期刊
FRONTIERS IN PSYCHOLOGY
卷 13, 期 -, 页码 -出版社
FRONTIERS MEDIA SA
DOI: 10.3389/fpsyg.2022.778722
关键词
social network; personality traits; asymmetric interaction; ego-network; social relationship prediction
This study aims to improve the accuracy of link prediction in directed social networks by proposing a four-dimensional link prediction model that integrates personality link preference and asymmetric interaction. Comparative experiments confirm the higher accuracy of the proposed model compared to the model based solely on similarity.
Social networks have become an important way for users to find friends and expand their social circle. Social networks can improve users' experience by recommending more suitable friends to them. The key lies in improving the accuracy of link prediction, which is also the main research issue of this study. In the study of personality traits, some scholars have proved that personality can be used to predict users' behavior in social networks. Based on these studies, this study aims to improve the accuracy of link prediction in directed social networks. Considering the integration of personality link preference and asymmetric interaction into the link prediction model of social networks, a four-dimensional link prediction model is proposed. Through comparative experiments, it is proved that the four-dimensional social relationship prediction model proposed in this study is more accurate than the model only based on similarity. At the same time, it is also verified that the matching degree of personality link preference and asymmetric interaction intensity in the model can help improve the accuracy of link prediction.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据