2. User Modeling
User modeling is well known in AI (Artificial Intelligence), where an accurate model of the user is fundamental for the success of an expert system session. Applications of user modeling in AI range from improved man-machine interfaces over expert systems to intelligent tutoring systems where the general goal is to improve human-computer interaction. In this chapter we will give a brief introduction to with an emphasis on its application to information retrieval.
IR systems often lack the capability of adapting their behavior to different categories of users. Naive users, users with specific background in the search domain, newcomers, and very experienced users are all treated the same. The goals that should be reached by applying user modeling techniques to IR are twofold:
- The linguistic gap between the user and the system should be closed.
- Users should be supported at the conceptual level in the analysis of their information needs, in the formulation of an appropriate search strategy, and in the evaluation of the obtained results.