PREDICTING INDIVIDUAL WELL-BEING THROUGH THE LANGUAGE OF SOCIAL MEDIA

H. Andrew Schwartz¹, Maarten Sap², Margaret L. Kern³, Johannes C. Eichstaedt², Adam Kapelner⁴, Megha Agrawal², Eduardo Blanco⁵, Lukasz Dziurzynski², Gregory Park², David Stillwell⁶, Michal Kosinski⁷, Martin E.P. Seligman², Lyle H. Ungar²

¹Computer Science, Stony Brook University
²Positive Psychology Center & Computer and Information Sciences, University of Pennsylvania
³Graduate School of Education, University of Melbourne
⁴Department of Mathematics, Queens College
⁵Computer Science, University of North Texas
⁶Psychometrics Centre, University of Cambridge
⁷Stanford Business School

Pacific Symposium on Biocomputing 21:516-527(2016)

© 2016 World Scientific
Open Access chapter published by World Scientific Publishing Company and distributed under the terms of the Creative Commons Attribution (CC BY) 4.0 License.

Abstract

We present the task of predicting individual well-being, as measured by a life satisfaction scale, through the language people use on social media. Well-being, which encompasses much more than emotion and mood, is linked with good mental and physical health. The ability to quickly and accurately assess it can supplement multi-million dollar national surveys as well as promote whole body health. Through crowd-sourced ratings of tweets and Facebook status updates, we create message-level predictive models for multiple components of well-being. However, well-being is ultimately attributed to people, so we perform an additional evaluation at the user-level, finding that a multi-level cascaded model, using both message-level predictions and user- level features, performs best and outperforms popular lexicon-based happiness models. Finally, we suggest that analyses of language go beyond prediction by identifying the language that characterizes well-being.