Sentiment-Based Influence Detection on Twitter

• Carolina Bigonha UFMG
• Mirella M. Moro UFMG
• Marcos A. Gonçalves UFMG

Abstract

We propose a method for answering the question on how to find influential users for a topic in large online communities. This method for ranking users in Twitter is based on a combination of the users’ position in networks that emerge from their relations, the polarity and the textual characteristics of their posts. Our evaluation shows that our approach can successfully identify influential users on different datasets.

References

C. Bigonha, T. Cardoso, M. Moro, M. Gonçalves, and V. Almeida. Detecting evangelists and detractors on twitter. In Simpósio Brasileiro de Sistemas Multimídia e Web, 2010.

C. Bigonha, T. Cardoso, M. Moro, M. Gonçalves, and V. Almeida. Sentiment-based influence detection on twitter. Journal of the Brazilian Computer Society, 18(3):169–183, 2012.

J. Brown, A. J. Broderick, and N. Lee. Word of mouth communication within online communities: Conceptualizing the online social network. Journal of Interactive Marketing, 21(3):2–20, 2007.

E. Katz, P. Lazarsfeld, and E. Roper. Personal influence: the part played by people in the flow of mass communications. Transaction Publishers, 1955.

E. S. Kwon and Y. Sung. Follow Me! Global Marketers’ Twitter Use. Journal of Interactive Advertising, 12:4–16, 2011.

J. Lee, D. Park, and I. Han. The effect of negative online consumer reviews on product attitude: An information processing view. Electronic Commerce Research and Applications, 7(3), 2008.

S. Ressler. Perspectives on electronic publishing: standards, solutions, and more. 1993.