Information Retrieval and Graph Analysis Approaches for Book Recommendation

Autor: Chahinez Benkoussas, Patrice Bellot
Jazyk: angličtina
Rok vydání: 2015
Předmět:
Zdroj: The Scientific World Journal, Vol 2015 (2015)
Druh dokumentu: article
ISSN: 2356-6140
1537-744X
DOI: 10.1155/2015/926418
Popis: A combination of multiple information retrieval approaches is proposed for the purpose of book recommendation. In this paper, book recommendation is based on complex user's query. We used different theoretical retrieval models: probabilistic as InL2 (Divergence from Randomness model) and language model and tested their interpolated combination. Graph analysis algorithms such as PageRank have been successful in Web environments. We consider the application of this algorithm in a new retrieval approach to related document network comprised of social links. We called Directed Graph of Documents (DGD) a network constructed with documents and social information provided from each one of them. Specifically, this work tackles the problem of book recommendation in the context of INEX (Initiative for the Evaluation of XML retrieval) Social Book Search track. A series of reranking experiments demonstrate that combining retrieval models yields significant improvements in terms of standard ranked retrieval metrics. These results extend the applicability of link analysis algorithms to different environments.
Databáze: Directory of Open Access Journals
Externí odkaz: