An improved Apriori–based algorithm for friends recommendation in microblog. (6th November 2017)

• Record Type: Journal Article
• Authors: Liu, Li; Yu, Shuo; Wei, Xiang; Ning, Zhaolong
• Is Part Of: International journal of communication systems. Volume 31:Number 2(2018)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2017-11-06
• Subjects: apriori -- associate rules -- friend recommendation -- microblog; Telecommunication systems -- Periodicals; 621.382
• DOI: 10.1002/dac.3453
• Languages: English
• ISSNs: 1074-5351

Abstract

Summary: With the rapid development of Internet, the world has come into a new era of network interaction. Internet development in China makes various kinds of software available to users, by which relatives, close friends, and partners can achieve real‐time interactions. It is acknowledged that the recommended issues and persons are the most important parts for user experience. This study concentrates on how to provide a recommendation for users with a common interest in Microblog. We first illustrate some recommended algorithms based on data mining, and the implementation process of friend‐recommended system is then stated. After that, by integrating the characteristics of the user information, the forwarding and comments on information to associated users, we present an improved Apriori–based algorithm to rank the recommended information with confidence interval. Simulation results demonstrate the superiority and efficiency of our method. Abstract : We present an improved Apriori–based algorithm to rank the recommended information with confidence interval. The efficiency of our presented algorithm is almost 2.5 times compared with the improved page rank algorithm when the number of users reaches 704. Our method can optimize network performance through generating a TID set to replace the entire database.