Abstract
One major problem of most current information retrieval systems is that they provide uniform access and retrieval results to all users solely based on the query terms users issued to the system. In this paper, we propose a model to personalize the search results according to the user's search context, in particular the type of task that led the user to engage in information-seeking behavior, and the behaviors that the user has engaged in during the search. The point of this personalization is to predict potentially useful documents based on the type of task, and on behaviors indicative of document usefulness. We believe this model can improve individual users' retrieval performance substantially.