Psycho-Demographic Analysis of the Facebook Rainbow Campaign

Yilun Wang, Himabindu Lakkaraju, Michal Kosinski, Jure Leskovec

Introduction

In 2015, millions of Facebook users adopted a rainbow filter on their profile pictures to signal support for marriage equality. This phenomenon, termed "pictivism," represents a significant shift in digital activism. Researchers from Stanford University conducted a large-scale "psycho-demographic" autopsy of this campaign, analyzing the digital footprints of nearly 800,000 users to uncover the psychological and social drivers behind such online movements.

Methodology and Data

The study utilized the myPersonality dataset, which contains psychological scores, profile data, and "Likes" for approximately 799,091 U.S. Facebook users. To identify participants, the researchers developed a high-precision computer vision algorithm to detect the rainbow filter. Personality was assessed using the Five Factor Model (FFM), and predictive modeling was employed to determine which factors most accurately identified campaign participants.

Psychological Predictors of Activism

A key finding of the study is the role of personality traits in digital activism. "Openness to experience" emerged as the strongest positive predictor. Interestingly, Neuroticism was also positively correlated, suggesting that individuals who are more emotionally reactive are more likely to take public stances on controversial issues. Conversely, Conscientiousness showed a negative correlation, potentially indicating that pictivism is often a spontaneous or impulsive act rather than a highly planned one.

The analysis revealed distinct demographic patterns among participants. Females, liberals, and non-believers were significantly more likely to join the campaign than their counterparts.

Age also played a critical role, with participation peaking among adults in their early 30s. Lower participation among adolescents suggests that social pressures or different priorities may influence younger cohorts differently.

Social influence was a powerful driver; the likelihood of a user participating grew linearly with the percentage of their friends who had already adopted the filter. Furthermore, geographic analysis showed a stark divide: participation rates were so distinct between historically Union and Confederate states that researchers could distinguish between them with an AUC of 0.98 based solely on campaign data.

The Predictive Power of Digital Footprints

One of the most significant insights was the stability of "Likes" as predictors. Facebook "Likes" recorded years prior to the campaign (2009–2011) were better indicators of participation than basic demographics like age or gender. A combined model incorporating "Likes," political/religious views, and personality traits achieved an AUC of 0.76 in identifying participants.

Conclusion

This research demonstrates that digital activism is not merely "slacktivism" but is deeply rooted in stable psychological traits and social structures. By moving beyond self-reported data to analyze real-world digital footprints, the study provides a robust framework for understanding how personality and social networks shape modern political expression.

Summary updated

Abstract

Over the past decade, online social media has had a tremendous impact on the way people engage in social activism. For instance, about 26M Facebook users expressed their support in upholding the cause of marriage equality by overlaying their profile pictures with rainbow-colored filters. Similarly, hundreds of thousands of users changed their profile pictures to a black dot condemning incidents of sexual violence in India. This act of demonstrating support for social causes by changing online profile pictures is being referred to as pictivism. In this paper, we analyze the psycho-demographic profiles, social networking behavior, and personal interests of users who participated in the Facebook Rainbow campaign. Our study is based on a sample of about 800K detailed profiles of Facebook users combining questionnaire-based psychological scores with Facebook profile data. Our analysis provides detailed insights into psycho-demographic profiles of the campaign participants. We found that personality traits such as openness and neuroticism are both positively associated with the likelihood of supporting the campaign, while conscientiousness exhibited a negative correlation. We also observed that females, religious disbelievers, democrats and adults in the age group of 20 to 30 years are more likely to be a part of the campaign. Our research further confirms the findings of several previous studies which suggest that a user is more likely to participate in an online campaign if a large fraction of his/her friends are already doing so. We also developed machine learning models for predicting campaign participation. Users' personal interests, approximated by Facebook user like activity, turned out to be the best indicator of campaign participation. Our results demonstrated that a predictive model which leverages the aforementioned features accurately identifies campaign participants (AUC=0.76).
BibTeX
@misc{wang2016psycho,
  author = {Yilun Wang and Himabindu Lakkaraju and Michal Kosinski and Jure Leskovec},
  title = {{Psycho-Demographic Analysis of the Facebook Rainbow Campaign}},
  year = {2016},
  eprint = {1610.05358},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/1610.05358},
}
Figure