Automatic detection of sexism in social media with a multilingual approach

Comunicació presentada a: Iberian Languages Evaluation Forum (IberLEF 2021), celebrat el 21 de setembre de 2021 de manera virtualThis paper describes the participation of the LaSTUS/TALN team in the shared task EXIST: sEXism Identification in Social neTworks at IberLEF 2021. EXIST promotes the development of classification systems able to spot sexism in social media posts in English and Spanish. More specifically a binary classification task is proposed to classify posts in either sexist or not sexist, while a multi-class task challenges systems to identify the type of sexism present in the post. We address the two tasks with a transformers-based system applying a multi-lingual BERT model. The paper reports and discusses the results obtained by our team.Our work is partly supported from the project Context-aware Multilingual Text Simplification (ConMuTeS) PID2019-109066GB-I00/AEI/10.13039/501100011033 awarded by Ministerio de Ciencia, Innovaci´on y Universidades (MCIU) and by Agencia Estatal de Investigaci´on (AEI) of Spain