Twitter Text Topic Mining and Sentiment Analysis Under the Belt and Road Initiative

  • Zhao Changyu ,
  • Wu Yaping ,
  • Wang Jimin
Expand
  • 1. Department of Information Management, Peking University, Beijing 100871;
    2. Peking University Library, Beijing 100871

Received date: 2018-12-11

  Revised date: 2019-03-21

  Online published: 2019-10-05

Supported by

 

Abstract

[Purpose/significance] The Belt and Road Initiative has attracted widespread attention around the world, and users in many countries have expressed their opinions, comments and discussed with each other on twitter, the most representative social media. The discussion topic and emotional tendency of "the Belt And Road" in the world extracted from the tweets will be helpful for the government to optimize their propaganda strategies and increase the exposure and attention of the Belt and Road Initiative.[Method/process] This paper collected more than 60 000 tweets related to the Belt and Road Initiative in 2017, and respectively carried out data preprocessing, data description, topic mining, and sentiment analysis in Chinese and English, and realized cross-analysis of topics and emotions to draw conclusions.[Result/conclusion] The tweet theme in 2017 is mainly around the "Belt and Road Forum for International Cooperation". Chinese tweets pay more attention to the planning and implementation of the forum, as well as security issues, visits by the leadership, etc. The emotional value fluctuates greatly, especially the negative emotions on security issues. English tweets are more concerned with the facts of holding the summit forum and the economic effects brought by the forum. The emotional fluctuations are small, and the emotional value of the economic aspect is that the positive proportion is significantly higher than the negative and neutral emotional values.

Cite this article

Zhao Changyu , Wu Yaping , Wang Jimin . Twitter Text Topic Mining and Sentiment Analysis Under the Belt and Road Initiative[J]. Library and Information Service, 2019 , 63(19) : 119 -127 . DOI: 10.13266/j.issn.0252-3116.2019.19.012

