Combining Interaction and Content for Feedback-Based Ranking

The paper is concerned with the design and the evaluation of the combination of user interaction and informative content features for implicit and pseudo feedback-based document re-ranking. The features are observed during the visit of the top-ranked documents returned in response to a query. Experiments on a TREC Web test collection have been carried out and the experimental results are illustrated. We report that the effectiveness of the combination of user interaction for implicit feedback depends on whether document re-ranking is on a single-user or a user-group basis. Moreover, the adoption of document re-ranking on a user-group basis can improve pseudo-relevance feedback by providing more effective document for expanding queries.

• Type: Journal
• Year: 2011
• Where: IRFC
• Authors: Emanuele Di Buccio, Massimo Melucci, Dawei Song
• Keywords: Implicit Feedback, Information Technology, IRFC 2011, Relevance Feedback, Trec Web