He said “who’s gonna take care of your children when you are at ACL?”: Reported Sexist Acts are Not Sexist

Abstract

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.

Exploiting Emojis for Abusive Language Detection

“…quotation signs indicate reported speech; a tweet may report an abusive remark, however, the reported remark itself may not be perceived as abusive (Chiril et al, 2020) presence of exclamation sign? a typical means of expressing high emotional intensity improve performance.…”

Implicitly Abusive Language – What does it actually look like and why are we not getting there?

“…Given that social-media platforms commonly used for obtaining natural language data, such as Twitter, increasingly ban abusive language on their sites 7 , the amount of data available in which abusive language is actually used is decreasing. 8 However, there are still many mentions of abuse available, such as reported cases (Chiril et al, 2020), including implicit abuse ( 51)-( 52). For example, we randomly sampled 50 tweets from Twitter containing the abusive clause homosexuality is unnatural.…”

“Be nice to your wife! The restaurants are closed”: Can Gender Stereotype Detection Improve Sexism Classification?

“…There are also a few notable neural network techniques: LSTM (Jha and Mamidi, 2017) or CNN+GRU (Zhang and Luo, 2018). Chiril et al (2020b) use a BERT model trained on word embeddings, linguistic features and generalization strategies to distinguish reports/denunciations of sexism from real sexist content that are directly addressed to a target.…”

“…FlauBERT lex /BERT lex . In order to force the classifier to learn from generalized concepts rather than words which may be rare in the corpus, we adopt several replacement combinations extending Badjatiya et al (2017)'s andChiril et al (2020b)'s approach. We used a publicly avail-able French lexicon comprising 130 gender stereotyped words 11 that we grouped according to our 3 categories (physical characteristics, behavioural characteristics, activities) and replaced these words/expressions when present in tweets by their category.…”