Adapting To Evolving Needs: Evaluating A Behaviour-Based Search Interface

In this paper we present an evaluation of a behaviour-based adaptive search interface that predicts the current state of a user’s information need based on their interaction. We evaluate the hypotheses that our adaptive system selects additional query words that closely describe user needs and is able to accurately depict the degree of change in these needs. Our evaluation, with real users and different types of information seeking scenario, shows that these hypotheses hold.