Hate Speech and Hate Crime: A Cross-Disciplinary Analysis of Xenophobia in Greece

Maria Gavriilidou, Vasiliki Georgiadou, Lamprini Rori, Maria Pontiki


Abstract
This paper investigates the correlation of hate speech and hate crime, in a inter-disciplinary approach, using a computational hate speech and hate crime detection method in a socio-political science framework, coupling Natural Language Processing with Political Sciences. The study focuses on Greece in the turbulent period from 2015 to 2022 (a period marked by economic, refugee, foreign policy, and pandemic crises); it analyzes tweets to discern linguistic patterns used to verbally attack predefined target groups consisting of ethnic and religious minorities in the country. Furthermore, it investigates hate crimes reported in the press, against the same target groups and during the same period and proceeds to examine correlations between xenophobic attitudes expressed verbally through social media, and those manifested as physical attacks in real life.
Anthology ID:
2026.politicalnlp-1.15
Volume:
Proceedings of the 3rd Workshop on Natural Language Processing for Political Sciences (PoliticalNLP 2026)
Month:
May
Year:
2026
Address:
Palma, Mallorca (Spain)
Editors:
Haithem Afli, Houda Bouamor, Wajdi Zaghouani, Sahar Ghannay, Shehenaz Hossain
Venues:
PoliticalNLP | WS
SIG:
Publisher:
ELRA Language Resources Association (ELRA)
Note:
Pages:
139–148
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-politicalnlp-15
DOI:
10.63317/5pv79t8paewu
Bibkey:
Cite (ACL):
Maria Gavriilidou, Vasiliki Georgiadou, Lamprini Rori, and Maria Pontiki. 2026. Hate Speech and Hate Crime: A Cross-Disciplinary Analysis of Xenophobia in Greece. In Proceedings of the 3rd Workshop on Natural Language Processing for Political Sciences (PoliticalNLP 2026), pages 139–148, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).
Cite (Informal):
Hate Speech and Hate Crime: A Cross-Disciplinary Analysis of Xenophobia in Greece (Gavriilidou et al., PoliticalNLP 2026)
Copy Citation: