposing the problem into
more manageable sub-problems of tourist grouping, POI recommendation and
tour guide assignment. Given the set of tourists T={t1, ..., tl}, tour guides
U={u1, ..., um}, tour groups G={g1, ..., gm}, and POIs P={p1, ..., pn}, the
main goal of GroupTourRec is to optimize the following function:
Maxα X
g∈GX
t∈TX
p∈P
xt,gyg ,pηIntt(C atp) + (1 −η)P op(p)
+(1 −α)X
g∈GX
u∈UX
p∈P
zu,gyg ,pEpt(u, p)
(10)
where xt,g = 1 if tourist tis assigned to group g,yg,p = 1 if group gis recom-
mended POI p,zu,g = 1 if tour guide uis assigned to group g, and 0 otherwise.
In short, the main objectives of Equation 10 are to find optimal values for:
(i) tourist allocation to tour group, i.e., xt,g ; (ii) POI recommendation to tour
group, i.e., yg,p; and (iii) tour guide assignment to tour group, i.e., zu,g.Group-
TourRec is divided into more manageable sub-problems and solved by: (i) using
18 K. H. Lim et al.
k-means to cluster users into tour groups based on their interest preferences; (ii)
using an OP variant for recommending itineraries to tour groups based on their
group interest; and (iii) using integer programming to assign tour guides to tour
groups based on the guide expertise and recommended itineraries.
Group Tours with Pre-assigned Groups. Anagnostopoulos et al. [2] also
proposed similar group tour recommendation problems, focusing on recommend-
ing tour itineraries that best satisfy a group of tourists, which is pre-determined
in advance. These are termed the TourGroupSum,TourGroupMin and Tour-
GroupFair problems, which differ based on the objective function to be opti-
mized. Instead of solving these problems as an Integer Linear Program like [72],
they utilized greedy heuristics and Ant Colony Optimization to solve their group
tour recommendation problems. Another difference is that [2] did not consider
the assignment of tour guides to lead each tour group, but they consider multiple
forms of optimization objectives to maximize the overall group interest (Tour-
GroupSum), interest of the least satisfied user (TourGroupMin) and fairness
among all members of a group (TourGroupFair).
e-Tourism System.e-Tourism [42, 43] is a system that aims to recommend
interesting activities (including POI visits) to either individuals or groups of
tourists. There are several main steps in using the e-Tourism system, namely:
1. Provide Tourist Profile and Groupings. The individual traveller first provides
his/her demographic details and interest preferences, and additionally, groups
of tourists need to explicitly state the members of their group.
2. Recommendation to Individuals and Groups. e-Tourism recommends a list
of activities or POIs to individual tourists, using approaches based on demo-
graphics [19], content [19], general likes-based filtering [50] or a hybrid. For
groups of tourists, a group interest preference is calculated using aggregation or
intersection techniques on the preferences of individual tourists in that group.
3. Tourist Feedback. Each tourist is able to rate individual items in the recom-
mended itineraries, which is used to improve future recommendations.
One unique characteristic of e-Tourism is their representation of tourist inter-
est preferences, which are based on a hierarchical taxonomy of features instead of
explicit POI categories. This approach provides a general representation of items
and allows the system to be easily generalized to other application domains.
Intrigue System. INteractive TouRist Information GUidE (or Intrigue) is a
web and mobile based system that aims to recommend tours to both individ-
uals and groups of tourists [3]. For a group of tourists, the usage scenario for
Intrigue is that a specific (lead) tourist will use the system to: (i) indicate the
number of tourists in that tour group; (ii) manually specify the sub-group that
each tourist belongs to, based on the tourist demographics (e.g., age and back-
ground) and interest preferences; and (iii) enter details about each sub-group via
a registration form (an optional step). The main idea is that a large tour group
could be divided into smaller homogeneous sub-groups, e.g., a particular sub-
group could be defined by the characteristics of ages ranging from 30 to 40 years
old, backgrounds in engineering, and interests in architecture and museums. The
tour recommendation occurs in an iterative fashion that involves the tourist in-
dicating their trip constraints and explicitly adding recommended POIs, before
Intrigue schedules an itinerary based on selected POIs and trip constraints.
Tour Recommendation and Trip Planning Survey 19
Travel Decision Forum. The Travel Decision Forum [53] was one of the ear-
lier applications that focused on group recommendations in the context of tour
planning. This system utilizes group-oriented interfaces and virtual agents to en-
hance mutual awareness among group members for soliciting interest preferences
to resolving conflicted preferences. Some key features of this application are:
–Solicitation of Interest Preferences. Interest preferences are solicited in the
form of user ratings and importance, which are viewable by all group members.
–Generation of Proposal. Solutions are generated using either average/median
rating, random choice or a non-manipulable, joint-rating mechanism [32].
–Discussion of Proposal. Each user can either accept the proposed solution or
discuss with other users to come to a mutually-agreeable solution.
While Travel Decision Forum is used for tourism purposes, its main purpose
is to solicit and de-conflict group interest preferences using interaction-based
techniques. Additional work is required to translate these group interests into
the recommendation of relevant POIs as a group tour itinerary.
