TV-Show Retrieval and Classification

Recommender systems are popular tools to aid users in find-ing interesting and relevant TV shows and other digital video assets,based on implicitly defined user preferences. In this context, a commonassumption is that user preferences can be specified by program types(such as documentary, sports), and that an asset can be labeled by oneor more program types, thus allowing an initial coarse preselection ofpotentially interesting assets. Furthermore each asset has a short tex-tual description, which allows us to investigate whether it is possible toautomatically label assets with program type labels. We compare theVector Space Model (vsm) with more recent approaches to text classifi-cation, such as Logistic Regression (lr) and Random Indexing (ri) on alarge collection of TV-show descriptions. The experimental results showthatlris the best approach, butrioutperformsvsmunder particularconditions.