Observing the Southern US Culture of Honor Using Large-Scale Social Media Analysis

TL;DR

This study uses large-scale social media analysis and GPT-3.5 to investigate the presence of a culture of honor in the US South by examining retaliatory behaviors in online insults.

Contribution

It introduces a novel large-scale LLM-based methodology to operationalize and test cultural hypotheses using social media data.

Findings

US Southerners are more likely to retaliate to personal attacks.

GPT-3.5 effectively detects insults and geolocates users.

The approach validates large-scale hypothesis testing using LLMs.

Abstract

A \textit{culture of honor} refers to a social system where individuals' status, reputation, and esteem play a central role in governing interpersonal relations. Past works have associated this concept with the United States (US) South and related with it various traits such as higher sensitivity to insult, a higher value on reputation, and a tendency to react violently to insults. In this paper, we hypothesize and confirm that internet users from the US South, where a \textit{culture of honor} is more prevalent, are more likely to display a trait predicted by their belonging to a \textit{culture of honor}. Specifically, we test the hypothesis that US Southerners are more likely to retaliate to personal attacks by personally attacking back. We leverage OpenAI's GPT-3.5 API to both geolocate internet users and to automatically detect whether users are insulting each other. We validate the use of GPT-3.5 by measuring its performance on manually-labeled subsets of the data. Our work demonstrates the potential of formulating a hypothesis based on a conceptual framework, operationalizing it in a way that is amenable to large-scale LLM-aided analysis, manually validating the use of the LLM, and drawing a conclusion.