Source-linked AI summary
Personality Traits and Echo Chambers on Facebook
Alessandro Bessi
TL;DR
The relation between personality and group formation in online echo chambers remains unclear. The paper estimates personality traits from the behavior of commenters on US Facebook Science and Conspiracy pages, finding similar profiles and the same dominant personality model across both communities.
Problem
How personality relates to group formation in online echo chambers remains unclear, despite extensive study of polarization and online behavior.
Source: §1 · p. 2Method
The authors classify personality traits from online behavior among commenters on US Facebook pages supporting Science or Conspiracy narratives.
Source: §1 · p. 2Results
Takeaways & Limitations
The analysis suggests that specific personality traits are associated with considerable involvement in supporting narratives, while echo-chamber permanence slightly shapes profiles.
Source: §1 · p. 3
Abstract
from arXiv · showhide
In online social networks, users tend to select information that adhere to their system of beliefs and to form polarized groups of like minded people. Polarization as well as its effects on online social interactions have been extensively investigated. Still, the relation between group formation and personality traits remains unclear. A better understanding of the cognitive and psychological determinants of online social dynamics might help to design more efficient communication strategies and to challenge the digital misinformation threat. In this work, we focus on users commenting posts published by US Facebook pages supporting scientific and conspiracy-like narratives, and we classify the personality traits of those users according to their online behavior. We show that different and conflicting communities are populated by users showing similar psychological profiles, and that the dominant personality model is the same in both scientific and conspiracy echo chambers. Moreover, we observe that the permanence within echo chambers slightly shapes users' psychological profiles. Our results suggest that the presence of specific personality traits in individuals lead to their considerable involvement in supporting narratives inside virtual echo chambers.
1. Introduction
Although polarization and online behavior have been widely studied, how personality relates to group formation remains unclear. This study examines personality profiles among users of conflicting US Facebook narratives and finds similarities across the communities.
1. Introduction
- The relation between personality traits and group formation remains unclear despite extensive research on personality and online behavior.Echo chambers are polarized communities of like-minded users, shaped by confirmation bias and selective exposure.Source: §1 · pp. 1–2
- The study examines whether users in conflicting Science and Conspiracy echo chambers share personality traits and whether either narrative attracts particular psychological profiles.It focuses on commenters on US Facebook pages and uses an unsupervised personality-recognition approach.Source: §1 · p. 2
- Personality traits are similarly distributed across the communities, except emotional stability is higher among Conspiracy supporters; both groups share a dominant personality model.The authors also report similar significant trait correlations and very weak correlations between comment volume and personality traits, suggesting echo-chamber permanence slightly shapes profiles.Source: §1 · p. 3
2. Methods
The methods define echo-chamber membership among commenters on US Facebook pages and estimate users’ Big Five profiles from linguistic behavior. The analysis uses a five-year dataset and an unsupervised recognition approach.
2.1. Dataset
- The dataset covers commenters on 413 public US Facebook pages supporting Science or Conspiracy from January 2010 to December 2014.A user qualifies for a chamber by placing more than 95% of their likes on its pages; users with fewer than 50 comments are excluded.Source: §2.1 · p. 3
- The final dataset contains 25,767 Science supporters with 2,620,733 comments and 6,262 Conspiracy supporters with 666,592 comments.The study uses publicly available Facebook data; comments are treated as a way users express personality and participate in collective debate.Source: §2.1 · p. 3
2.2. Personality Model Recognition
- The recognition approach estimates each user’s Big Five traits from linguistic features statistically correlated with personality dimensions.Examples include first-person singular pronouns and parentheses for extraversion, and exclamation marks and longer words for emotional stability.Source: §2.2 · p. 4
- For each user, the method compares mean feature counts with dataset averages, adjusts trait scores according to known correlations, then encodes scores as five labels.Each label indicates the trait, its reverse, or neither.Source: §2.2 · pp. 4–5
3. Results and Discussion
Users in conflicting Science and Conspiracy echo chambers show similar personality distributions and correlated trait patterns, with the same personality model dominant in both. Comment activity is only weakly correlated with traits, and the authors conclude that echo-chamber permanence slightly shapes psychological profiles.
3.1. Distribution of Personality Traits
- The trait-correlation matrices are highly similar across Science and Conspiracy supporters (r = 0.996; simulated p-value < 0.01).The Mantel test used 104 Monte Carlo replicates.Source: §3.1 · p. 7, Figure 2 · p. 7
- Both echo chambers show low agreeableness and conscientiousness, high openness, and slightly introverted profiles; Conspiracy supporters have higher emotional stability than Science supporters.Emotional stability averages 0.45(±1.65) for Conspiracy supporters and 0.05(±1.56) for Science supporters (Mann-Whitney p-value < 10−6).Source: §3.1 · pp. 5–7
3.2. Personality and Echo Chambers
- “nynny” is the dominant personality model in both echo chambers, representing low extraversion, high emotional stability, low agreeableness and conscientiousness, and high openness.The authors report that this model exceeds 10% despite 243 possible combinations of the five traits.Source: §3.2 · p. 8, Table 1 · p. 8
- Comment counts have very weak correlations with personality traits in both echo chambers, and the authors conclude that echo-chamber permanence slightly shapes users’ psychological profiles.They suggest instead that specific personality traits lead to considerable involvement in supporting narratives.Source: §3.2 · pp. 8–9, Table 2 · p. 8
4. Conclusions
The authors compare five personality traits among users in conflicting Science and Conspiracy echo chambers. Their profiles are broadly similar, with higher emotional stability among Conspiracy supporters, and comment counts correlate only very weakly with traits.
- The analysis compares extraversion, emotional stability, agreeableness, conscientiousness, and openness among about 30K users in conflicting echo chambers.It uses a quantitative analysis of more than 3M comments.Source: §4 · p. 9
- Personality traits are similarly distributed across the two communities, except that emotional stability is higher among Conspiracy supporters.The prevalent personality model is the same in both echo chambers.Source: §4 · p. 9
- Comment counts have very weak Pearson correlations with personality traits; the authors suggest specific traits accompany considerable involvement in supporting narratives within echo chambers.Source: §4 · p. 9