References

[1] 黄炎秋. 建构主义国际关系视域下"一带一路"对非洲传播策略研究[D].武汉:华中师范大学, 2017.
[2] 朱桂生,黄建滨.美国主流媒体视野中的中国"一带一路"战略——基于《华盛顿邮报》相关报道的批评性话语分析[J].新闻界,2016(17):58-64.
[3] 龚言浩,甄峰,席广亮."一带一路"倡议关注与响应的空间格局——基于新浪微博数据的分析[J].地域研究与开发,2018,37(2):29-35.
[4] 贾爽. "一带一路":Twitter网络舆情分析与对策建议[D].南京:南京大学,2016.
[5] HOFMANN T. Probabilistic latent semantic indexing[J]. Sigir forum,2017, 51(2):211-218.
[6] BLEI D M, NG A Y, JORDAN M I. Latent dirichlet allocation[J]. Journal of machine learning research, 2003, 3(1):993-1022.
[7] 陈晓美,高铖,关心惠. 网络舆情观点提取的LDA主题模型方法[J]. 图书情报工作,2015, 59(21):21-26.
[8] MICHELSON M, MACSKASSY S A. Discovering users' topics of interest on twitter:a first look[C]//Workshop on analytics for noisy unstructured text data. New York:ACM, 2010.
[9] YOOSUN H, HONGJIN S. Opinion leadership on twitter and twitter use-motivations and patterns of twitter use and case study of opinion leaders on twitter[J]. Korean journal of broadcasting and telecommunication studies, 2010, 24(6):365-404.
[10] HU Y, JOHN A, SELIGMANN D D. Event analytics via social media[C]//ACM workshop on social and behavioural networked media access. New York:ACM, 2011:39-44.
[11] MEI Q, ZHAI C X. A mixture model for contextual text mining[C]//Proceedings of the 12th ACM SIGKDD international conference on knowledge discovery and data mining. New York:ACM, 2006:649-655.
[12] MOGHADDAM S, ESTER M. ILDA:Interdependent LDA model for learning latent aspects and their ratings from online product reviews[C]//Proceedings of the 34th international ACM SIGIR conference on research and development in information retrieval. New York:ACM, 2011:665-674.
[13] BLEI D M, LAFFERTY J D. Dynamic topic models[C]//Proceedings of the 23rd international conference on machine learning. New York:ACM, 2006:113-120.
[14] ALSUMAIT L, BARBARÁ D, DOMENICONI C. On-line lda:adaptive topic models for mining text streams with applications to topic detection and tracking[C]//Eighth IEEE international conference on Data mining. Washington, DC:IEEE, 2008:3-12.
[15] MIKOLOV T, SUTSKEVER I, CHEN K, et al. Distributed representations of words and phrases and their compositionality[C]//Advances in neural information processing systems. New York:Curran Associates, Inc., 2013:3111-3119.
[16] GO A, BHAYANI R, HUANG L. Twitter sentiment classification using distant supervision[R]. Cs224n project report. Palo Alto:Stanford University, 2009.
[17] JANSEN B J, ZHANG M, SOBEL K, et al. Twitter power:tweets as electronic word of mouth[J]. Journal of the American Society for Information Science & Technology, 2009, 60(11):2169-2188.
[18] TUMASJAN A, SPRENGER T O, SANDNER P G, et al. Predicting elections with twitter:what 140 characters reveal about political sentiment[C]//International conference on weblogs and social media, Icwsm 2010. Washington, DC:DBLP, 2010.
[19] BOLLEN J, PEPE A, MAO H. Modeling public mood and emotion:twitter sentiment and socio-economic phenomena[J]. Computer science, 2009, 44(12):2365-2370.
[20] SHERIDAN D P, DECKER H K, KLOUMANN I M, et al. Temporal patterns of happiness and information in a global social network:hedonometrics and Twitter[J]. PlOS ONE, 2011, 6(12):e26752.
[21] HU M, LIU B. Mining and summarizing customer reviews[C]//Tenth ACM SIGKDD international conference on knowledge discovery and data mining. Seattle:ACM, 2004:168-177.
[22] ZHANG L, GHOSH R, DEKHIL M, et al. Combining lexiconbased and learning-based methods for Twitter sentiment analysis[EB/OL].[2018-04-03]. https://www.hpl.hp.com/techreports/2011/HPL-2011-89.pdf.
[23] 知网发布情感分析用词语集[EB/OL].[2018-03-08]. http://www.keenage.com/html/c_bulletin_2007.htm.
[24] FELDMAN R. Techniques and applications for sentiment analysis[M]. New York:ACM, 2013.
[25] VOLKOVA S, WILSON T, YAROWSKY D. Exploring sentiment in social media:bootstrapping subjectivity clues from multilingual twitter streams[C]//Proceedings of ACL 2013-51st Annual Meeting of the Association for Computational Linguistics.Sofia:ACL,2013:505-510.
[26] VOLKOVA S, WILSON T, YAROWSKY D. Exploring demographic language variations to improve multilingual sentiment analysis in social media[C]//Proceedings of conference on empirical methods in natural language processing. Seattle:ACL,2013:1815-1827.
[27] PANG B, LEE L, VAITHYANATHAN S. Thumbs up?:sentiment classification using machine learning techniques[C]//Proceedings of the ACL-02 conference on empirical methods in natural language processing-Volume 10. Philadelphia:ACM,2002:79-86.
[28] 张志华. 基于深度学习的情感词向量及文本情感分析的研究[D].武汉:华东师范大学,2016.
[29] 范云满, 马建霞. 基于LDA与新兴主题特征分析的新兴主题探测研究[J]. 情报学报, 2014, 33(7):698-711.
[30] 贺亮, 李芳. 基于话题模型的科技文献话题发现和趋势分析[J]. 中文信息学报, 2012, 26(2):109-116.
[31] 杨希. 基于情感词典与规则结合的微博情感分析模型研究[D].合肥:安徽大学,2014.
[32] 法媒称中巴经济走廊重振巴基斯坦[EB/OL].[2018-04-03]. http://news.163.com/17/0805/00/CR1LUS9A00018AOQ_all.html.
[33] 2017年我对"一带一路"沿线国家投资合作情况[EB/OL].[2018-04-03]. http://fec.mofcom.gov.cn/article/fwydyl/tjsj/201801/20180102699450.shtml.
[34] "一带一路"国际合作高峰论坛"政策沟通"平行主题会议签署32个合作协议[EB/OL].[2018-04-03]. http://www.xinhuanet.com/2017-05/14/c_1120970716.htm.
Outlines

/