Discovering Sentiment of Social Messages by Mining Message Correlations
With explosive growth of the Internet, the amount of information in text form is growing rapidly and the demand for data analysis is also increases. We can perform sentiment analysis on a large set of text messages to discover valuable knowledge and obtain enormous benefits in national security, business, politics, economics, etc. However, text messages from the social networks are rather different from those of traditional text documents. Therefore, it is difficult but essential to develop an effective method of sentiment exploration in social networks. In this paper we first applied a neural network model, namely the self-organizing maps, to cluster similar messages and sentiment keywords, respectively. We then developed an association discovery process to find the associations between a message and some sentiment keywords. The sentiment of a message is then determined according to such associations. We performed experiments on Twitter messages and obtained promising results.
KeywordsSentiment Analysis Social Network Analysis Text Mining Self-Organizing Map
Unable to display preview. Download preview PDF.
- 1.comSCORE: It’s a social world: Top 10 need-to-knows about social networking and where it’s headed (2011), http://www.comscore.com/Insights/Presentations_and_Whitepapers/2011/it_is_a_social_world_top_10_need-to-knows_about_social_networking
- 2.Nielsen: Social media report 2012: Social media comes of age (2012), http://www.nielsen.com/us/en/newswire/2012/social-media-report-2012-social-media-comes-of-age.html
- 3.Lipsman, A., Mudd, G., Rich, M., Bruich, S.: The power of like: How brands reach and influence fans through social media marketing (2011), http://www.comscore.com/Insights/Presentations_and_Whitepapers/2011/The_Power_of_Like_How_Brands_Reach_and_Influence_Fans_Through_Social_Media_Marketing
- 4.Krikorian, R.: New tweets per second record, and how! (2013), https://blog.twitter.com/2013/new-tweets-per-second-record-and-how
- 7.Turney, P.D.: Thumbs up or thumbs down?: Semantic orientation applied to unsupervised classification of reviews. In: Proceedings of the 40th Annual Meeting on Association for Computational Linguistics, ACL 2002, pp. 417–424. Association for Computational Linguistics, Stroudsburg (2002)Google Scholar
- 8.Pang, B., Lee, L., Vaithyanathan, S.: Thumbs up?: Sentiment classification using machine learning techniques. In: Proceedings of the ACL 2002 Conference on Empirical Methods in Natural Language Processing, EMNLP 2002, vol. 10, pp. 79–86. Association for Computational Linguistics, Stroudsburg (2002)CrossRefGoogle Scholar
- 9.Pang, B., Lee, L.: Seeing stars: Exploiting class relationships for sentiment categorization with respect to rating scales. In: Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics, ACL 2005, pp. 115–124. Association for Computational Linguistics, Stroudsburg (2005)CrossRefGoogle Scholar
- 10.Snyder, B., Barzilay, R.: Multiple aspect ranking using the Good Grief algorithm. In: Proceedings of the Joint Human Language Technology/North American Chapter of the ACL Conference (HLT-NAACL), pp. 300–307 (2007)Google Scholar
- 12.Kim, S.M., Hovy, E.: Identifying and analyzing judgment opinions. In: Proceedings of the Main Conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics, HLT-NAACL 2006, pp. 200–207. Association for Computational Linguistics, Stroudsburg (2006)CrossRefGoogle Scholar