Old wine in old glasses: Comparing computational and qualitative methods in identifying incivility on Persian Twitter during the #MahsaAmini movement

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Kermani, Hossein, Oudlajani, Fatemeh, Yarahmadi, Pardis, Soltani, Hamideh Mahdi, Makki, Mohammad, HosseiniKhoo, Zahra
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914315770003456
author Kermani, Hossein
Oudlajani, Fatemeh
Yarahmadi, Pardis
Soltani, Hamideh Mahdi
Makki, Mohammad
HosseiniKhoo, Zahra
author_facet Kermani, Hossein
Oudlajani, Fatemeh
Yarahmadi, Pardis
Soltani, Hamideh Mahdi
Makki, Mohammad
HosseiniKhoo, Zahra
contents This paper compares three approaches to detecting incivility in Persian tweets: human qualitative coding, supervised learning with ParsBERT, and large language models (ChatGPT). Using 47,278 tweets from the #MahsaAmini movement in Iran, we evaluate the accuracy and efficiency of each method. ParsBERT substantially outperforms seven evaluated ChatGPT models in identifying hate speech. We also find that ChatGPT struggles not only with subtle cases but also with explicitly uncivil content, and that prompt language (English vs. Persian) does not meaningfully affect its outputs. The study provides a detailed comparison of these approaches and clarifies their strengths and limitations for analyzing hate speech in a low-resource language context.
format Preprint
id arxiv_https___arxiv_org_abs_2602_08688
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Old wine in old glasses: Comparing computational and qualitative methods in identifying incivility on Persian Twitter during the #MahsaAmini movement
Kermani, Hossein
Oudlajani, Fatemeh
Yarahmadi, Pardis
Soltani, Hamideh Mahdi
Makki, Mohammad
HosseiniKhoo, Zahra
Computation and Language
Computers and Society
This paper compares three approaches to detecting incivility in Persian tweets: human qualitative coding, supervised learning with ParsBERT, and large language models (ChatGPT). Using 47,278 tweets from the #MahsaAmini movement in Iran, we evaluate the accuracy and efficiency of each method. ParsBERT substantially outperforms seven evaluated ChatGPT models in identifying hate speech. We also find that ChatGPT struggles not only with subtle cases but also with explicitly uncivil content, and that prompt language (English vs. Persian) does not meaningfully affect its outputs. The study provides a detailed comparison of these approaches and clarifies their strengths and limitations for analyzing hate speech in a low-resource language context.
title Old wine in old glasses: Comparing computational and qualitative methods in identifying incivility on Persian Twitter during the #MahsaAmini movement
topic Computation and Language
Computers and Society
url https://arxiv.org/abs/2602.08688