电信科学 ›› 2016, Vol. 32 ›› Issue (7): 97-105.doi: 10.11959/j.issn.1000-0801.2016158

• 研究与开发 • 上一篇    下一篇

一种融入公众情感投入分析的微博话题发现与细分方法

琚春华1,2,鲍福光1,3,戴俊彦2   

  1. 1 浙江工商大学现代商贸研究中心，浙江 杭州310018
    2 浙江工商大学计算机与信息工程学院，浙江 杭州310018
    3 浙江工商大学工商管理学院，浙江 杭州310018
  • 出版日期:2016-07-20 发布日期:2017-04-26
  • 基金资助:
    国家自然科学基金资助项目;国家科技支撑计划基金资助项目;浙江省哲学社会科学规划课题;浙江省自然科学基金资助项目;教育部人文社会科学重点研究基地项目资助;教育部人文社会科学重点研究基地项目资助

Discovery and segmentation method in micro-blog topics based on public emotional engagement analysis

Chunhua JU1,2,Fuguang BAO1,3,Junyan DAI2   

  1. 1 School of Computer and Information Engineering,Zhejiang Gongshang University,Hangzhou 310018,China
    2 Contemporary Business and Trade Research Center of Zhejiang Gongshang University,Hangzhou 310018,China
    3 School of Business Administration,Zhejiang Gongshang University,Hangzhou 310018,China
  • Online:2016-07-20 Published:2017-04-26
  • Supported by:
    The National Natural Science Foundation of China;The National Key Technology R ＆ D Program of China;Zhejiang Province Philosophy Social Sciences Planning Project;Natural Science Foundation of Zhejiang Province of China;Key Research Institutes of Social Sciences and Humanities Ministry of Education;Key Research Institutes of Social Sciences and Humanities Ministry of Education

在线阅读

1

PDF下载

658

摘要：

为了提升微博话题发现效率以及发现质量问题，提出了一种融入公众情感投入分析的微博话题快速发现与细分方法，促使话题演化，进而产生新话题及其情感变化趋势。首先，基于情感词典和TFDF值在历史语料库中挖掘常用情感词并构建情感词库；其次，快速抽取情感文本，结合Sigmoid函数检测情感投入密集期，保证话题事件挖掘的质量；最后，通过改进的模糊C-均值聚类算法在新的微博数据中发现高质量话题。实验结果表明，本文方法能够有效提升移动环境下的话题发现效率及质量。

关键词: 情感词, 微博, 话题发现, NE-FCM

Abstract:

To improve the discovery efficiency and quality of micro-blog topic,a method of rapid discovery and segmentation in micro-blog topics based on public emotional engagement analysis was proposed,it would prompt evolution of the topics,then generate new topics and gain emotional change trend.Firstly,common emotional words were mined from corpus to build emotional thesaurus based on emotional word dictionary and TFDF.Then,emotional text was extracted quickly and sigmoid function was utilized to detect the intensive period of emotional engagement,ensuring the validity of topic mining.Besides,an improved adaptive FCM was used to cluster and discover topics.The experimental results show that this method can enhance the efficiency and quality of topic discovery in mobile environment.

Key words: emotional word, micro-blog, topic discovery, NE-FCM

No Suggested Reading articles found!