RESEARCH ARTICLE Studying User Income through Language, Behaviour and Affect in Social Media

Automatically inferring user demographics from social media posts is useful for both social science research and a range of downstream applications in marketing and politics. We present the first extensive study where user behaviour on Twitter is used to build a predic-tive model of income. We apply non-linear methods for regression, i.e. Gaussian Pro-cesses, achieving strong correlation between predicted and actual user income. This allows us to shed light on the factors that characterise income on Twitter and analyse their interplay with user emotions and sentiment, perceived psycho-demographics and language use expressed through the topics of their posts. Our analysis uncovers correlations between dif-ferent feature categories and income, some of which reflect common belief e.g. higher per-ceived education and intelligence indicates higher earnings, known differences e.g. gender and age differences, however, others show novel findings e.g. higher income users express more fear and anger, whereas lower income users express more of the time emotion and opinions