How Linguistic Resources May Help to Recommend TV Programmes

This paper presents an approach to exploit free text descriptions of TV programmes as available from EPG data sets for a TV recommendation system that takes the content of programmes into account1. The paper focusses on the natural language understanding problem underlying the analysis of free text descriptions and on methods of classifying free text descriptions in relation to a natural language user query. A evaluation of user acceptance is presented. The paper closes with a discussion of future work and proposals of how to integrate our search algorithm into recommendation systems that are described in the literature (see (Ardissono et al., 2001; Gena, 2001; Buczak et al., 2002)).