Modeling, characterizing and recommendation in multimedia web content services

Abstract

Web content has gained 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 networks. This paper evaluates a set of corporate online videos hosted by Sambatech, a company that holds the largest platform for online multimedia content distribution in Latin America. We propose a novel analytical approach for video recommendation, focusing on video objects being consumed, and not on consumer profile data. After modeling this service, we characterize the contents from multiple sources, and propose techniques for video recommendation. Experimental results indicate that the proposed method obtains a gain of about 42% in precision for a set of five recommendations, as compared to a baseline that is based only on video metadata.