Social Weak-tie Assisted Cross-domain Short Video Recommendation

Abstract

As a comprehensive information carrier, the short video is gaining increasing attention for a user to spread information, read the news and conduct interpersonal communication. Consequently, short video recommendation problem has been a hot spot in the field of the recommender system. However, current short video recommendation algorithms have to tackle with data sparsity and cold start problem, which is caused by the small amounts of data that the recommender system has accumulated and massive video data while limited users’ access.Aiming at the problem of data sparsity and cold start, the paper proposes a short video recommendation algorithm Social Weak-tie Bayesian Personalized Ranking (SWTBPR). Social weak-tie refers to the following relation in online social network, which means they are not real-world friends, somehow it can reflect users’ preference. Experimental results demonstrate that SWTBPR outperforms other existing video recommendation algorithms and solves the data sparsity and cold start problem with a real-world dataset collected from Sina Weibo.