Abstract

[ Slides ]

Abstract

Over the past few years user-generated content has been the centre of various research efforts in the domain of statistical natural language processing. In particular, the open nature of the microblogging platform of Twitter provided the opportunity for various appealing ideas to be evaluated. Based on the hypothesis that this online stream of content should represent at least a biased fraction of real-world situations or opinions, we have proposed core algorithms for nowcasting the rate of an infectious disease, such as influenza, or even a natural phenomenon like rainfall rates [1,2]. A simplified emotion analysis on a longitudinal set of tweets revealed interesting patterns, including signs of rising anger and fear before the UK riots in August, 2011 [3]. By extending linear text regression approaches to embed user relevance, we proposed a family of bilinear regularised regression models, which found application in the approximation of voting intention trends [4]. Finally, we attempted to reverse the previous modelling principle to look into how various user attributes or behaviours may influence a generic notion of user-impact [5].

1. Lampos and Cristianini. Tracking the flu pandemic by monitoring the Social Web, Cognitive Information Processing ‘10.
2. Lampos and Cristianini. Nowcasting Events from the Social Web with Statistical Learning, ACM TIST (2012).
3. Lansdall-Welfare, Lampos and Cristianini. Effects of the Recession on Public Mood in the UK, WWW ‘12.
4. Lampos, Preotiuc-Pietro and Cohn. A user-centric model of voting intention from Social Media, ACL ‘13.
5. Lampos, Aletras, Preotiuc-Pietro and Cohn. Predicting and Characterising User Impact on Twitter, EACL ‘14.