Within the CyberEmotions project and elsewhere, sentiment analysis methods are being applied to social web data in order to gain insights into the role of sentiment in important events or normal online communication and to understand patterns of user behaviours. This talk will describe sentiment analysis methods that can be applied to social web data and make the case that traditional machine learning approaches can give sub-optimal results by identifying spurious sentiment patterns. The talk will explain how the sentiment strength detection program SentiStrength works and how it has been adapted for different social web environments, such as those where negativity or positivity are common, for topics for which key phrases with unusual sentiment meanings are common, and for ongoing communication where patterns of sentiment exchanges between participants can be harnessed to improve sentiment predictions.  The talk will be primarily based on the papers below.

1.  Thelwall, M. & Buckley, K. (in press). Topic-based sentiment analysis for the Social Web: The role of mood and issue-related words. Journal of the American Society for Information Science and Technology.

2. Thelwall, M., Buckley, K., & Paltoglou, G. (2012). Sentiment strength detection for the social Web. Journal of the American Society for Information Science and Technology, 63(1), 163-173.

3. Thelwall, M., Buckley, K., & Paltoglou, G. (2011). Sentiment in Twitter events. Journal of the American Society for Information Science and Technology, 62(2), 406-418.

4. Thelwall, M., Buckley, K., Paltoglou, G., Cai, D., & Kappas, A. (2010). Sentiment strength detection in short informal text. Journal of the American Society for Information Science and Technology, 61(12), 2544–2558.

• Legal notice:
  

  Copyright (c) Pielaszek Research, all rights reserved.
  The above materials, including auxiliary resources, are subject to Publisher's copyright and the Author(s) intellectual rights. Without limiting Author(s) rights under respective Copyright Transfer Agreement, no part of the above documents may be reproduced without the express written permission of Pielaszek Research, the Publisher. Express permission from the Author(s) is required to use the above materials for academic purposes, such as lectures or scientific presentations.
  In every case, proper references including Author(s) name(s) and URL of this webpage: https://science24.com/paper/28450 must be provided.

1. Observations and analysis  of the origins of lognormal distributions of  user post lengths in  Internet discussions
2. Negative emotions as a fuel for discussion in cyber communities