A Novel User Profile Learning Approach with Fuzzy Constraint for News Retrieval

This study conducts a novel user profile learning approach based on fuzzy constraints. From the vantage of knowledge representation, a fuzzy constraint network is used not only to present the ambiguity of concepts and the diversity between concepts but also to express a single user profile with dependent multisubjects of interest. From the vantage of problem solving, the construction of a user profile is viewed as a problem of fuzzy constraint satisfaction. The subject of interest is extracted by a spreading activation model. To achieve the information filtering of the retrieved data, fuzzy information gain is employed to reduce unnecessary user feedback for matching the user's retrieval requirements.