25 Apr
11:00 - 12:00
Data Science Research Talk

More than a feeling: understanding the interactions between online social networks, language, and well-being

by visiting professor Prof. Dr. Johan Bollen


Social media platforms cater to a fundamental human need for social connections, but, surprisingly, their use may be associated with lower levels of individual well-being and increased incidence of mental health issues. When we extract longitudinal indicators of subjective well-being from the online language of hundreds of thousands of individuals and compare the results to their social relations, we observe a strong homophily of subjective well-being in online social networks. Most social media users nevertheless experience a situation in which their friends on average are more more popular and happier than they are, a so-called friendship and happiness paradox. When we analyze the language of tens of thousands of individuals before and after they report experiencing a strong emotion, we also observe how these emotions evolve over time at the resolution of individual minutes. Notably, valence levels rapidly return to baseline levels immediately after individuals put their feelings into words, suggesting the effects of individual emotion regulation strategies such as affect labeling. Combined these results suggest distinct pathways through which social media use may exert both its deleterious and beneficial effects on individual and social well-being. I will conclude with a brief overview of our present efforts to model the morbidity, online correlates, and longitudinal dynamics of mental health issues from large-scale social media data.


Johan Bollen is a professor at the Indiana University School of Informatics and Computing after serving as a staff scientist at the Los Alamos National Laboratory from 2005-2009.  He obtained his PhD in Experimental Psychology from the Vrije Universiteit Brussel (2001). His research investigates how behavior, language, information, and emotions interact in online networks with applications in public health. It has been funded by the NSF, DARPA, IARPA, EDA, NASA, and Andrew W. Mellon Foundation. He is a co-director of the Indiana University Center for Social and Bio-Medical Complexity and a fellow at the Wageningen University SparcS center. He has published more than 75 articles on computational science, network science, social media analytics, and informetrics.
https://www.informatics.indiana.edu/jbollen/ and https://scholar.google.com/citations?hl=en&user=jDmcdsUAAAAJ.

Also read