Top-k group recommendations. Closely related to the group tour recom-
mendation problem are the problems of top-k recommendations for groups and
group recommendation, where the main objective is to recommend a ranked list
or set of items that are of relevance to a group of users. These problems typically
focus on retail items such as films, songs or books, with [87] recommending sets
of POIs as items but not in the form of an itinerary. More specifically, [87] exam-
ined the problem of group formation such that the constructed group comprises
members who are more likely to prefer a top-k item recommendation. Others
have studied a related problem where the group members are pre-determined,
and the objective is to model a collective group preference and/or recommend
items to each group. For example, [52] proposed an algorithm for representing
group preferences as a set of high level features that are not biased towards spe-
cific individuals, using collective deep belief networks and dual-wing restricted
Boltzmann machines. Others like [1] tried to derive a group consensus score that
maximizes item satisfaction for all members of a group, while minimizing the
level of disagreement among members of the group. Yuan et al. [111] proposed a
probabilistic model for group recommendations that accounts for group members
with different levels of influence and how user preferences change when acting as
an individual compared to being a member of a group.
While these works are targetted at groups of users, their main objective is
to recommend either a ranked list of items or a set of items, which are typically
retail items and merchandise. Although these works can be adapted to tourism
by treating individual POIs as items, they do not recommend these POIs as
a connected itinerary nor do they consider the various spatial and temporal
constraints that are associated with tour planning. For a more comprehensive
review on group recommendation research, we refer the interested reader to [10].
5. Evaluation Strategies
A key process in tour recommendation research is the evaluation of the recom-
mended tour itineraries, namely how well they satisfy the requirements of the in-
dividual tourists. However, there are many interpretations of these requirements,
thus leading to a variety of evaluation strategies used by the various works in
20 K. H. Lim et al.
this area. In this section, we aim to highlight the various forms of evaluation
strategies, and discuss the advantages and disadvantages for each of them.
5.1. Real-life Evaluations
We classify an evaluation strategy as a real-life evaluation if the recommended
itineraries are compared against the real-life travel history of a tourist. As dis-
cussed in Section 2, these real-life travel histories can be obtained from various
sources, namely: (i) geo-tagged photos; and (ii) location-based check-ins. For
both of these sources, the real-life visits of tourists can be narrowed down to in-
dividual POIs, which allow a researcher to compare the POIs in a recommended
itinerary against the real-life POI visits by tourists. To facilitate such a compar-
ison, various Information Retrieval (IR) based metrics are used, such as:
1. Precision. The proportion of recommended POIs that were also visited by
the tourist in real-life.
2. Recall. The proportion of POIs visited by the tourist in real-life that were
also recommended.
3. F1-score. The harmonic mean of both precision and recall.
Other definitions of Precision, Recall and F1-score include variants to mea-
sure how well the categories of POIs in the recommended tour reflect the POI
categories that were visited in real-life, i.e., how well the recommendations match
real-life user preferences [15, 17]. Similarly, Chen et al. [25] used variants that
account for POI visit orders in real-life, while others [71, 73] used root-mean-
square error to determine the variations between recommend POI visit durations
and real-life visits.
5.2. Heuristic-based Evaluations
In cases where the real-life travel histories of tourists are not available, or as a sup-
plemental analysis to the IR-based metrics introduced in Section 5.1, heuristic-
based metrics are often used to evaluate the effectiveness of the recommended
itineraries. Some examples of heuristic-based metrics are:
1. Total POIs Recommended. The total number of POIs recommended to a
tourist as part of an itinerary.
2. POI Popularity. The summation of popularity scores of all POIs recom-
mended to a tourist, i.e., total tour popularity.
3. Tourist Interests. The summation of interest alignment scores of all POIs
recommended to a tourist, i.e., total tour interest.
Apart from using the summation of POI popularity and tourist interests,
possible variations include using other statistical values based on the average,
median, minimum, maximum or other percentile/quartile values. Particularly for
group tour recommendation, the minimum and maximum tour interest values
would respectively reflect the least and most satisfied tourist in a group. Novelty
is another important aspect of recommendations, thus another measure would
be based on how new and interesting recommended POIs are.
Tour Recommendation and Trip Planning Survey 21
5.3. Crowd-based Evaluations and User Studies
In contrast to the quantitative measures used in the real-life and heuristic-based
evaluations (covered in the previous sections), an alternative evaluation method-
ology is to utilize qualitative measures, which are typically smaller in scale but
more detailed in scope. Examples of such qualitative measures are:
– User Studies. This evaluation involves a small number of experiment par-
ticipants using the proposed tour recommendation system and other baseline
systems, before answering a survey based on subjective criteria, such as the us-
ability of the system. For example, [106] utilized user studies of 10 participants
comparing their Aurigo system against the baseline Google Maps.
– Crowd-based Evaluations. Crowdsourcing services, like Amazon Mechan-
ical Turk (AMT), are another popular platform for evaluation purposes with
more focus on the recommendation results, i.e., the tour itineraries. In contrast,
user studies focus on the user experience in using the tour recommendation sys-
tem. For example, [30, 29] used AMT workers to evaluate their recommended
tour itineraries against baseline itineraries by tour agencies.
One key advantage of these evaluations is that they provide us with infor-
mation regarding active user volumes and user feedback, thus serving as real-life
indicators of how successful a specific system or algorithm is.
