Abstract: As a side effect of increasingly popular social media, cyberbullying has emerged as a serious problem afflicting children, adolescents and young adults. Since the textual contents on online social media area highly unstructured, informal, and Often misspelled, existing research on message level offensive language detection cannot accurately detect offensive contents. Here we design a framework called Lexical Syntactic Feature (LSF) architecture to detect offensive contents and identify potential offensive users in social media. We distinguished the contribution of profanities and obscenities in determining offensive content and introduce hand authoring syntactic rule in identifying name calling harassments. In particular we incorporated a user’s writing style, structure and specific cyberbullying contents as features to predict the users capability to send out offensive content. Results from the experiments shows that the LSF framework performed significantly better than existing methods in offensive content detection.
Keywords: Cyberbullying, Offensive ,Lexical syntactic feature, detection.
|
DOI:
10.17148/IJARCCE.2022.11680
