User-level Weibo Recommendation incorporating Social Influence based on Semi-Supervised Algorithm

TL;DR

This paper introduces TSI-WR, a semi-supervised, factor graph-based Weibo recommendation algorithm that leverages both direct and indirect social influence at the topic level to improve recommendation accuracy amidst data sparsity.

Contribution

It proposes a novel social influence model incorporating topic-level influence and a semi-supervised algorithm to enhance Weibo recommendations.

Findings

Model outperforms baseline methods in experiments.

Incorporating social influence improves recommendation accuracy.

Semi-supervised approach reduces data sparsity effects.

Abstract

Tencent Weibo, as one of the most popular micro-blogging services in China, has attracted millions of users, producing 30-60 millions of weibo (similar as tweet in Twitter) daily. With the overload problem of user generate content, Tencent users find it is more and more hard to browse and find valuable information at the first time. In this paper, we propose a Factor Graph based weibo recommendation algorithm TSI-WR (Topic-Level Social Influence based Weibo Recommendation), which could help Tencent users to find most suitable information. The main innovation is that we consider both direct and indirect social influence from topic level based on social balance theory. The main advantages of adopting this strategy are that it could first build a more accurate description of latent relationship between two users with weak connections, which could help to solve the data sparsity problem; second provide a more accurate recommendation for a certain user from a wider range. Other meaningful contextual information is also combined into our model, which include: Users profile, Users influence, Content of weibos, Topic information of weibos and etc. We also design a semi-supervised algorithm to further reduce the influence of data sparisty. The experiments show that all the selected variables are important and the proposed model outperforms several baseline methods.