5.4. Online Controlled Experiments
Online companies such as Google, Microsoft and Yahoo! frequently use online
controlled experiments to evaluate the effects of website user interface and de-
sign changes on live users in a real-life setting [92, 58, 74, 63]. Such experiments
involve showing a specific design or algorithmic variant to a user group, while
an alternative variant is shown to another user group. Similarly, tour recom-
mendation systems can utilize online controlled experiments on a smaller subset
of users before introducing new features. The evaluation of these features could
include:
– Design-based Variants. The evaluation of changes to a website user inter-
face, which could include the way recommended tours are displayed or the
design of a form to solicit user information.
– Algorithm-based Variants. The evaluation of changes to the underlying
tour recommendation algorithms, e.g., comparing a Naive Bayes recommender
against a popularity-based recommender such as in [56].
More importantly, online experiments serve as a form of implicit user feed-
back, which allows us to determine the interest level of users based on their
interactions with the tour recommendation systems.
6. Conclusion and Future Directions
We have provided a comprehensive review of the literature in the area of tour
itinerary recommendation and highlighted the key differences between tour itinerary
22 K. H. Lim et al.
recommendation and the related areas of Operations Research, next-location pre-
diction, top-k location recommendation and travel package/region recommenda-
tion. We developed a taxonomy to describe general touring-related research, with
a detailed breakdown of tour itinerary recommendations based on various real-
life considerations such as POI popularity, user interests, time constraints, user
demographics, transport modes and traffic conditions. In addition to reviewing a
large selection of tour itinerary recommendation problems and solutions, we also
discuss the various types of datasets (geo-tagged social media, location-based
social networks, and GPS trajectory traces) and evaluation methodologies (real-
life and heuristic-based metrics, user studies and online experiments) that can
be employed in tour itinerary recommendation research.
Based on our survey, we observed a trend of tour recommendations that
originated from optimization approaches and moving towards personalized and
context-aware approaches with the prevalence of big social data. Although tour
itinerary recommendation has been well-studied in recent years, there still remain
interesting research directions to explore. Moving forward, we highlight future
directions that consider various new context and personalization, such as:
–Consideration of Transport Modes. Future tour itinerary recommenda-
tion research can consider multiple modes of transport (e.g., walking, bus,
train, taxi, car), instead of a single type of transport, with an objective of min-
imizing changing and waiting time when switching between transport modes.
Another research direction is incorporate constraints on transport modes to
cater to different demographics group, e.g., adults (all transport modes), fam-
ilies with babies or the elderly (all transport modes except walking).
–Dynamic Tour Recommendation. As environment may change during the
course of a tour, another possibility for future work is to develop dynamic tour
recommendation algorithms that adapt to these changing contexts during a
pre-planned tour, e.g., bad weather, human fatigue, traffic congestion. For
example, a tourist completed half of a recommended tour itinerary before it
started to rain, in which case the algorithm should modify the remaining tour
itinerary to include POIs that are indoor and linked by shelter.
–Country-specific Tour Recommendation. Politics, economy and culture
are also important considerations for a tourist to visit a specific city or country,
e.g., tourists might prefer visa-free countries or countries speaking the same
language. Thus, an interesting future direction would be to consider the home
country of the tourist, before recommending tours in countries that matches
his/her preferences for certain political, economical and cultural status.
–Explicit Feedback and Improvements. Another possible future enhance-
ment is to incorporate mechanisms for obtaining explicit feedback (e.g., user
ratings) or implicit signals (e.g., length of time at POIs), which can serve:
(i) as an evaluation metric to measure user satisfaction; (ii) to build a more
accurate interest model for returning user; and (iii) to improve future tour
recommendations by avoiding POIs with negative feedback.
–Sentiment and Activity-based User Interests. Current tour recommen-
dations typically model user interests based on visit counts to specific POIs or
POI categories, but do not consider the sentiments towards these POIs or the
type of activities. Future work can utilize sentiment analysis or topic modelling
techniques to better model sentiments and activities at specific POIs, leading
to a more fine-grained model of user interests for tour recommendations.
Tour Recommendation and Trip Planning Survey 23
–Cold-start Tour Recommendation. For the widespread adoption of auto-
mated tour recommendation systems, there is a need to address the cold-start
problem of determining the interest preferences of new users with no previous
travel history. Future work can infer interest preferences of users based on
other sources of information, e.g., demographic details or interests of friends.
References
[1] S. Amer-Yahia, S. B. Roy, A. Chawlat, G. Das, and C. Yu. Group recommendation:
Semantics and efficiency. In Proc. of VLDB’09, pages 754–765, 2009.
[2] A. Anagnostopoulos, R. Atassi, L. Becchetti, A. Fazzone, and F. Silvestri. Tour recom-
mendation for groups. Data Mining and Knowledge Discovery, pages 1–32, 2016.
[3] L. Ardissono, A. Goy, G. Petrone, M. Segnan, and P. Torasso. Intrigue: personalized rec-
ommendation of tourist attractions for desktop and hand held devices. Applied Artificial
Intelligence, 17(8-9):687–714, 2003.
[4] R. Baeza-Yates and B. Ribeiro-Neto. Modern information retrieval. Addison-Wesley,
1999.
[5] J. Bao, D. W. Yu Zheng, and M. Mokbel. Recommendations in location-based social
networks: A survey. GeoInformatica, 19(3):525–565, 2015.
