Multi-label Categorization of Accounts of Sexism using a Neural Framework

TL;DR

This paper introduces the first multi-label classification framework for sexism accounts, utilizing a neural hierarchical model that combines various embeddings and leverages unlabeled data, significantly improving over existing methods.

Contribution

It presents the first multi-label sexism classification model, introduces the largest dataset for this task, and develops a neural architecture that integrates multiple embeddings and unlabeled data.

Findings

Proposed method outperforms baseline models.

Achieved high accuracy in multi-label sexism categorization.

Leveraged unlabeled data to enhance model performance.

Abstract

Sexism, an injustice that subjects women and girls to enormous suffering, manifests in blatant as well as subtle ways. In the wake of growing documentation of experiences of sexism on the web, the automatic categorization of accounts of sexism has the potential to assist social scientists and policy makers in studying and countering sexism better. The existing work on sexism classification, which is different from sexism detection, has certain limitations in terms of the categories of sexism used and/or whether they can co-occur. To the best of our knowledge, this is the first work on the multi-label classification of sexism of any kind(s), and we contribute the largest dataset for sexism categorization. We develop a neural solution for this multi-label classification that can combine sentence representations obtained using models such as BERT with distributional and linguistic word embeddings using a flexible, hierarchical architecture involving recurrent components and optional convolutional ones. Further, we leverage unlabeled accounts of sexism to infuse domain-specific elements into our framework. The best proposed method outperforms several deep learning as well as traditional machine learning baselines by an appreciable margin.