期刊文献+

社交媒体中表情符号的使用行为及成因分析 被引量:5

Usage Behavior and Cause of Emoji in Social Media
下载PDF
导出
摘要 为了探究社交媒体中表情符号的使用现象及其成因,分析了新浪微博“昆山反杀案”话题下的1800958条微博中的表情使用情况。首先对表情使用频次进行统计分析,研究群体中表情的重复使用现象。然后对高频表情以及微博文本进行情感分类,分析个体用户表情使用的多样性。研究表明:微博中存在大量表情符号且出现频率呈长尾分布并遵循齐夫定律;高频表情的演变可以反映出事件舆情;个体用户习惯使用23个相同表情或情感相近的不同表情。用户使用的表情符号往往与其表达的主题相关且受从众心理影响,而多表情连用现象通常是为了加强所表达的情感。 In order to explore the usage behavior and cause of emojis on social media,we analyzed the use of emojis in 1800958 microblogs under the topic of"Kunshan Case"on Sina Weibo.First,we analysis the frequency of emoji to study the phenomenon of repeated usage of emoji in the group,and then we classify popular emojis and micro-blog texts,we analyze the diversity of emoji usage of individual users.The result shows that:There are a lot of emojis in Weibo and the frequency of emojis is long-tailed and follow Zipf′s Law;The evolution of popular emojis can reflect the public opinion of the event;Individual users are used to using 2~3 same emojis or different emojis with similar emotions.The emojis used by users are often related to the topics they express and are influenced by the psychology of herds,and the phenomenon of co-occurrence emojis is usually to strengthen the emotions expressed.
作者 刘飞 王浩 许小可 LIU Fei;WANG Hao;XU Xiaoke(College of Information and Communication Engineering, Dalian Minzu University, Dalian 116600, China)
出处 《复杂系统与复杂性科学》 EI CSCD 2020年第3期70-77,共8页 Complex Systems and Complexity Science
基金 国家自然科学基金(61773091,61603073) 辽宁省重点研发计划指导计划项目(2018104016) 辽宁省“兴辽英才”计划项目(XLYC1807106) 辽宁省高等学校创新人才支持计划(LR2016070)。
关键词 表情符号 事件舆情 社交媒体 情感表达 emoji public opinion social media emotional expression
  • 相关文献

参考文献4

二级参考文献50

  • 1林传鼎,无.社会主义心理学中的情绪问题——在中国社会心理学研究会成立大会上的报告(摘要)[J].社会心理科学,2006,21(1):37-37. 被引量:15
  • 2M.Q. Hu, B. Liu. Mining and Summarizing Custom- er Reviews[C]//ACM SIGKDD 2004.. 168-177.
  • 3Bo Pang, Lillian Lee. Opinion mining and sentiment a- nalysis[C]//Foundations and Trends in Information Retrieval, 2(1-2):1-135.
  • 4M.Q. Hu, B. Liu. Opinion Extraction and Summari- zation on the Web[C]//AAAI06, Boston: 1621-1624.
  • 5H. Yu, V. Hatzivassiloglou. Towards Answering O- pinion Question: Separating Facts from Opinions and Identifying the Polarity of Opinion Sentences[C]// EMNLP'03 : 129-136.
  • 6Bo Pang, Lillian Lee, Shivakumar Vaithyanathan. Thumbs up? sentiment classification using machine learning techniques[C]//ACL'02: 79-86.
  • 7Bo Pang, Lillian Lee. A sentimental education: Senti- ment analysis using subjectivity summarization based on minimum cuts[C]//ACL'04: 271-278.
  • 8E. Riloff, J. Wiebe. 2003. Learning extraction pat-terns for subjective expressions[C]//EMNLP'03: 105- 112.
  • 9Glance, N. , M. Hurst, K. Nigam, et al. 2005. Deri- ving marketing intelligence from online discussion [C]//SIGKDD'05 : 419-428.
  • 10Wilson, T. , J. Wiebe, P. Hoffmann. 2005. Recog- nizing contextual polarity in phrase-level sentiment a- nalysis[C]//HLT-EMNLP'05 .. 347-354.

共引文献595

同被引文献76

引证文献5

二级引证文献10

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部