[6] R. Baraglia, C. I. Muntean, F. M. Nardini, and F. Silvestri. Learnext: learning to predict
tourists movements. In Proc. of CIKM’13, pages 751–756, 2013.
[7] I. Benouaret and D. Lenne. A composite recommendation system for planning tourist
visits. In Proc. of WI’16, pages 626–631, 2016.
[8] I. Benouaret and D. Lenne. A package recommendation framework for trip planning
activities. In Proc. of RecSys’16, pages 203–206, 2016.
[9] P. Bolzoni, S. Helmer, K. Wellenzohn, J. Gamper, and P. Andritsos. Efficient itinerary
planning with category constraints. In Proc. of SIGSPATIAL’14, pages 203–212, 2014.
[10] L. Boratto and S. Carta. State-of-the-art in group recommendation and new approaches
for automatic identification of groups. In Information Retrieval and Mining in Distributed
Environments, pages 1–20. Springer Berlin Heidelberg, 2011.
[11] J. Borr`as, A. Moreno, and A. Valls. Intelligent tourism recommender systems: A survey.
Expert Systems with Applications, 41(16):7370–7389, 2014.
[12] A. Botea and S. Braghin. Contingent versus deterministic plans in multi-modal journey
planning. In Proc. of ICAPS’15, pages 268–272, 2015.
[13] A. Botea, E. Nikolova, and M. Berlingerio. Multi-modal journey planning in the presence
of uncertainty. In Proc. of ICAPS’13, pages 20–28, 2013.
[14] O. Braysy and M. Gendreau. Vehicle routing problem with time windows. Transportation
Science, 39(1):104–118, 2005.
[15] I. Brilhante, J. A. Macedo, F. M. Nardini, R. Perego, and C. Renso. Where shall we go
today? Planning touristic tours with TripBuilder. In Proc. of CIKM’13, pages 757–762,
2013.
[16] I. Brilhante, J. A. Macedo, F. M. Nardini, R. Perego, and C. Renso. TripBuilder: A tool
for recommending sightseeing tours. In Proc. of ECIR’14, pages 771–774, 2014.
[17] I. R. Brilhante, J. A. Macedo, F. M. Nardini, R. Perego, and C. Renso. On planning
sightseeing tours with TripBuilder. Information Processing & Management, 51(2):1–15,
2015.
[18] C. B. Browne, E. Powley, D. Whitehouse, S. M. Lucas, P. I. Cowling, P. Rohlfshagen,
S. Tavener, D. Perez, S. Samothrakis, and S. Colton. A survey of monte carlo tree search
methods. IEEE Tran. on Computational Intelligence and AI in Games, 4(1):1–43, 2012.
[19] R. Burke. Hybrid web recommender systems. In The Adaptive Web, pages 377–408.
Springer Berlin/Heidelberg, 2007.
[20] G. Cai, K. Lee, and I. Lee. Itinerary recommender system with semantic trajectory pattern
mining from geo-tagged photos. Expert Systems with Applications, 94:32–40, 2018.
[21] L. Castillo, E. Armengol, E. Onaind´ıa, L. Sebasti´a, J. Gonz´alez-Boticario, A. Rodr´ıguez,
S. Fern´andez, J. D. Arias, and D. Borrajo. SAMAP: An user-oriented adaptive system
for planning tourist visits. Expert Systems with Applications, 34(2):1318–1332, 2008.
[22] C. Chekuri and M. Pal. A recursive greedy algorithm for walks in directed graphs. In
Proc. of FOCS’05, pages 245–253, 2005.
[23] C. Chen, X. Chen, Z. Wang, Y. Wang, and D. Zhang. Scenicplanner: planning scenic travel
24 K. H. Lim et al.
routes leveraging heterogeneous user-generated digital footprints. Frontiers of Computer
Science, 11(1):61–74, 2017.
[24] C. Chen, D. Zhang, B. Guo, X. Ma, G. Pan, and Z. Wu. TripPlanner: Personalized
trip planning leveraging heterogeneous crowdsourced digital footprints. IEEE Tran. on
Intelligent Transportation Systems, 16(3):1259–1273, 2015.
[25] D. Chen, C. S. Ong, and L. Xie. Learning points and routes to recommend trajectories.
In Proc. of CIKM’16, pages 2227–2232, 2016.
[26] Y.-Y. Chen, A.-J. Cheng, and W. H. Hsu. Travel recommendation by mining people
attributes and travel group types from community-contributed photos. IEEE Tran. on
Multimedia, 15(6):1283–1295, 2013.
[27] Z. Chen, H. T. Shen, and X. Zhou. Discovering popular routes from trajectories. In Proc.
of ICDE’11, pages 900–911, 2011.
[28] A.-J. Cheng, Y.-Y. Chen, Y.-T. Huang, W. H. Hsu, and H.-Y. M. Liao. Personalized
travel recommendation by mining people attributes from community-contributed photos.
In Proc. of MM’11, pages 83–92, 2011.
[29] M. D. Choudhury, M. Feldman, S. Amer-Yahia, N. Golbandi, R. Lempel, and C. Yu.
Automatic construction of travel itineraries using social breadcrumbs. In Proc. of HT’10,
pages 35–44, 2010.
