Open AccessSyntax and prejudice: ethically-charged biases of a syntax-based hate speech recognizer unveiled
Author(s) -
Michele Mastromattei,
Leonardo Ranaldi,
Francesca Fallucchi,
Fabio Massimo Zanzotto
Publication year - 2022
Publication title -
peerj. computer science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.806
H-Index - 24
ISSN - 2376-5992
DOI - 10.7717/peerj-cs.859
Subject(s) - syntax , prejudice (legal term) , computer science , parsing , syntax error , linguistics , natural language processing , psychology , social psychology , abstract syntax , philosophy
Hate speech recognizers (HSRs) can be the panacea for containing hate in social media or can result in the biggest form of prejudice-based censorship hindering people to express their true selves. In this paper, we hypothesized how massive use of syntax can reduce the prejudice effect in HSRs. To explore this hypothesis, we propose Unintended-bias Visualizer based on Kermit modeling ( KERM-HATE ): a syntax-based HSR, which is endowed with syntax heat parse trees used as a post-hoc explanation of classifications. KERM-HATE significantly outperforms BERT-based, RoBERTa-based and XLNet-based HSR on standard datasets. Surprisingly this result is not sufficient. In fact, the post-hoc analysis on novel datasets on recent divisive topics shows that even KERM-HATE carries the prejudice distilled from the initial corpus. Therefore, although tests on standard datasets may show higher performance, syntax alone cannot drive the “attention” of HSRs to ethically-unbiased features.