A Language Model for Misogyny Detection in Latin American Spanish Driven by Multisource Feature Extraction and Transformers

Edwin Aldana-Bobadilla,Alejandro Molina-Villegas,Yuridia Montelongo-Padilla,Ivan Lopez-Arevalo,Oscar S Sordia

doi:10.3390/app112110467

Abstract

Creating effective mechanisms to detect misogyny online automatically represents significant scientific and technological challenges. The complexity of recognizing misogyny through computer models lies in the fact that it is a subtle type of violence, it is not always explicitly aggressive, and it can even hide behind seemingly flattering words, jokes, parodies, and other expressions. Currently, it is even difficult to have an exact figure for the rate of misogynistic comments online because, unlike other types of violence, such as physical violence, these events are not registered by any statistical systems. This research contributes to the development of models for the automatic detection of misogynistic texts in Latin American Spanish and contributes to the design of data augmentation methodologies since the amount of data required for deep learning models is considerable.

Highlights

According to a recent report released by the World Health Organization, ”Physical or sexual violence is a public health problem that affects more than one third of all women globally” [1]
The experiment consisted of assessing the performance of our approach from two aspects: (1) the learning ability of the model in terms of the well-known evaluation metrics to predict the misogyny degree on a test dataset consisting of sentences belonging to the corpus gathered via our proposal, and
We performed a sampling strategy known as k-folds in order to find the most reliable model that minimizes the overfitting

Summary

Introduction

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. According to a recent report released by the World Health Organization, ”Physical or sexual violence is a public health problem that affects more than one third of all women globally” [1]

Objectives

Results

Discussion

Conclusion