[30] M. D. Choudhury, M. Feldman, S. Amer-Yahia, N. Golbandi, R. Lempel, and C. Yu. Con-
structing travel itineraries from tagged geo-temporal breadcrumbs. In Proc. of WWW’10,
pages 1083–1084, 2010.
[31] R. Cohen and L. Katzir. The generalized maximum coverage problem. Information
Processing Letters, 108(1):15–22, 2008.
[32] V. Conitzer and T. Sandholm. Complexity of mechanism design. In Proc. of UAI’02,
pages 103–110, 2002.
[33] R. Coulom. Efficient selectivity and backup operators in monte-carlo tree search. In Proc.
of CCG’06, pages 72–83, 2006.
[34] M. Dorigo, M. Birattari, and T. St¨utzle. Ant colony optimization. IEEE Computational
Intelligence Magazine, 1(4):28–39, 2006.
[35] D. Eppstein. Finding the k shortest paths. SIAM J. on Computing, 28(2):652–673, 1998.
[36] J. E. Fl´orez, A. T. A. de Reyna, C. L. L. Javier Garc´ıa, A. G. Olaya, and D. Borrajo.
Planning multi-modal transportation problems. In Proc. of ICAPS’11, pages 66–73, 2011.
[37] Z. Friggstad, S. Gollapudi, K. Kollias, T. Sarlos, C. Swamy, and A. Tomkins. Orienteering
Algorithms for Generating Travel Itineraries? In Proc. of WSDM’18, pages 180–188, 2018.
[38] C.-Y. Fu, M.-C. Hu, J.-H. Lai, H. Wang, and J.-L. Wu. Travelbuddy: Interactive travel
route recommendation with a visual scene interface. In Proc. of MMM’14, pages 219–230,
2014.
[39] E. Galbrun, K. Pelechrinis, and E. Terzi. Safe navigation in urban environments. In Proc.
of UrbComp’14, 2014.
[40] E. Galbrun, K. Pelechrinis, and E. Terzi. Urban navigation beyond shortest route: The
case of safe paths. Information Systems, 57:160–171, 2016.
[41] H. Gao, J. Tang, and H. Liu. Exploring social-historical ties on location-based social
networks. In Proc. of ICWSM’12, pages 114–121, 2012.
[42] I. Garcia, L. Sebastia, and E. Onaindia. On the design of individual and group recom-
mender systems for tourism. Expert Systems with Applications, 38(6):7683–7692, 2011.
[43] I. Garcia, L. Sebastia, E. Onaindia, and C. Guzman. A group recommender system for
tourist activities. In Proc. of EC-WEB’09, pages 26–37, 2009.
[44] D. Gavalas, V. Kasapakis, C. Konstantopoulos, G. Pantziou, N. Vathis, and C. Zaro-
liagis. The ecompass multimodal tourist tour planner. Expert Systems with Applications,
42(21):7303–7316, 2015.
[45] D. Gavalas, C. Konstantopoulos, K. Mastakas, and G. Pantziou. A survey on algorithmic
approaches for solving tourist trip design problems. J. of Heuristics, 20(3):291–328, 2014.
[46] D. Gildea and T. Hofmann. Topic-based language models using em. In Proc. of Eu-
roSpeech’99, 1999.
[47] A. Gionis, T. Lappas, K. Pelechrinis, and E. Terzi. Customized tour recommendations in
urban areas. In Proc. of WSDM’14, pages 313–322, 2014.
[48] A. Gunawan, H. C. Lau, and P. Vansteenwegen. Orienteering problem: A survey of
recent variants, solution approaches and applications. Euro. J. of Operational Research,
255(2):315–332, 2016.
[49] J. Han, J. Pei, B. Mortazavi-Asl, H. Pinto, Q. Chen, U. Dayal, and M. C. Hsu. Prefixspan:
Tour Recommendation and Trip Planning Survey 25
Mining sequential patterns efficiently by prefix-projected pattern growth. In Proc. of
ICDE’01, pages 215–224, 2001.
[50] U. Hanani, B. Shapira, and P. Shoval. Information filtering: Overview of issues, research
and systems. User Modeling and User-Adapted Interaction, 11(3):203–259, 2001.
[51] T. Hofmann. Probabilistic latent semantic indexing. In Proc. of SIGIR’99, pages 50–57,
1999.
[52] L. Hu, J. Cao, G. Xu, L. Cao, Z. Gu, and W. Cao. Deep modeling of group preferences
for group-based recommendation. In Proc. of AAAI’14, pages 1861–1867, 2014.
[53] A. Jameson, S. Baldes, and T. Kleinbauer. Enhancing mutual awareness in group recom-
mender systems. In Proc. of ITWP’03, 2003.
[54] S. Jiang, X. Qian, T. Mei, and Y. Fu. Personalized travel sequence recommendation on
multi-source big social media. IEEE Tran. on Big Data, 2(1):43–56, 2016.
[55] A. Keler and J. D. Mazimpaka. Safety-aware routing for motorised tourists based on open
data and vgi. J. of Location Based Services, 10(1):64–77, 2016.
[56] J. Kiseleva, M. J. Mueller, L. Bernardi, C. Davis, I. Kovacek, M. S. Einarsen, J. Kamps,
A. Tuzhilin, and D. Hiemstra. Where to go on your next trip?: Optimizing travel desti-
nations based on user preferences. In Proc. of SIGIR’15, pages 1097–1100, 2015.
