Modelagem, caracterização e recomendação em serviços de conteúdo web multimídia

Abstract

Web multimedia content has reached much importance lately. One of the most important content types is online video, as demonstrated by the success of platforms such as YouTube. The growth in the volume of available online video is also observed in corporate scenarios, such as TV stations. This work presents an analysis of corporate multimedia Web content services. We evaluate real data from online videos hosted by Samba Tech, the largest platform for online multimedia content distribution in Latin America. After modeling and characterize this service, we propose a novel technique for multimedia content recommendation, focusing on object being consumed. Experimental results indicate that the proposed method is very promising, obtaining almost 70% in precision. We also perform distinct evaluations using different approaches from literature, such as the state-of-the-art technique for item recommendation. These results are important for content providers and consumers, and it can be applied in personalized services and recommendation systems.