北京邮电大学学报

  • EI核心期刊

北京邮电大学学报 ›› 2013, Vol. 36 ›› Issue (6): 50-54.doi: 10.13190/j.jbupt.2013.06.011

• 论文 • 上一篇    下一篇

新浪微博群体分级别情感行为分析及建模仿真

朱江, 王柏, 吴斌   

  1. 北京邮电大学 计算机学院, 北京 100876
  • 收稿日期:2013-03-28 出版日期:2013-12-31 发布日期:2013-10-08
  • 作者简介:朱摇江(1982—),男,博士生,E-mail:zhujiang@bupt.edu.cn;王摇柏(1962—),女,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(2013CB329603);国家自然科学基金项目(61074128)

Analysison Sina Micro-Blogging Graded Emotional Behavior and Its Modeling and Simulation

ZHU Jiang, WANG Bai, WU Bin   

  1. School of Computer Science, Beijing University of Posts and Telecommunications, Beijing 100876, China
  • Received:2013-03-28 Online:2013-12-31 Published:2013-10-08

摘要:

为研究社会网络用户情感行为,以新浪微博数据为基础,对用户微博内容情感进行分级,进而对微博用户群体情感行为进行分析,建立了分级别情感发帖模型,并进行了仿真实验. 通过分析发现用户在表达某一级别情感的发帖量均服从幂律分布,且幂指数随着情感级别趋向平和而增加. 大部分用户通过微博表达情感时较为平和,需要表达激烈的情感时,用户参与比例会减小. 在级别情感发帖模型的建立过程中,考虑到了发帖人受到周围情感环境因素的影响以及自身情感的随机性变化,并通过模型仿真的结果验证了分级别情感发帖量服从幂律分布以及幂指数的变化趋势.

关键词: 情感分级, 群体情感行为, 幂律分布

Abstract:

In order to study the social network users' emotional behavior, the massive sina micro-blogging data is graded by emotional stage, and the group emotional behavior is analyzed as well. An emotional stage posting model is established and model simulation is done. Analysis shows that the posting amount of users obeys power-law distribution at a certain emotional stage, and the exponent increases as the emotional stage tends to calm. Most of posts are peaceful when users express emotion through the micro-blogging, and the user participation rates will also decrease when the intense emotions need to be expressed. In the emotional stage posting model, the impact of the around emotional environmental factors of the poster is considered, and also the randomly changing of poster's own emotion. Finally the previous experiments are verified by model simulation.

Key words: emotional stage, group emotional behavior, power-law distribution

中图分类号: