Sexism Prediction in Spanish and English Tweets Using Monolingual and Multilingual BERT and Ensemble Models

TL;DR

This paper presents an ensemble-based multilingual approach using BERT models for sexism detection in English and Spanish tweets, achieving top results in the EXIST 2021 challenge.

Contribution

It introduces a novel ensemble strategy combining monolingual and multilingual BERT models with data translation for sexism classification in social media.

Findings

Ensemble models outperform individual BERT models.

The proposed system surpasses baseline performance.

Achieved top accuracy and F1-scores in the EXIST 2021 tasks.

Abstract

The popularity of social media has created problems such as hate speech and sexism. The identification and classification of sexism in social media are very relevant tasks, as they would allow building a healthier social environment. Nevertheless, these tasks are considerably challenging. This work proposes a system to use multilingual and monolingual BERT and data points translation and ensemble strategies for sexism identification and classification in English and Spanish. It was conducted in the context of the sEXism Identification in Social neTworks shared 2021 (EXIST 2021) task, proposed by the Iberian Languages Evaluation Forum (IberLEF). The proposed system and its main components are described, and an in-depth hyperparameters analysis is conducted. The main results observed were: (i) the system obtained better results than the baseline model (multilingual BERT); (ii) ensemble models obtained better results than monolingual models; and (iii) an ensemble model considering all individual models and the best standardized values obtained the best accuracies and F1-scores for both tasks. This work obtained first place in both tasks at EXIST, with the highest accuracies (0.780 for task 1 and 0.658 for task 2) and F1-scores (F1-binary of 0.780 for task 1 and F1-macro of 0.579 for task 2).