Title: "Fast Sentiment Strength Detection for the Social Web"
ABSTRACT
This talk will describe a sentiment analysis application, SentiStrength, which is designed to detect the strength of positive and negative sentiment in short informal social web texts. SentiStrength can be used unsupervised and approaches human-level accuracy for a range of different types of social web text. It has a range of tools to help customise it for specific domains. SentiStrength is available in seven languages and can be customised for new languages with about two weeks of work - although more effort is needed if there are morphology issues. The talk will illustrate some fun and some serious applications of SentiStrength - including one from Yahoo. It will give examples of sentiment analysis applied to tweets related to major media events and to the comments on YouTube videos, showing how sentiment analysis can give insights into how people use the social web to express sentiment and how sentiment can drive online communication.
http://sentistrength.wlv.ac.uk/
BIOGRAPHICAL NOTE
Mike Thelwall is a Professor of Information Science and leader of the Statistical Cybermetrics Research Group at the University of Wolverhampton, UK and a research associate at the Oxford Internet Institute. Mike has developed software and methods for gathering and analysing web data, including sentiment analysis, altmetrics and content analysis for Twitter, YouTube, blogs and the general web. He has published 225 refereed journal articles, 23 chapters and two books, including Introduction to Webometrics. He is an associate editor of the Journal of the Association for Information Science and Technology and sits on three other editorial boards.
http://www.scit.wlv.ac.uk/~cm1993/mycv.html
ABSTRACT
This talk will describe a sentiment analysis application, SentiStrength, which is designed to detect the strength of positive and negative sentiment in short informal social web texts. SentiStrength can be used unsupervised and approaches human-level accuracy for a range of different types of social web text. It has a range of tools to help customise it for specific domains. SentiStrength is available in seven languages and can be customised for new languages with about two weeks of work - although more effort is needed if there are morphology issues. The talk will illustrate some fun and some serious applications of SentiStrength - including one from Yahoo. It will give examples of sentiment analysis applied to tweets related to major media events and to the comments on YouTube videos, showing how sentiment analysis can give insights into how people use the social web to express sentiment and how sentiment can drive online communication. http://sentistrength.wlv.ac.uk/
BIOGRAPHICAL NOTE
Mike Thelwall is a Professor of Information Science and leader of the Statistical Cybermetrics Research Group at the University of Wolverhampton, UK and a research associate at the Oxford Internet Institute. Mike has developed software and methods for gathering and analysing web data, including sentiment analysis, altmetrics and content analysis for Twitter, YouTube, blogs and the general web. He has published 225 refereed journal articles, 23 chapters and two books, including Introduction to Webometrics. He is an associate editor of the Journal of the Association for Information Science and Technology and sits on three other editorial boards. http://www.scit.wlv.ac.uk/~cm1993/mycv.html 
mobile