Journal Article

Studying user income through language, behaviour and affect in social media

Lampos, Vasileios, Volkova, Svitlana, Bachrach, Yoram, Preotiuc-Pietro, Daniel, Aletras, Nikolaos

2015

Overview

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 predictive model of income. We apply non-linear methods for regression, i.e. Gaussian Processes, 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 different feature categories and income, some of which reflect common belief e.g. higher perceived 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.

• Publisher: Public Library of Science,Public Library of Science (PLoS)
• Subject: Affect / Age / Age differences / Artificial intelligence / Bildungsniveau / Computer science / Correlation / Correlation analysis / Data Collection - classification / Data Collection - methods / Data Collection - statistics & numerical data / Datasets / Datenanalyse / Datengewinnung / Demografischer Faktor / Demographics / Demography / Digital media / Educational Status / Einkommen / Einkommenshöhe / Emotionalität / Ethnicity / Female / Gaussian process / Gender / Großbritannien / Humans / Income / Income - classification / Income - statistics & numerical data / Indikator / Information Retrieval / Intelligence / Intelligenz (Psychologie) / Internet / Kommunikationsstruktur / Kommunikationsverhalten / Language / Linear Models / Linguistics / Male / Natural language processing / Neural networks / Prediction models / Präferenz / Psychology / Random variables / Regression analysis / Reproducibility of Results / Social aspects / Social behavior / Social media / Social Media - utilization / Social networks / Social science research / Social sciences / Soziale Software / Soziales Netzwerk / Soziales Verhalten / Sprache / Studies / Taxonomy / User generated content