Figure - available from: User Modeling and User-Adapted Interaction
This content is subject to copyright. Terms and conditions apply.
![Structure of a bundle or recommendable item in the EvoRecSys framework. An individual contains K≥1\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$K \ge 1$$\end{document} bundles](publication/358251047/figure/fig2/AS:11431281102710004@1669519940493/Structure-of-a-bundle-or-recommendable-item-in-the-EvoRecSys-framework-An-individual.png)
Structure of a bundle or recommendable item in the EvoRecSys framework. An individual contains K≥1\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$K \ge 1$$\end{document} bundles
Source publication
In recent years, recommender systems have been employed in domains like e-commerce, tourism, and multimedia streaming, where personalising users’ experience based on their interactions is a fundamental aspect to consider. Recent recommender system developments have also focused on well-being, yet existing solutions have been entirely designed consi...
Similar publications
![Figure 4: Likert-type questions [23] with the results for both versions...](publication/373753688/figure/fig1/AS:11431281187129357@1694142319632/Likert-type-questions-23-with-the-results-for-both-versions-of-the-Recommender-System_Q320.jpg)
This paper investigates how large language models (LLMs) can enhance recommender systems, with a specific focus on Conversational Recommender Systems that leverage user preferences and personalised candidate selections from existing ranking models. We introduce VideolandGPT, a recommender system for a Video-on-Demand (VOD) platform, Videoland, whic...
Structured interviews are used in many settings, importantly in market research on topics such as brand perception, customer habits, or preferences, which are critical to product development, marketing, and e-commerce at large. Such interviews generally consist of a series of questions that are asked to a participant. These interviews are typically...
Citations
... Aging societies and increased awareness of the importance of active lifestyles increase the demand of recommendation systems helping people in sports-related contexts. Numerous applications of recommender systems in sports already exist, ranging from the recommendation of healthy food (Alcaraz-Herrera et al., 2022) and the recommendation of training plans (Smyth et al., 2022) to the recommendation of adventure playgrounds in e-sports (Wu et al., 2017). In this article, we provide an overview of the state-of-the-art in applying recommender systems in sports-related scenarios -we denote such systems as sports recommender systems. ...
... In this context, collaborative filtering can help to identify food items an athlete could be interested (depending on his her previous food preferences and further parameters such as physical condition) (Shrimal et al., 2021). Collaborative filtering is specifically useful to find recipes and menus relevant for athletes in a similar situation in terms of personal goals, physical condition, and food preferences (Alcaraz-Herrera et al., 2022;Donciu et al., 2011;Ni et al., 2019). Grouping athletes into similar categories also helps to better understand which recommendations can help best to motivate users to increase their personal performance. ...
Sports recommender systems receive an increasing attention due to their potential of fostering healthy living, improving personal well-being, and increasing performances in sports. These systems support people in sports, for example, by the recommendation of healthy and performance-boosting food items, the recommendation of training practices, talent and team recommendation, and the recommendation of specific tactics in competitions. With applications in the virtual world, for example, the recommendation of maps or opponents in e-sports, these systems already transcend conventional sports scenarios where physical presence is needed. On the basis of different examples, we present an overview of sports recommender systems applications and techniques. Overall, we analyze the related state-of-the-art and discuss future research directions.
... This strategy simplifies the shopping process for customers, offering a ready-made solution and often presenting a cost-saving opportunity compared to individ-ual purchases [13]. Bundle recommender systems enhance the overall shopping experience by catering to the customer's needs in a holistic manner, contributing to increased sales and customer satisfaction [14]. ...
This paper presents a pioneering methodology for refining product recommender systems, introducing a synergistic integration of unsupervised models—K-means clustering, content-based filtering (CBF), and hierarchical clustering—with the cutting-edge GPT-4 large language model (LLM). Its innovation lies in utilizing GPT-4 for model evaluation, harnessing its advanced natural language understanding capabilities to enhance the precision and relevance of product recommendations. A flask-based API simplifies its implementation for e-commerce owners, allowing for the seamless training and evaluation of the models using CSV-formatted product data. The unique aspect of this approach lies in its ability to empower e-commerce with sophisticated unsupervised recommender system algorithms, while the GPT model significantly contributes to refining the semantic context of product features, resulting in a more personalized and effective product recommendation system. The experimental results underscore the superiority of this integrated framework, marking a significant advancement in the field of recommender systems and providing businesses with an efficient and scalable solution to optimize their product recommendations.
