Are generics and negativity about social groups common on social media? A comparative analysis of Twitter (X) data

Uwe Peters*, Ignacio Ojea Quintana

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Many philosophers hold that generics (i.e., unquantified generalizations) are pervasive in communication and that when they are about social groups, this may offend and polarize people because generics gloss over variations between individuals. Generics about social groups might be particularly common on Twitter (X). This remains unexplored, however. Using machine learning (ML) techniques, we therefore developed an automatic classifier for social generics, applied it to 1.1 million tweets about people, and analyzed the tweets. While it is often suggested that generics are ubiquitous in everyday communication, we found that most tweets (78%) about people contained no generics. However, tweets with generics received more “likes” and retweets. Furthermore, while recent psychological research may lead to the prediction that tweets with generics about political groups are more common than tweets with generics about ethnic groups, we found the opposite. However, consistent with recent claims that political animosity is less constrained by social norms than animosity against gender and ethnic groups, negative tweets with generics about political groups were significantly more prevalent and retweeted than negative tweets about ethnic groups. Our study provides the first ML-based insights into the use and impact of social generics on Twitter.

Original languageEnglish
Article number213
JournalSynthese
Volume203
Issue number6
DOIs
Publication statusPublished - Jun 2024

Keywords

  • Classifier
  • Generics
  • Machine learning
  • Negativity
  • Social groups
  • Twitter

Fingerprint

Dive into the research topics of 'Are generics and negativity about social groups common on social media? A comparative analysis of Twitter (X) data'. Together they form a unique fingerprint.

Cite this