USTB at INEX2014: Social Book Search Track

In this paper, we describe our participation in the INEX 2014 Social Book Search(SBS) Track Suggestion Task. We investigate the contribution of user-generated data and construct a social book search system based on several important techniques. We perform re-ranking on Galago searching results on enriched XML index by 11 dierent s- trategies and combine the results with learning to rank. We nd that 1) enriched index improves the eectiveness, 2) tag is the best-performed social feature on re-ranking and 3) Random Forest shows the best per- formance on combining in this case.