[57] S. Kisilevich, F. Mansmann, and D. Keim. P-dbscan: a density based clustering algorithm
for exploration and analysis of attractive areas using collections of geo-tagged photos. In
Proc. of COM.Geo’10, page 38, 2010.
[58] R. Kohavi, A. Deng, B. Frasca, T. Walker, Y. Xu, and N. Pohlmann. Online controlled
experiments at large scale. In Proc. of KDD’13, pages 1168–1176, Aug 2013.
[59] S. Kotiloglu, T. Lappas, K. Pelechrinis, and P. Repoussis. Personalized multi-period tour
recommendations. Tourism Management, 62:76–88, 2017.
[60] T. Kurashima, T. Iwata, G. Irie, and K. Fujimura. Travel route recommendation using
geotags in photo sharing sites. In Proc. of CIKM’10, pages 579–588, 2010.
[61] T. Kurashima, T. Iwata, G. Irie, and K. Fujimura. Travel route recommendation using
geotagged photos. Knowledge and Information Systems, 37(1):37–60, 2013.
[62] K. W.-T. Leung, D. L. Lee, and W.-C. Lee. Clr: a collaborative location recommendation
framework based on co-clustering. In Proc. of SIGIR’11, pages 305–314, 2011.
[63] R. A. Lewis, J. M. Rao, and D. H. Reiley. Here, there, and everywhere: Correlated online
behaviors can lead to overestimates of the effects of advertising. In Proc. of WWW’11,
pages 157–166, Mar 2011.
[64] Q. Li, Y. Zheng, X. Xie, Y. Chen, W. Liu, and W.-Y. Ma. Mining user similarity based
on location history. In Proc. of SIGSPATIAL’08, page 34, 2008.
[65] X. Li, G. Cong, X.-L. Li, T.-A. N. Pham, and S. Krishnaswamy. Rank-geofm: a ranking
based geographical factorization method for point of interest recommendation. In Proc.
of SIGIR’15, pages 433–442, 2015.
[66] D. Lian, V. W. Zheng, and X. Xie. Collaborative filtering meets next check-in location
prediction. In Proc. of WWW’13, pages 231–232, 2013.
[67] T. Liebig, N. Piatkowski, C. Bockermann, and K. Morik. Predictive trip planning-smart
routing in smart cities. In Proc. of MUD’14, pages 331–338, 2014.
[68] T. Liebig, N. Piatkowski, C. Bockermann, and K. Morik. Dynamic route planning with
real-time traffic predictions. Information Systems, 64:258–265, 2017.
[69] K. H. Lim. Recommending tours and places-of-interest based on user interests from geo-
tagged photos. In Proc. of SIGMOD’15 PhD Symposium, pages 33–38, 2015.
[70] K. H. Lim, J. Chan, S. Karunasekera, and C. Leckie. Personalized itinerary recommen-
dation with queuing time awareness. In Proc. of SIGIR’17, pages 325–334, 2017.
[71] K. H. Lim, J. Chan, C. Leckie, and S. Karunasekera. Personalized tour recommendation
based on user interests and points of interest visit durations. In Proc. of IJCAI’15, pages
1778–1784, 2015.
[72] K. H. Lim, J. Chan, C. Leckie, and S. Karunasekera. Towards next generation touring:
Personalized group tours. In Proc. of ICAPS’16, pages 412–420, 2016.
[73] K. H. Lim, J. Chan, C. Leckie, and S. Karunasekera. Personalized trip recommendation
for tourists based on user interests, points of interest visit durations and visit recency.
Knowledge and Information Systems, 54(2):375–406, Feb 2018.
[74] K. H. Lim, E.-P. Lim, B. Jiang, and P. Achananuparp. Using Online Controlled Experi-
ments to Examine Authority Effects on User Behavior in Email Campaigns. In Proc. of
HT’16, pages 255–260, Jul 2016.
[75] K. H. Lim, X. Wang, J. Chan, S. Karunasekera, C. Leckie, Y. Chen, C. L. Tan, F. Q. Gao,
26 K. H. Lim et al.
and T. K. Wee. PersTour: A personalized tour recommendation and planning system. In
Proc. of HT’16, 2016.
[76] Q. Liu, S. Wu, L. Wang, and T. Tan. Predicting the next location: A recurrent model
with spatial and temporal contexts. In Proc. of AAAI’16, pages 194–200, 2016.
[77] X. Lu, C. Wang, J.-M. Yang, Y. Pang, and L. Zhang. Photo2trip: generating travel routes
from geo-tagged photos for trip planning. In Proc. of MM’10, pages 143–152, 2010.
[78] C. Lucchese, R. Perego, F. Silvestri, H. Vahabi, and R. Venturini. How random walks can
help tourism. In Proc. of ECIR’12, pages 195–206, 2012.
[79] A. Majid, L. Chen, H. T. Mirza, I. Hussain, and G. Chen. A system for mining interesting
tourist locations and travel sequences from public geo-tagged photos. Data & Know ledge
Engineering, 95:66–86, 2015.
[80] I. Memon, L. Chen, A. Majid, M. Lv, I. Hussain, and G. Chen. Travel recommendation
using geo-tagged photos in social media for tourist. Wireless Personal Communications,
80(4):1347–1362, 2015.