... MOEAs NSGA-II MOIA MOEA/D IBEA NSHA GA ENS NSGA-III [71] x [72] x [73] x [74] x [26] x [75] x [76] x [77] x [78] x x [79] x [41] x [80] x [81] x [42] x [82] x [83] x [84] x [85] x [86] x [87] x [88] x [19] x [89] x [39] x [90] x [91] x [92] x [93] x [94] x x [95] x [96] x [97] x [40] x [98] x [99] x [100] x [101] x [102] x [103] x [27] x [104] x [105] x a multi-objective evolutionary algorithm-based online learning resource recommendation model that balances accuracy, novelty, and diversity to improve the recommendation performance of online learning resources. Their approach provides more accurate, diverse, and novel results compared to existing algorithms. ...
... Evolutionary algorithms [84] To (continued on next page) (continued on next page) (continued on next page) Evolutionary algorithms [97] To optimize the utilities of all stakeholders to generate balanced and effective recommendations. The approach optimizes the utilities of multiple stakeholders in a recommender system, resulting in recommendations that balance multiple utilities and recommendation performance. ...
... The study benefits researchers and engineers to develop a better advisory system for studying at MOOC and promoting the quality of human resources in society. The second article [84] presents EvoRecSys, a novel recommendation framework that models the problem of generating personalized well-being recommendations as a MOO problem, considering multiple aspects of well-being and constructing configurable recommendations in the form of bundled items with dynamic properties. The framework uses a genetic algorithm as the recommendation engine. ...
Recommender systems have become essential in modern information systems and Internet applications by delivering personalized and pertinent content to users. While conventional recommendation algorithms usually prioritize optimizing a single objective, it is now evident that considering additional metrics is crucial for improving the overall user experience. Despite the importance of considering multiple objectives, conventional recommendation models face the challenge of balancing these objectives, which can sometimes conflict with each other. To tackle this challenge, there is a growing interest in multi-objective recommender systems (MORS) that consider multiple objectives simultaneously and provide a more personalized and varied set of recommendations. MORS can optimize recommendations based on various metrics, including accuracy, diversity, novelty, and user satisfaction, leading to more efficient and personalized recommendation systems. The objective of this paper is to conduct a systematic review study to assess the current state of research in the field of MORS and identify potential avenues for future exploration. The study selection procedure includes 78 primary studies published from 2019 to January 2023. These preliminary studies are categorized based on different variables to address the research questions outlined in this study. The findings of this systematic review study reveal a diverse range of applications, objectives, datasets, methodologies, and evaluation metrics utilized in the field of MORS. Additionally, this review offers a crucial overview of the current state of research in this area, highlighting the existing challenges and future directions for enhancing the efficiency of MORS. These outcomes can benefit both professionals and academic researchers in the development and implementation of effective MORS.
... Pathway-based drug response prediction is better than gene-based prediction in a recommender system. In [52], an evolutionary algorithmic approach that implements a multiobjective optimization problem (user preference, user requirement, and user final goal determination) in the form of food training packages. This study [53] recommends the symptoms experienced by patients to predict the disease. ...
... First, we perform a more extensive comparative analysis of SF in the greater than domain; using mutation bias as a control to simulate the dynamics of more complex realworld application domains. Second, we test the applicability of the findings from the greater than game by addressing the more complex problem of recommender systems for health and well-being; and we show that a coevolutionary approach using SF outperforms the evolutionary approach published in [5]. We present this as evidence that SF is likely to be generally beneficial across a variety of real-world application domains where coevolutionary disengagement occurs. ...
... In Section "Coevolving Well-Being Recommendations", we present experiments conducted in the more complex real-world domain of recommender systems for health and well-being. This work introduces a coevolutionary extension of a previously published evolutionary recommender system (EvoRecSys) [5]. It is shown that SF is able to produce recommendations that are of higher quality and more diverse than the results obtained using RV and AVA, and also produces better overall recommendations than the standard evolutionary approach of EvoRecSys. ...
... In this section we explore the performance of SF, RV and AVA in the domain of recommender systems for health and well-being. Furthermore, we introduce a coevolutionary adaptation of an evolutionary recommender system, first introduced in [5]. ...
