Social book search: the impact of the social web on book retrieval and recommendation

Abstract

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.