Skip to Main content Skip to Navigation

Automatic Hate Speech Detection on Social Media

Patricia Chiril 1 
1 IRIT-MELODI - MEthodes et ingénierie des Langues, des Ontologies et du DIscours
IRIT - Institut de recherche en informatique de Toulouse
Abstract : This dissertation is focused on two objectives: (I) Hate Speech detection and (II) Sexism detection in social media. (I) Hate Speech and harassment are widespread in online communication, due to users' freedom and anonymity and the lack of regulation provided by social media platforms. Hate speech is topically-focused (misogyny, sexism, racism, xenophobia, homophobia, etc.) and each specific manifestation of hate speech targets different vulnerable groups based on characteristics such as gender (misogyny, sexism), ethnicity, race, religion (xenophobia, racism, Islamophobia), sexual orientation (homophobia), and so on. Most automatic hate speech detection approaches cast the problem into a binary classification task without addressing either the topical focus or the target-oriented nature of hate speech. In this dissertation, we propose to tackle, for the first time, hate speech detection from a multi-target perspective. We leverage manually annotated datasets, to investigate the problem of transferring knowledge from different datasets with different topical focuses and targets. (II) Sexism is a type of hate speech. It can be defined as prejudice or discrimination based on a person's gender. It is based on the belief that one sex or gender is superior to another. We believe that it is important not only to be able to automatically detect messages with a sexist content but also to distinguish between real sexist messages and messages which relate sexism. Indeed, whereas messages could be reported and moderated in the first case as recommended by European laws, messages relating sexism experiences should not be moderated. We experimented with different neural models, in particular models that are able to detect the presence of gender stereotypes in order to improve sexism detection. Our results are encouraging and constitute a first step towards automatic sexist content moderation and demonstrate that multi-target hate speech detection from existing datasets is feasible, which is a first step towards hate speech detection for a specific topic/target when dedicated annotated data are missing.
Complete list of metadata
Contributor : ABES STAR :  Contact
Submitted on : Monday, March 7, 2022 - 10:40:59 AM
Last modification on : Monday, July 4, 2022 - 9:34:21 AM
Long-term archiving on: : Wednesday, June 8, 2022 - 6:59:14 PM


Version validated by the jury (STAR)


  • HAL Id : tel-03599458, version 1


Patricia Chiril. Automatic Hate Speech Detection on Social Media. Social and Information Networks [cs.SI]. Université Paul Sabatier - Toulouse III, 2021. English. ⟨NNT : 2021TOU30123⟩. ⟨tel-03599458⟩



Record views


Files downloads