A video recommendation algorithm based on the combination of video content and social network

摘要

Recently, social network has been one of the biggest information exchange platforms of the Internet. Moreover,rnthe users in social network used to watch videos through social network application. To provide arnproper recommended video list, the video recommendation algorithm for social network is becoming a hotrnresearch issue. On one hand, more and more researchers introduce the concept of trust into video recommendationrnalgorithms. However, most of them only select the trust friends based on the similarity and neglect therncharacteristics of social network. On the other hand, most previous video recommendation algorithms arernonly based on the number that a video is viewed to evaluate a video’s quality. They do not make good use ofrnthe social relationship in social network and the video’s reputation. This paper mainly focuses on the challengernthat the effectiveness and performance of current video recommendation algorithm in social networkrncannot satisfy the users. In this paper, we propose a novel video recommendation algorithm based on therncombination of video content and social network. Our proposed algorithm consists of the trust friends computingrnmodel and video’s quality evaluation model. The trust friends computing method takes into accountrnsimilarity between users, interaction between users, and the active degree of a user. In our video’s qualityrnevaluation model, we combine the acceptance ratio of a video with a video’s reputation. The video canrnbe given an appropriate rating score through this model. We design corresponding trust friends computingrnalgorithm and video recommendation algorithm respectively for two proposed models. Our integral videornrecommendation algorithm consists of these two algorithms. The experimental results indicate that the performancernand effectiveness of our algorithm are better than those of two classical video recommendationrnalgorithms (i.e., user-based collaborative filtering algorithm and TBR-d algorithm), in terms of precision,rnrecall and F1-measure.