Inducing a lexicon of abusive words

• Verfasst von: Wiegand, Michael [VerfasserIn]
• Verfasst von: Ruppenhofer, Josef [VerfasserIn]
• Verfasst von: Schmidt, Anna [VerfasserIn]
• Verfasst von: Greenberg, Clayton [VerfasserIn]
• Titel: Inducing a lexicon of abusive words
• Titelzusatz: a feature-based approach
• Verf.angabe: Michael Wiegand, Josef Ruppenhofer, Anna Schmidt, Clayton Greenberg
• Jahr: 2018
• Umfang: 11 S.
• Fussnoten: Gesehen am 04.09.2019
• Titel Quelle: Enthalten in: The 2018 conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - proceedings of the conference
• Ort Quelle: Stroudsburg, PA : Association for Computational Linguistics (ACL), 2018
• Jahr Quelle: 2018
• Band/Heft Quelle: (2018), Seite 1046-1056
• DOI: doi:10.18653/v1/N18-1095
• Datenträger: Online-Ressource
• Sprache: eng
• Bibliogr. Hinweis: Forschungsdaten Wiegand, Michael, 1982 - : Lexicon of abusive words (EN)
• K10plus-PPN: 1675908249

Abstract

We address the detection of abusive words. The task is to identify such words among a set of negative polar expressions. We propose novel features employing information from both corpora and lexical resources. These features are calibrated on a small manually annotated base lexicon which we use to produce a large lexicon. We show that the word-level information we learn cannot be equally derived from a large dataset of annotated microposts. We demonstrate the effectiveness of our (domain-independent) lexicon in the cross-domain detection of abusive microposts.