Detecting Hate Speech Online: A Case of Croatian

Scientific paper - Chapter in Book

• Author: Kristina Kocijan
• Author: Lucija Košković
• Author: Petra Bajac
• Editor: Hela Fehri
• Editor: Slim Mesfar
• Editor: Max Silberztein
• Author's institution: University of Zagreb; Faculty of Humanities and Social Sciences; (Department of information and Communication sciences)
• Author's institution: University of Zagreb; Faculty of Humanities and Social Sciences; (Department of Linguistics)
• Scientific / art field, discipline and subdiscipline: SOCIAL SCIENCES; Information and Communication Sciences

Abstract (english)

This project proposes a NooJ algorithm with the task to find and categorize various slurs, insults and ultimately, hate speech in Croatian. The results also provide a more detailed insight into inappropriate language in Croatian. We strongly emphasize the ethical considerations of (mis)identifying hate speech and as a result, an unethical and undeserved censorship of inappropriate, but free speech. Thus, we tried to make a clear distinction between insults and hate speech.
The test corpus... More consists of written online comments and remarks posted on five Croatian Facebook news pages during one week period. Given the differences between the standard Croatian grammar and syntax, and what is actually being used in informal on-line communication, the false negatives present the biggest difficulty since some variations (substandard usages of cases, spelling errors, colloquialisms) are impossible to predict, and therefore, extremely hard to implement into the algorithm. Less

• Keywords (english): hate speech; insults; pattern detection; information extraction; syntactic grammars; Croatian; NooJ
• Language: english
• Publication type: Scientific paper - Chapter in Book
• Publication status: Published
• Peer review: Peer review - international
• Publication version: Accepted version
• Book title: Formalizing Natural Languages with NooJ 2019 and Its Natural Language Processing Applications
• Series title: Communications in Computer and Information Science
• Numbering: vol. 1153, pp. 185-197
• ISBN: 978-3-030-38833-1 (eBook ISBN)
• ISBN: 978-3-030-38832-4 (Softcover ISBN)
• p-ISSN: 1865-0929
• DOI: https://doi.org/10.1007/978-3-030-38833-1_16
• URN:NBN: urn:nbn:hr:131:462545
• Publication: 2020-01
• Type of resource: Text
• Publisher: Springer International Publishing
• Publishing place: Switzerland
• Access conditions: Restricted access
• Created on: 2020-01-13 10:38:25