Assessing the impact of contextual information in hate speech detection

no code implementations • 2 Oct 2022 • Juan Manuel Pérez, Franco Luque, Demian Zayat, Martín Kondratzky, Agustín Moro, Pablo Serrati, Joaquín Zajac, Paula Miguel, Natalia Debandi, Agustín Gravano, Viviana Cotik

In this work, we provide a novel corpus for contextualized hate speech detection based on user responses to news posts from media outlets on Twitter.

Hate Speech Detection

RoBERTuito: a pre-trained language model for social media text in Spanish

1 code implementation • LREC 2022 • Juan Manuel Pérez, Damián A. Furman, Laura Alonso Alemany, Franco Luque

Experiments on a benchmark of tasks involving user-generated text showed that RoBERTuito outperformed other pre-trained language models in Spanish.

Language Modelling Natural Language Understanding +1

pysentimiento: A Python Toolkit for Opinion Mining and Social NLP tasks

1 code implementation • 17 Jun 2021 • Juan Manuel Pérez, Mariela Rajngewerc, Juan Carlos Giudici, Damián A. Furman, Franco Luque, Laura Alonso Alemany, María Vanina Martínez

In recent years, the extraction of opinions and information from user-generated text has attracted a lot of interest, largely due to the unprecedented volume of content in Social Media.

Fairness Opinion Mining +1

ANDES at SemEval-2020 Task 12: A jointly-trained BERT multilingual model for offensive language detection

1 code implementation • SEMEVAL 2020 • Juan Manuel Pérez, Aymé Arango, Franco Luque

This paper describes our participation in SemEval-2020 Task 12: Multilingual Offensive Language Detection.