[81] J. Pennebaker. The Secret Life of Pronouns: What Our Words Say About Us. Blooms-
bury, 2013.
[82] T.-A. N. Pham, X. Li, and G. Cong. A general model for out-of-town region recommen-
dation. In Proc. of WWW’17, pages 401–410, 2017.
[83] D. Quercia, R. Schifanella, and L. M. Aiello. The shortest path to happiness: Recom-
mending beautiful, quiet, and happy routes in the city. In Proc. of HT’14, pages 116–125,
2014.
[84] I. Refanidis and A. Alexiadis. Deployment and evaluation of selfplanner, an automated
individual task management system. Computational Intel ligence, 27(1):41–59, 2011.
[85] I. Refanidis, C. Emmanouilidis, I. Sakellariou, A. Alexiadis, R.-A. Koutsiamanis, K. Ag-
nantis, A. Tasidou, F. Kokkoras, and P. S. Efraimidis. myVisitPlanner GR: Personalized
itinerary planning system for tourism. In Proc. of SETN’14, pages 615–629, 2014.
[86] I. Refanidis and N. Yorke-Smith. A constraint-based approach to scheduling an individ-
ual’s activities. ACM Tran. on Intel ligent Systems and Technology, 1(2):12, 2010.
[87] S. B. Roy, L. V. Lakshmanan, and R. Liu. From group recommendations to group for-
mation. In Proc. of SIGMOD’15, pages 1603–1616, 2015.
[88] W. Souffriau and P. Vansteenwegen. Tourist trip planning functionalities: State-of-the-art
and future. In Proc. of ICWE’10, pages 474–485, 2010.
[89] W. Souffriau, P. Vansteenwegen, J. Vertommen, G. V. Berghe, and D. V. Oudheusden.
A personalized tourist trip design algorithm for mobile tourist guides. Applied Artificial
Intelligence, 22(10):964–985, 2008.
[90] E. Spyrou and P. Mylonas. A survey on flickr multimedia research challenges. Engineering
Applications of Artificial Intelligence, 51:71–91, 2016.
[91] Y. Su, X. Li, W. Tang, J. Xiang, and Y. He. Next Check-in Location Prediction via
Footprints and Friendship on Location-Based Social Networks. In Proc. of MDM’18,
pages 251–256, 2018.
[92] D. Tang, A. Agarwal, D. O’Brien, and M. Meyer. Overlapping experiment infrastructure:
more, better, faster experimentation. In Proc. of KDD’10, pages 17–26, Jul 2010.
[93] K. Taylor, K. H. Lim, and J. Chan. Travel Itinerary Recommendations with Must-see
Points-of-Interest. In Proc. of WWW’18, pages 1198–1205, 2018.
[94] H. Tong and C. Faloutsos. Center-piece subgraphs: problem definition and fast solutions.
In Proc. of KDD’06, pages 404–413, 2006.
[95] M. Toyoshima, M. Hirota, D. Kato, T. Araki, and H. Ishikawa. Where Is the Memorable
Travel Destinations? In Proc. of SocInfo’18, pages 291–298, 2018.
[96] T. Tsiligirides. Heuristic methods applied to orienteering. J. of the Operational Research
Society, 35(9):797–809, 1984.
[97] UNWTO. United Nations World Tourism Organization (UNWTO) annual report 2015,
2016. http://www2.unwto.org/annual-reports.
[98] P. Vansteenwegen and D. V. Oudheusden. The mobile tourist guide: An OR opportunity.
OR Insight, 20(3):21–27, 2007.
[99] P. Vansteenwegen, W. Souffriau, G. V. Berghe, and D. V. Oudheusden. Iterated local
search for the team orienteering problem with time windows. Computers & Operations
Research, 36(12):3281–3290, 2009.
[100] P. Vansteenwegen, W. Souffriau, G. V. Berghe, and D. V. Oudheusden. The city trip
planner: An expert system for tourists. Expert Systems with Applications, 38(6):6540–
6546, 2011.
Tour Recommendation and Trip Planning Survey 27
[101] P. Vansteenwegen, W. Souffriau, and D. V. Oudheusden. The orienteering problem: A
survey. Euro. J. of Operational Research, 209(1):1–10, 2011.
[102] P. Viola and M. Jones. Rapid object detection using a boosted cascade of simple features.
In Proc. of CVPR’01, pages 511–518, 2001.
[103] J. Wang, Y. Feng, E. Naghizade, L. Rashidi, K. H. Lim, and K. E. Lee. Happiness is a
Choice: Sentiment and Activity-Aware Location Recommendation. In Proc. of WWW’18,
pages 1401–1405, 2018.
[104] X. Wang, C. Leckie, J. Chan, K. H. Lim, and T. Vaithianathan. Improving personalized
trip recommendation by avoiding crowds. In Proc. of CIKM’16, pages 25–34, 2016.
[105] World Travel and Tourism Council. 2016 economic impact annual update summary, 2016.
https://www.wttc.org/research/economic-research/economic-impact-analysis/.
[106] A. Yahi, A. Chassang, L. Raynaud, H. Duthil, and D. H. P. Chau. Aurigo: An interactive
tour planner for personalized itineraries. In Proc. of IUI’15, pages 275–285, 2015.
