Learning Scrutable User Models: Inducing Conceptual Descriptions

The problem of filtering relevant information from the huge amount of available data is tackled by using models of the user’s interest in order to discriminate interesting information from un–interesting data. As a consequence, Machine Learning for User Modeling (Ml4Um) has become a key technique in recent adaptive systems. This article presents the novel approach of conceptual user models which are easy to understand and which allow for the system to explain its actions to the user. We show that Ilp can be applied for the task of inducing user models from even sparse feedback by mutual sample enlargement. Results are evaluated independently of domain knowledge within a clear machine learning problem definition. The whole concept presented is realized in a meta web search engine, OySTER. (To appear in: ”Kunstliche Intelligenz”, 4/2002.)