Multimodal Social Book Search

Mélanie Imhof (1, 2) , Ismail Badache (3) , Mohand Boughanem (3, 4)

1 UNINE - Université de Neuchâtel = University of Neuchatel
2 UZH - Universität Zürich [Zürich] = University of Zurich
3 IRIT-SIG - Systèmes d’Informations Généralisées
4 UT3 - Université Toulouse III - Paul Sabatier

Today's information retrieval applications have become increasingly complex. The Social Book Search (SBS) lab at CLEF 2015 allows evaluating retrieval methods on a complex search task with several textual and non-textual meta-data fields. The challenge is to incorporate the different information types (modalities) into a single ranked list. We build a strong textual baseline and combine it with a document prior based on social signals. Further, we include non-textual modalities in relation to the user preferences using random forest learning to rank. Our experiments show that both the social document prior and the learning to rank approach improve the search results.

Mots clés: Relevance feedback; Random forest; Non-textual modalities; Social signals; Document prior

Domaines: Théorie de l'information [cs.IT]; Recherche d'information [cs.IR]

Mélanie Imhof, Ismail Badache, Mohand Boughanem. Multimodal Social Book Search. 6th Conference on Multilingual and Multimodal Information Access Evaluation (CLEF 2015), Sep 2015, Toulouse, France. pp. 1-9. ⟨hal-01360875⟩