Overview - Contextual Suggestion 2016¶
Proceedings | Data | Results | Runs | Participants
The TREC Contextual Suggestion Track offers a personalized point of interest (POI) recommendation task, in which participants develop systems to give a ranked list of suggestions related to a profile and a context pair available in the tasks' requests provided by the track organizers. Previously, reusability of the contextual suggestion track suffered from using dynamic collections and a shallow pool depth. The main innovations at TREC 2016 are the following. First, the TREC CS web corpus, consisting of a web crawl of the TREC contextual suggestion collection, was made available. The rich textual descriptions of the web pages makes far more information available for each candidate POI in the collection. Second, we released endorsements (end user tags) of the attractions as given by NIST assessors, potentially matching the endorsements of POIs in another city as given by the person issuing the request as part of her profile. Third, a multi-depth pooling approach extending beyond the shallow top 5 pool was used. The multi-depth pooling approach has created a test collection that provides more reliable evaluation results in ranks deeper than the traditional pool cut-off.
Track coordinator(s):
- Seyyed Hadi Hashemi,University of Amsterdam
- Jaap KampsUniversity of Amsterdam
- Julia Kiseleva, University of Amsterdam
- Charles L.A. Clarke, University of Waterloo
- Ellen M. Voorhees, National Institute of Standards and Technology (NIST)
Tasks:
phase1: Phase 1 Experimentsphase2: Phase 2 Experiments
Track Web Page: https://sites.google.com/site/treccontext/