Supporting Exploratory Search Through User Modeling

Exploratory search is becoming more common as the web is used more increasingly as a medium for learning and discovery. Compared to traditional known-item search, exploratory search is more challenging and difficult to support because it initiates with poorly defined search goals, while the user knowledge and information-needs constantly change throughout the search process. Although information-retrieval algorithms have improved greatly in providing users with relevant information to specific queries, there is still room to improve our understanding of users’ exploratory information-seeking strategies as well as design of systems supporting exploratory information-seeking. Modeling the user behavior and predicting dynamically changing information-needs in exploratory search is hard. Over the past decade there has been increasing attention on rich user interfaces, retrieval techniques, and studies of exploratory search. However, existing work does not yet support the dynamic aspects of exploratory search. The aim of this research is to explore different aspects of how to understand and support exploratory search, including user studies, intent visualization and user modeling.