Abstract
In this paper, we describe our participation in the INEX 2012 Social Book Search track. We investigate the contribution of different types of document metadata, both social and controlled, and examine the effectiveness of re-ranking retrieval results using different social features, such as user ratings, tags, and authorship information. We find that the best results are obtained using all available document fields and topic representations. Reranking retrieval results works better on shorter topic representations, where there is less information for the retrieval algorithm to work with; longer topic representations do not benefit from our social re-ranking approaches.
Originalsprog | Engelsk |
---|---|
Tidsskrift | CEUR Workshop Proceedings |
Vol/bind | 1178 |
ISSN | 1613-0073 |
Status | Udgivet - 1 jan. 2012 |
Udgivet eksternt | Ja |
Begivenhed | 2012 Cross Language Evaluation Forum Conference, CLEF 2012 - Rome, Italien Varighed: 17 sep. 2012 → 20 sep. 2012 |
Konference
Konference | 2012 Cross Language Evaluation Forum Conference, CLEF 2012 |
---|---|
Land/Område | Italien |
By | Rome |
Periode | 17/09/2012 → 20/09/2012 |
Emneord
- Social Book Search
- Document metadata
- Social features
- Re-ranking retrieval
- Topic representations