Hate speech has unfortunately become a significant phenomenon on social media platforms, and it can cover various topics (misogyny, sexism, racism, xenophobia, etc.) and targets (e.g., black people, women). Various hate speech detection datasets have been proposed, some annotated for specific topics, and others for hateful speech in general. In either case, they often employ different annotation guidelines, which can lead to inconsistencies, even in datasets focusing on the same topics. This can cause issues in models trying to generalize across more data and more topics in order to improve detection accuracy. In this paper, we propose, for the first time, a topic-oriented approach to study generalization across popular hate speech datasets. We first perform a comparative analysis of the performances of Transformer-based models in capturing topic-generic and topic-specific knowledge when trained on different datasets. We then propose a novel, simple yet effective approach to study more precisely which topics are best captured in implicit manifestations of hate, showing that selecting combinations of datasets with better out-of-domain topical coverage improves the reliability of automatic hate speech detection.

The manner in which gender is portrayed in materials used to teach children conveys messages about people’s roles in society. In this paper, we measure the gendered depiction of central domains of social life in 100 years of highly influential children’s books. We make two main contributions: (1) we find that the portrayal of gender in these books reproduces traditional gender norms in society, and (2) we publish StoryWords 1.0, the first word embeddings trained on such a large body of children’s literature. We find that, relative to males, females are more likely to be represented in relation to their appearance than in relation to their competence; second, they are more likely to be represented in relation to their role in the family than their role in business. Finally, we find that non-binary or gender-fluid individuals are rarely mentioned. Our analysis advances understanding of the different messages contained in content commonly used to teach children, with immediate applications for practice, policy, and research.

In this paper, we focus on the detection of sexist hate speech against women in tweets studying for the first time the impact of gender stereotype detection on sexism classification. We propose: (1) the first dataset annotated for gender stereotype detection, (2) a new method for data augmentation based on sentence similarity with multilingual external datasets, and (3) a set of deep learning experiments first to detect gender stereotypes and then, to use this auxiliary task for sexism detection. Although the presence of stereotypes does not necessarily entail hateful content, our results show that sexism classification can definitively benefit from gender stereotype detection.

Social media networks have become a space where users are free to relate their opinions and sentiments which may lead to a large spreading of hatred or abusive messages which have to be moderated. This paper presents the first French corpus annotated for sexism detection composed of about 12,000 tweets. In a context of offensive content mediation on social media now regulated by European laws, we think that it is important to be able to detect automatically not only sexist content but also to identify if a message with a sexist content is really sexist (i.e. addressed to a woman or describing a woman or women in general) or is a story of sexism experienced by a woman. This point is the novelty of our annotation scheme. We also propose some preliminary results for sexism detection obtained with a deep learning approach. Our experiments show encouraging results.

In a context of offensive content mediation on social media now regulated by European laws, it is important not only to be able to automatically detect sexist content but also to identify if a message with a sexist content is really sexist or is a story of sexism experienced by a woman. We propose: (1) a new characterization of sexist content inspired by speech acts theory and discourse analysis studies, (2) the first French dataset annotated for sexism detection, and (3) a set of deep learning experiments trained on top of a combination of several tweet’s vectorial representations (word embeddings, linguistic features, and various generalization strategies). Our results are encouraging and constitute a first step towards offensive content moderation.

The massive growth of user-generated web content through blogs, online forums and most notably, social media networks, led to a large spreading of hatred or abusive messages which have to be moderated. This paper proposes a supervised approach to hate speech detection towards immigrants and women in English tweets. Several models have been developed ranging from feature-engineering approaches to neural ones.

Social media networks have become a space where users are free to relate their opinions and sentiments which may lead to a large spreading of hatred or abusive messages which have to be moderated. This paper proposes a supervised approach to hate speech detection from a multilingual perspective. We focus in particular on hateful messages towards two different targets (immigrants and women) in English tweets, as well as sexist messages in both English and French. Several models have been developed ranging from feature-engineering approaches to neural ones. Our experiments show very encouraging results on both languages.