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

By Daniel Preotiuc-Pietro, Svitlana Volkova, Vasileios Lampos, Yoram Bachrach, Nikolaos Aletras. 2015

216 citations recorded by the source corpus.

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.

Subfields: Sociology and Political Science, Statistical and Nonlinear Physics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Sociology and Political Science

In Statistical and Nonlinear Physics

Citations in the corpus

How Polarized Have We Become? A Multimodal Classification of Trump Followers and Clinton Followers (2017, background): “Individual attributes such as age, gender, sentiment and even income, can be estimated using either texts [2, 39, 26] or images [17, 42].”
Deciphering the 2016 U.S. Presidential Campaign in the Twitter Sphere: A Comparison of the Trumpists and Clintonists (2016, background): “One way to measure social status is income, and there already exists research that predicts income based on user-generated tweets (Preotiuc-Pietro et al. 2015).”
Beyond Binary Labels: Political Ideology Prediction of Twitter Users (2017, methodology): “We use the method from (Preoţiuc-Pietro et al., 2015a) to compute topics using word2vec similarity (Mikolov et al., 2013a,b) and spectral clustering (Shi and Malik, 2000; von Luxburg, 2007) of different sizes (from 30 to 2000).”
User Classification with Multiple Textual Perspectives (2016, background): “, 2010), political orientation (Rao et al., 2010) and user occupational class prediction (Preotiuc-Pietro et al, 2015) are also popularly studied in recent years.”
Predicting judicial decisions of the European Court of Human Rights: a Natural Language Processing perspective (2016, background): “…dimensionality of the feature space, which is essential for feature selection, it limits overfitting to245 training data (Lampos et al., 2014; Preoţiuc-Pietro et al., 2015; Preoţiuc-Pietro et al., 2015) and246 also provides a more concise semantic representation.247 Classification Model248…”