[107] L. Yao, Q. Z. Sheng, Y. Qin, X. Wang, A. Shemshadi, and Q. He. Context-aware point-
of-interest recommendation using tensor factorization with social regularization. In Proc.
of SIGIR’15, pages 1007–1010, 2015.
[108] M. Ye, P. Yin, W.-C. Lee, and D.-L. Lee. Exploiting geographical influence for collabo-
rative point-of-interest recommendation. In Proc. of SIGIR’11, pages 325–334, 2011.
[109] P. Yin, M. Ye, W.-C. Lee, and Z. Li. Mining gps data for trajectory recommendation. In
Proc. of PAKDD’14, pages 50–61, 2014.
[110] Z. Yu, H. Xu, Z. Yang, and B. Guo. Personalized travel package with multi-point-of-
interest recommendation based on crowdsourced user footprints. IEEE Tran. on Human-
Machine Systems, 46(1):151–158, 2016.
[111] Q. Yuan, G. Cong, and C.-Y. Lin. COM: a generative model for group recommendation.
In Proc. of KDD’14, pages 163–172, 2014.
[112] Q. Yuan, G. Cong, Z. Ma, A. Sun, and N. M. Thalmann. Time-aware point-of-interest
recommendation. In Proc. of SIGIR’13, pages 363–372, 2013.
[113] Q. Yuan, G. Cong, and A. Sun. Graph-based point-of-interest recommendation with
geographical and temporal influences. In Proc. of CIKM’14, pages 659–668, 2014.
[114] C. Zhang, H. Liang, and K. Wang. Trip recommendation meets real-world constraints:
Poi availability, diversity, and traveling time uncertainty. ACM Tran. on Information
Systems, 35(1):5, 2016.
[115] C. Zhang, H. Liang, K. Wang, and J. Sun. Personalized trip recommendation with poi
availability and uncertain traveling time. In Proc. of CIKM’15, pages 911–920, 2015.
[116] V. W. Zheng, Y. Zheng, X. Xie, and Q. Yang. Collaborative location and activity recom-
mendations with gps history data. In Proc. of WWW’10, pages 1029–1038, 2010.
[117] Y. Zheng and X. Xie. Learning travel recommendations from user-generated gps traces.
ACM Tran. on Intelligent Systems and Technology, 2(1):2, 2011.
[118] Y. Zheng, L. Zhang, Z. Ma, X. Xie, and W.-Y. Ma. Recommending friends and locations
based on individual location history. ACM Tran. on the Web, 5(1):5, 2011.
[119] Y. Zheng, L. Zhang, X. Xie, and W.-Y. Ma. Mining interesting locations and travel
sequences from gps trajectories. In Proc. of WWW’09, pages 791–800, 2009.
Author Biographies
Kwan Hui Lim is an Assistant Professor at the Information Systems Tech-
nology and Design Pillar, Singapore University of Technology and Design. Pre-
viously, he was a Research Fellow at the School of Computing and Information
Systems, University of Melbourne, Research Engineer at the Living Analytics Re-
search Centre, Singapore Management University, and Research Intern at IBM
Research - Australia. He received his PhD from the University of Melbourne, and
MSc (Research) and BCompSci (1st Class Honours) from the University of West-
ern Australia. He is a recipient of the 2016 Google PhD Fellowship in Machine
Learning. His research interests are in Data Mining, Machine Learning, Artificial
Intelligence, Social Network Analysis, and Social Computing.
28 K. H. Lim et al.
Jeffrey Chan is a Senior Lecturer at RMIT University, Melbourne, Australia.
He has a BEng, BSci and PhD, all from the University of Melbourne, and have
interned at the National Institute of Informatics in Japan. He was previously a
senior post-doctoral fellow at the Digital Enterprise Research Institute in Ireland
and a research fellow at the University of Melbourne. He has over 70 publica-
tions in graph mining, social network analysis and data mining and his research
interests are in data analytics, analysing graphs and social networks and learning
about new and exciting research.
Christopher Leckie received the B.Sc. degree in 1985, the B.E. degree in elec-
trical and computer systems engineering (with first-class Honors) in 1987, and the
Ph.D. degree in computer science in 1992, all from Monash University, Clayton,
Vic., Australia. He joined Telstra Research Laboratories in 1988, where he con-
ducted research and development into artificial intelligence techniques for various
telecommunication applications. In 2000, he joined the University of Melbourne,
Parkville, Vic., where he is currently a Professor in the Department of Comput-
ing and Information Systems. His research interests include scalable data mining,
network intrusion detection, bioinformatics, and wireless sensor networks.
Shanika Karunasekera received the B.Sc. degree in electronics and telecom-
munications engineering from the University of Moratuwa, Sri Lanka, in 1990
and the Ph.D. degree in electrical engineering from the University of Cambridge,
Cambridge, U.K., in 1995. From 1995 to 2002, she was a Software Engineer and
a Distinguished Member of Technical Staff with Lucent Technologies, Bell Labs
Innovations, USA. In January 2003, she joined the University of Melbourne, Vic-
toria, Australia, and currently she is a Professor in the Department of Computing
and Information Systems. Her current research interests include distributed sys-
tem engineering, distributed data-mining and social media analytics.
A preview of this full-text is provided by Springer Nature.
Content available from Knowledge and Information Systems
This content is subject to copyright. Terms and conditions apply.
