Fig 1 - uploaded by Amal Htait
Content may be subject to copyright.
Source publication
In this paper, we present our contribution in Suggestion Track at the Social Book Search Lab. This track aims to develop test collections for evaluating ranking effectiveness of book retrieval and rec-ommender systems. In our experiments, we combine the results of Sequential Dependence Model (SDM) and the books information that includes the price,...
Contexts in source publication
Context 1
... the users profiles, we create for each book an XML file with all its information. An example is illustrated in the following XML code of Figure 1. ...
Citations
... The textual baseline was re-ranked considering different non-textual modalities including ratings, price, and the number of pages. In a similar study, Htait et al. (2016) devised a textual baseline by running topic's TN against the search index having social and professional metadata and ranking using SDM. The results were re-ranked by applying QE on it using the example books from the topic creator and tags from the user profile. ...
The role of formulating a well-defined query in the retrieval of relevant search results is well-known to the users of an Information Retrieval (IR) system. Researchers have experimented with various approaches to formulating a search query, e.g., using topic fields in different combinations, reducing verbose queries, and query expansion to name a few. These approaches have been tested in various domain-specific IR applications. However, to the best of our knowledge, no survey or review article reviews the current state of query formulation in the domain of book search. This paper fills this gap in the literature by reviewing research publications on query formulation, published during 2007–2022. These publications have been selected through a rigorous search and selection strategy, where the findings have been summarized using a well-defined theoretical framework. It identifies the current trends and presents a cross-comparison for identifying the best-performing methods. The paper has implications for researchers working in IR in general and book search in specific.
Social Book Search (SBS) studies how the Social Web impacts book retrieval. This impact is studied in two steps. In this first step, called the baseline run, the search index having bibliographic descriptions or professional metadata and user-generated content or social metadata is searched against the search queries and ranked using a retrieval model. In the second step, called re-ranking, the baseline search results are re-ordered using social metadata to see if the search relevance improves. However, this improvement in the search relevance can only be justified if the baseline run is made stronger by considering the contribution of the query, index, and retrieval model. Although the existing studies well-explored the role of query formulation and document representation, only a few considered the contribution of the retrieval models. Also, they experimented with a few retrieval models. This article fills this gap in the literature. It identifies the best retrieval model in the SBS context by experimenting with twenty-five retrieval models using the Terrier IR platform on the Amazon/LibraryThing dataset holding topic sets, relevance judgments, and a book corpus of 2.8 million records. The findings suggest that these retrieval models behave differently with changes in query and document representation. DirichletLM and InL2 are the best-performing retrieval models for a majority of the retrieval runs. The previous best-performing SBS studies would have produced better results if they had tested multiple retrieval models in selecting baseline runs. The findings confirm that the retrieval model plays a vital role in developing stronger baseline runs.
The emergence of the Social Web and social collaborative cataloging web applications have changed the way books are described, discovered and accessed. These applications present books not only through the bibliographic descriptions or professional metadata but also allow users to describe these resources through user-generated content or social metadata. This social practice has attracted researchers under the broader topic of Social Book Search to make it part of the book retrieval process aiming to improve the relevance of search results and understand the impact of the Social Web on the search performance. For this purpose, the classical Information Retrieval (IR) approaches are employed to produce an initial set of search results, which are re-ranked using the social metadata to see if the search relevance gets improved. Although numerous studies found that the social metadata improves over the baseline run, they are unable to exploit fully the potential role of query-document representation and weighting model, which questions the credibility of such a conclusion. Also, in re-ranking, most of the studies evaluated and compared different metadata features to produce better search results but remained silent about the final shape of re-ranking.
To fill these gaps in the literature, this research work considers the contribution of query-document representation and weighting model to the fullest to produce a strong classical baseline run and re-ranks it using a multifeatured fusion of different social metadata features. Our best-performing baseline and re-ranking runs outperform the existing approaches on several topics sets and relevance judgments. The findings suggest that the best document representation can be achieved if the social metadata is made part of the search index. The best query representation is achieved using all-topic-fields. The relevance of search results improves with re-ranking the best-performing baseline runs. These findings have implications for researchers working in Libraries, Information Science, IR, and Interactive IR.
Social media has changed the digital landscape of book retrieval and recommendation on the Web. The availability of the social collaborative cataloging and search applications including Amazon, GoodReads, and LibraryThing has enabled users to discuss their complex information needs and request recommendations on books in natural language. Others with similar interests and preferences suggest books. On these social book websites, users not only benefit from the available professionally-curated, publisher-provided (professional) metadata but also look at how group members assess books by reading their reviews, tags, and ratings, which are commonly referred to as the user-generated content or social metadata. This social collaborative cataloging practice and the resulting rich metadata collection attracted researchers under the broader topic of Social Book Search (SBS). The aim is to exploit the social metadata in book retrieval and understand the search behavior of users while interacting with the rich metadata collection. The retrieval side of the SBS research, which is the main focus of this paper, attempts to come up with book retrieval solutions considering the ambiguity of the natural language and the complexity of the information needs of the users. This paper gives in-depth and comprehensive coverage to the current state of the retrieval side of SBS research from its origin to the present day by critically and analytically reviewing the academically significant relevant research contributions. It reports on the retrieval methods, evaluation methodology, and best-performing runs using different evaluation metrics. It identifies the current trends as well as research challenges and opportunities.
An online exchange system is a web service that allows communities to trade items without the burden of manually selecting them, which saves users' time and effort. Even though online book-exchange systems have been developed, their services can further be improved by reducing the workload imposed on their users. To accomplish this task, we propose a recommendation-based book exchange system, called EasyEx, which identifies potential exchanges for a user solely based on a list of items the user is willing to part with. EasyEx is a novel and unique book-exchange system because unlike existing online exchange systems, it does not require a user to create and maintain a wish list, which is a list of items the user would like to receive as part of the exchange. Instead, EasyEx directly suggests items to users to increase serendipity and as a result expose them to items which may be unfamiliar, but appealing, to them. In identifying books to be exchanged, EasyEx employs known recommendation strategies, that is, personalized mean and matrix factorization, to predict book ratings, which are treated as the degrees of appeal to a user on recommended books. Furthermore, EasyEx incorporates OptaPlanner, which solves constraint satisfaction problems efficiently, as part of the recommendation-based exchange process to create exchange cycles. Experimental results have verified that EasyEx offers users recommended books that satisfy the users' interests and contributes to the item-exchange mechanism with a new design methodology.
