Topological Influence‐Aware Recommendation on Social Networks

Abstract

Users in online networks exert different influence during the process of information propagation, and the heterogeneous influence may contribute to personalized recommendations. In this paper, we analyse the topology of social networks to investigate users’ influence strength on their neighbours. We also exploit the user-item rating matrix to find the importance of users’ ratings and determine their influence on entire social networks. Based on the local influence between users and global influence over the whole network, we propose a recommendation method with indirect interactions that makes adequate use of users’ relationships on social networks and users’ rating data. The two kinds of influence are incorporated into a matrix factorization framework. We also consider indirect interactions between users who do not have direct links with each other. Experimental results on two real-world datasets demonstrate that our proposed framework performs better than other state-of-the-art methods for all users and cold-start users. Compared with node degrees, betweenness, and clustering coefficients, coreness constitutes the best topological descriptor to identify users’ local influence, and recommendations with the measure of coreness outperform other descriptors of user influence.

Mining Heterogeneous Influence and Indirect Trust for Recommendation

“…With the rapid development of social networks, social recommendation that uses the social relationships among users to infer their preferences and make recommendations has emerged and been intensively researched in recent years. Social recommendation algorithms based on matrix factorization [8], [9], [14], [24], [25] have received more attention than neighbor based recommendation algorithms because the former have high prediction accuracy and good scalability.…”

“…One potential way to improve the recommendation accuracy of CF techniques and solve these problems is to incorporate social information provided by users into recommendation models [7]- [14]. The homophily theory [15] indicates that people are more likely to socialize with people who are similar with themselves.…”

Self-Presentation and Adolescent Altruistic Behaviors in Social Networks

“…Since most adolescents are in junior high school or senior high school stage, under the practical pressure of China's high school entrance examination and college entrance examination, the knowledge in this stage is mainly based on mathematical, physical, and chemical knowledge and is not much connected with the computer network and other aspects of knowledge. us, there are not many support behaviors in social networks [30]. For example, adolescents rarely upload useful programs.…”

A Clickthrough Rate Prediction Algorithm Based on Users’ Behaviors

“…The research methods in the recommendation system [15] such as collaborative filtering are also applicable to the advertisement click rate prediction. Huo et al [16] used collaborative filtering algorithm to find other neighboring pages similar to the page, and realized the click rate prediction, which was used as the basis for advertising recommendation.…”