Tracking “Gross Community Happiness” from Tweets

Daniele Quercia, University of Cambridge
Jonathan Ellis,University College London
Licia Capra, University College London
Jon Crowcroft, University of Cambridge

We consider Twitter users based in a variety of London census communities, and study the relationship between sentiment expressed in residents’ tweets and community socioeconomic wellbeing.

We find that the two are highly correlated: the higher the normalized sentiment score of a community’s tweets, the higher the community’s socioeconomic well-being. This suggests that it is possible to effectively track the emotional health of local communities from their residents’ tweets in an unobtrusive way, as tweets are publicly available and easily crawled.

For more, see our full paper, Tracking “Gross Community Happiness” from Tweets.