• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

J4 ›› 2015, Vol. 37 ›› Issue (11): 2175-2181.

• 论文 • 上一篇    下一篇

一种基于词序的社会情感演变分析模型

刘义红1,2,朱琛2,祝恒书3   

  1. (1.淮南师范学院计算机学院,安徽 淮南 232001;2.中国科学技术大学计算机科学与技术学院,安徽 合肥 230027;
    3.百度研究院大数据实验室,北京 100085)
  • 收稿日期:2015-08-13 修回日期:2015-10-21 出版日期:2015-11-25 发布日期:2015-11-25
  • 基金资助:

    国家杰出青年科学基金资助项目(61325010);安徽省教育厅自然科学基金资助项目(KJ2013Z299)

BTMESE:a bigram topic model for
analyzing the evolution of social emotions 

LIU Yihong1,2,ZHU Chen2,ZHU Hengshu3   

  1. (1.College of Computer,Huainan Normal University,Huainan 232001;
    2.College of Computer Science and Technology,University of Science and Technology of China,Hefei 230027;
    3.Big Data Lab,Baidu Research,Beijing 100085,China)
  • Received:2015-08-13 Revised:2015-10-21 Online:2015-11-25 Published:2015-11-25

摘要:

提出了一种基于词序的社会情感演变分析模型(BTMESE),模型通过引入文档中词与词之间的前后关联性,以期有效地揭示时间、文本、情感三种信息之间的潜在联系,进而追踪社会情感演变趋势,进一步提高情感分析的准确率。该模型可应用于情感预测、时间预测等领域。通过在真实世界的数据集上进行验证,结果证明该模型简单有效,能够较好地进行社会情感分析。

关键词: 词序, 情感分析, 社交媒体, 主题模型

Abstract:

We introduce a novel bigram topic model for analyzing the evolution of social emotions (BTMESE). Specifically, the proposed model can discern the semantic relationships among time, texts, and social emotions by creatively integrating wordorder information. In particular, the model could be applied to a wide range of application scenarios,such as emotion prediction and time prediction. The experiments based on real world datasets validate the model's effectiveness in terms of social emotion analysis.

Key words: wordorder;emotion analysis;social media;topic model