Skip to main content
WorldCist'17 - 5th World Conference on Information Systems and Technologies

Full Program »

The semantics of movie metadata: enhancing user profiling for hybrid recommendation

Recommendation systems are used to enable suggesting new items to a user in the service. In the movie/TV domain, ratings users gave to already visited content are often used as the only input that enables building profiles. However, two users might have rated equally the same movie but due to different reasons: either because of its genre, the crew or the director. In such cases, though users could have assigned the same rating to a movie, this rating is insufficient to represent in detail their preferences and it is wrong to conclude that they share similar tastes. The work presented in this paper tries to solve this ambiguity by exploiting some hidden semantics in metadata elements usually associated with movie content. A deep analysis on the influence of each of the standard movie description elements (actors, directors and genre) in representing user’s preferences and enabling enhanced user profiles is presented. Simulations were conducted using Movielens and Netflix datasets and different evaluation metrics were considered. The obtained results demonstrate that the implemented approach yields significant advantages both in terms of improving performance, as well as in dealing with common limitations of standard collaborative algorithm.

Author(s):

Márcio Soares    
INESC TEC
Portugal

Paula Viana    
INESC TEC and P. Porto
Portugal

 

Powered by OpenConf®
Copyright ©2002-2016 Zakon Group LLC