This research explores substitution of the fittest (SF), a technique designed to counteract the problem of disengagement in two-population competitive coevolutionary genetic algorithms. SF is domain independent and requires no calibration. We first perform a controlled comparative evaluation of SF’s ability to maintain engagement and discover optimal solutions in a minimal toy domain. Experimental results demonstrate that SF performs similarly to alternative techniques presented in the literature but has the advantage of requiring no parameter tuning. We then address the more complex real-world problem of evolving recommendations for health and well-being. We introduce a coevolutionary extension of EvoRecSys, a previously published evolutionary recommender system. We demonstrate that SF is able to maintain a better trade-off between engagement and performance than other techniques in the literature, and the resultant recommendations using SF are higher quality and more diverse than those produced by EvoRecSys.
... But it is in health recommender systems [10] where we found natural examples of multiple constraint from multiple sources. As examples, it is already common to have systems to help us decide what to eat [11] (more on this topic in Section IV), how we should exercise [12], [13] or what to do when we are ill [14]. • Structured recommendation: ...
... Evolutionary algorithms has also been used with good results. Works like [29], [13] began to explore the possibility of using evolutionary algorithms to produces bundles or sets to be recommended (and extra source of recommendation with physical exercises). ...
Over the last few years, the ability of recommender systems to help us in different environments has been increasing. Several systems try to offer solutions in highly complex environments such as nutrition, housing, or traveling. In this paper, we present a recommendation system capable of using different input sources (data and knowledge-based) and producing a complex structured output. We have used an evolutionary approach to combine several unitary items within a flexible structure and have built an initial set of complex configurable items. Then, a content-based approach refines (in terms of preferences) these candidates to offer a final recommendation. We conclude with the application of this approach to the healthy diet recommendation problem, addressing its strengths in this domain.
... First, we perform a more extensive comparative analysis of SF in the greater than domain. Second, and more significantly, we address the more complex problem of recommender systems for health and well-being, and demonstrate that a coevolutionary approach using SF outperforms the evolutionary approach published in [4]. ...
... In Section 5, we present experiments conducted in the more complex real-world domain of recommender systems for health and well-being. This work introduces a coevolutionary extension of a previously published evolutionary recommender system (EvoRecSys) [4]. It is shown that SF is able to maintain engagement much better than RV and AVA, and leads to recommendations that are of higher quality and more diverse than the results from the standard evolutionary approach of EvoRecSys. ...
... A second parent M is selected at random from the population. Then, some elements from parent M are injected into the child following the method of [4,. Each bundle in the child has items injected from parent M with probability P b = 0.9. ...
This research explores substitution of the fittest (SF), a technique designed to counteract the problem of disengagement in two-population competitive coevolutionary genetic algorithms. SF is domain-independent and requires no calibration. We first perform a controlled comparative evaluation of SF's ability to maintain engagement and discover optimal solutions in a minimal toy domain. Experimental results demonstrate that SF is able to maintain engagement better than other techniques in the literature. We then address the more complex real-world problem of evolving recommendations for health and well-being. We introduce a coevolutionary extension of EvoRecSys, a previously published evolutionary recommender system. We demonstrate that SF is able to maintain engagement better than other techniques in the literature, and the resultant recommendations using SF are higher quality and more diverse than those produced by EvoRecSys.
... Currently, the vast majority of recommender systems focus on a single aspect of health [22]. A variety of devices and technological solutions can be used to achieve a healthier lifestyle. ...
To live longer, healthier, and more active, people at any age have to follow simple and clear suggestions that cover the 3 main pillars of health: physical activity, nutrition, and sleeping. Unfortunately, due to the intrinsic (e.g., daily-life habits) and extrinsic (e.g., environmental change) factors, people are far to have a healthy life and, thus, there is an increase of chronic diseases, mental disorders, and premature death. This paper presents the approach followed in CarpeDiem, an IoT-based system focused on self-management as a way to engage and empower citizens in order to improve their quality of life and to allow a better follow-up of their own health. The CarpeDiem self-management system is intelligent and autonomous, and it is aimed at monitoring physical-and sleeping-activity, nutrition, as well as environmental data and lifestyle habits, with the final goal of providing personalized recommendations and nudges to foster behaviour change towards healthier behaviours. CarpeDiem system currently designed to provide individual recommendations in each one of the domains. However, there is increasing evidence that these three pillars influence each other. Subsequently, the final goal of the application is to assemble the information provided by the three pillars together and supply holistic recommendations to the users to induce a meaningful and enduring change in their behaviours. The purpose of this study is to analyze the existing associations between the three mentioned pillars, by using data from a previous pilot and current state of the art, to later design intelligent recommendations capable of producing lasting behavioural changes in the user’s community.
