东北大学学报（自然科学版）

东北大学学报(自然科学版) ›› 2013, Vol. 34 ›› Issue (4): 490-493.DOI: -

• 信息与控制 • 上一篇    下一篇

基于LDA模型的中文微博话题意见领袖挖掘

冯时，景珊，杨卓，王大玲   

  1. (东北大学信息科学与工程学院，辽宁沈阳110819)
  • 收稿日期:2012-10-22 修回日期:2012-10-22 出版日期:2013-04-15 发布日期:2013-06-19
  • 通讯作者: 冯时
  • 作者简介:冯时(1981-)，男，辽宁沈阳人，东北大学讲师，博士；王大玲(1962-)，女，辽宁沈阳人，东北大学教授，博士生导师.
  • 基金资助:
    国家重点基础研究发展计划项目(2011CB302200-G)；国家自然科学基金资助项目(61100026，60973019).

Detecting Topical Opinion Leaders Based on LDA Model in Chinese Microblogs

FENG Shi， JING Shan， YANG Zhuo， WANG Daling   

  1. School of Information Science ＆ Engineering， Northeastern University， Shenyang 110819， China.
  • Received:2012-10-22 Revised:2012-10-22 Online:2013-04-15 Published:2013-06-19
  • Contact: FENG Shi
  • About author:-
  • Supported by:
    -

RichHTML

0

PDF (PC)

1893

摘要： 有效挖掘微博空间中的话题意见领袖成为亟待解决的热点问题.针对这一问题，提出了基于LDA语义信息和HowNet知识库的短文本子话题分类算法.对分类后的微博从显式、隐式及用户等方面综合衡量微博的影响力，并根据层次分析法对多个因素进行科学地权值分配.实验结果表明，提出的方法较基于支持向量机的方法具有更好的效果，同时提出的影响力度量模型可以有效地挖掘出微博中的话题意见领袖.

关键词: 微博, 短文本分类, 意见领袖, 情感分析, LDA

Abstract: How to effectively detect the opinion leaders in the Chinese microblog space has become a hot research problem in the related area. To tackle this issue， an algorithm combined LDA model and HowNet was proposed to classify the short texts in microblogs based on their underlying subtopics. Then an influence measurement containing the criteria on explicit， implicit and user features was introduced. An analytic hierarchy process method was employed to assign different weight of each parameter. Experiment results showed that the proposed short text classification method outperformed the traditional SVM based method， and the proposed influence measurement model could effectively detect the opinion leaders in the Chinese hot topic microblogs.

Key words: microblog, short text classification, opinion leader, sentiment analysis, LDA

中图分类号: