Query Log Analysis for User-Centric Multimedia Databases
Résumé
Recently, the information community has seen the emergence of user-centric media
applications, which are characterized by the central position given to the user. To fulfill the
user-centric promise, it is necessary to understand and model the actions of the users of the
system. This position paper presents a methodology for modeling the behavior of multimedia
database users. To this end, we propose to analyze the query logs to derive the classes of
behaviors of a user. The presented method bases on the characteristics of user queries and on
taxonomies. The behaviors are established using a query classification algorithm.