... In addition, many HRSs utilize context-related features to determine opportune moments for delivering recommendations, of which location and time of day are the most prevalent (e.g., [24], [26]- [28], [33]), but calendar availability [27], [28] and users' momentary activities [24], [26] have also been used in a few examples. Considering user preferences (e.g., preferred PA modalities and times, dietary restrictions) [20], [25]- [27], [44], [45] and the usefulness or effectiveness of recommendations (either user-evaluated or inferred) [24], [28], [30], [35], [38], [43] are also quite common. Some HRSs consider mental state (e.g., stress level, mood) [28], [29], [47], social ties [27], [33], environmental conditions [22], [47], or personal traits [28] ...
... In current HRS research, the attempts to improve the performance of a HRS are mostly focused on finding the most accurate recommendation techniques (e.g., [27], [30], [34], [44]), while user models have attracted less research interest, even though wisely chosen user features can increase the suitability of recommendations significantly, which is important for improved user engagement and a positive health impact. The VI model provides a common user model framework that serves different personalization goals by considering not only the health and behavior change needs of individuals, which are the most widely used features for personalization and, beyond doubt, the most important ones in terms of the expected health impact, but also various other factors that influence user engagement and adherence to intervention. ...
... The time lag between receiving and reading messages has been used to infer the best time to disrupt a user [39]. In addition, user preferences regarding physical activity (PA) modes and food items have been used to personalize recommendations [25]- [27], [44], [45]. However, we could not find examples that attempted to make behavior change objectives personally meaningful or personalized the tone of messages. ...
Health recommender systems (HRSs) have the potential to effectively personalize well-being related behavior change interventions to the needs of individuals. However, personalization is often considered from a narrow perspective, and the underlying user features are inconsistent across HRSs. Particularly, theory-based determinants of behavior and the variety of lifestyle domains influencing well-being are poorly addressed. We propose a comprehensive, theory-based framework of user features, a virtual individual (VI) model, to support the extensive personalization of digital well-being interventions. We introduce a prototype HRS (With-Me HRS), which uses knowledge-based filtering and recommends behavior change objectives and activities from several lifestyle domains. With-Me HRS realizes a minimum set of important VI model features related to well-being, lifestyle, and behavioral intention. We report the preliminary validity and usefulness of the HRS, evaluated in a real-life health-coaching program with 50 participants. The recommendations were used in decision-making for half of the participants and hidden for others. For 73% of the participants (85% with visible vs. 62% with hidden recommendations), at least one of the recommended activities was included into their coaching plans. The HRS reduced coaches’ perceived effort in identifying appropriate coaching tasks for the participants (effect size: Vargha-Delaney Â=0.71, 95% CI 0.59-0.84) but not in identifying behavior change objectives. From the participants’ perspective, the quality of coaching improved (effect size for one of three quality metrics: Â=0.71, 95% CI 0.57-0.83). These results provide a baseline for testing the influence of additional user model features on the validity of recommendations generated by knowledge-based multi-domain HRSs.
Multi-objective evolutionary algorithms (MOEAs) have been proved to be competitive in recommender systems. As the application scenarios of recommender systems become increasingly complex, the number of objectives to be considered in the recommender systems increases. However, most existing multi-objective recommendation algorithms lead to increased environmental selection pressure as the number of objectives increases. To tackle the issue, in this paper, we propose a multi-population based evolutionary algorithm named MP-MORS for many-objective recommendations, where two subpopulations and one major population are used to evolve and interact to find high-quality solutions. Specifically, the objectives are firstly divided into those evaluated on individual users (defined as IndObjectives) and those evaluated on all users (defined as as AllObjectives). Then two subpopulations are suggested to optimize the two types of objectives respectively, with which the potential good solutions can be easily found. In addition, the major population considers the balance of all objectives and refines these potential good solutions. Finally, a set of high-quality solutions can be obtained by the proposed adaptive population interaction strategy. Experiments on the datasets
Movielens
and
Douban
show that the proposed MP-MORS outperforms the state-of-the-art algorithms for many-objective recommendations.
