Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Journal of Guangxi Normal University(Natural Science Edition)》 2018-04
Add to Favorite Get Latest Update

Domain Experts Recommendation in Social Network Based on the LDA Theme Model of Trust

LIU Dianting;WU Lina;College of Mechanical and Control Engineering,Guilin University of Technology;College of Information Science and Engineering,Guilin University of Technology;  
With the development of Web 2.0 technology,the social network has provided a new and convenient platform to communicate and collaborate for people.Faced with the problem of network information overloaded,it is very difficult to find the experts who are interested in the topic and are reliable to make decisions based on experts' opinions.In this paper,domain experts recommendation in social network based on the LDA theme model of trust method is proposed.The personalized recommendation of domain experts for the user trust is implemented.The method is based on the topic model(LDA),the social network structure,the users' trust relationship and social influence.It makes up the deficiency of the traditional experts recommendation methods that only involve expert's characteristics which lead to low recommendation accuracy and the problem of the pattern of recommended results.Finally,the feasibility and effectiveness of the method are verified by experiments.
【Fund】: 国家自然科学基金(51165004);; 广西科学研究与技术开发计划(桂科攻1598007-15)
【CateGory Index】: TP391.3
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved