Earticle

초록

영어

Clustering of Weibo users is one of the most important topics in data mining on social network. Clustering can help dig out the relations among people or between people and resources. A lot of work relating to clustering has been done on analyzing personal relationship, whereas we focus our clustering model on preferences and interests. In this article, we propose a new clustering model focusing on users’ tags people choose to describe themselves. First, we will study the characteristics of Sina Weibo tags of users, which are the foundation of the new clustering model. Second, we will use the word2vec tool to cluster Weibo users based on their tags and verify the accuracy of the results.

목차

Abstract
 1. Introduction
 2. Related Work
  2.1. Tag Clustering
  2.2. Word2vec
 3. Study of Weibo Users’ Tags
  3.1. Suitable
  3.2. Long Tail
  3.3. Ambiguity
 4. Clustering Using Word2vec Tool
  4.1. Similarity Measures
  4.2. Tag Clustering and Result Analysis
 5. Clustering Validity
 6. Conclusion and Future Work
 References

키워드

저자

• Bai Xue [ Department of Computer Science and Technology Beijing Foreign Studies University Beijing, China ]
• Chen Fu [ Department of Computer Science and Technology Beijing Foreign Studies University Beijing, China ]
• Zhan Shaobin [ Shenzhen institute of information & technology Shenzhen, China ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Grid and Distributed Computing

• 간기

  격월간

• pISSN

  2005-4262

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605