Contextual Suggestion from Wikitravel: Exploiting Community-Based Suggestions

This paper describes our participation in the TREC 2012 Contextual Suggestion Track. The goal of the track is to evaluate systems that provide suggestions for activities to users in a specific location, at a specific time, taking into account their personal preferences. As a source for travel suggestions we use Wikitravel, which is a community-based travel guide for destinations all over the world. From pages dedicated to cities in the US we extract suggestions for sightseeing, shopping, eating and drinking. Descriptions from positive examples in the user profiles are used as queries to rank all suggestions in the US. Our baseline approach merges the per-query rankings of all positive examples of all users. Our userdependent approach merges the per-query rankings of the positive examples of a single user. The rankings suggestions are then filtered based on the location of the user. We ignore the temporal aspects of the context. The user-dependent rankings are more effective for contextual suggestion than user-independent rankings. The two systems show similar perform on the geographical dimension, but the user-dependent system provides more interesting suggestions. Our results show that information on user preferences is valuable for providing appropriate suggestions.