Collaborative Filtering for Book Recommandation.
Chahinez Benkoussas, Hussam Hamdan, Shereen Albitar, Anaïs Ollagnier, Patrice Bellot · CLEF (Working Notes) · 2014
In this paper, we present our contribution in INEX 2014 Social Book Search Track. This track aims to exploit social information (users reviews, ratings, etc...) from LibraryThing and Amazon collections. In our experiments we used di erent methods, one of our submissions which uses INL2 got the second rank w.r.t nDCG@10 measure, the o cial measure for this task. In addition, we tested the combination of the Sequential Dependence Model (SDM) and the use of social information that takes into account ratings,tags and customer reviews, we also tested several query expansion techniques: concept expansion, tag expansion and pseudo relevance feedback.