Anticipatory Search: Using Context to Initiate Search

Identifying content for which a user may search has a variety of applications, including ranking and recommendation. In this poster, we examine how pre-search context can be used to predict content that the user will seek before they have even specified a search query. We call this anticipatory search. Using a log-based approach, we compare different methods for predicting the content to be searched using different attributes of the pre-query context and behavioral signals from previous visitors the most recent browse URL in that context. Each method covers different cases and shows promise for query-free anticipatory search on the Web.