Hate-Speech Spanish Lexicons

This repository provides curated lexical resources for hate speech detection in Spanish, developed by researchers at the Universidad de Jaén. It includes four domain-specific lexicons compiled to support natural language processing (NLP) tasks targeting harmful content in Spanish-language social media, particularly Twitter.
The collection comprises four files:

Xenophobia lexicon — 44 hateful terms directed at immigrants
Immigrant lexicon — 250 words referring to immigrant nationalities
Misogyny lexicon — 183 terms expressing hatred toward women
Insults lexicon — 279 general-purpose offensive terms

These resources were created in the context of the paper "Detecting Misogyny and Xenophobia in Spanish Tweets Using Language Technologies" (Plaza-Del-Arco et al., 2020, ACM Transactions on Internet Technology), and are intended as feature extraction tools for machine learning classifiers or rule-based hate speech detection systems.