Combining textual features to detect cyberbullying in social media posts
Abstract
Cyberbullying has become prevalent in social media communication. To create a safe space for cyber communication, an effective cyberbullying detection method is needed. This study focuses on using combination of textual features to detect cyberbullying across social media platforms. Lexicon enhanced rule-based method was applied to detect cyberbullying on Facebook comments. The resulting algorithm was evaluated using performance measures of accuracy, precision, recall, and F1 Score, and showed promising performance with average recall of 95.981%.
Keywords
cyberbullying; cyber aggression; textual aggression; sentiment analysis; emoticon sentiment; emoji sentiment; aggression detectionFields of Research
170203 Knowledge Representation and Machine Learning; 200101 Communication Studies; 200102 Communication Technology and Digital Media Studies; 209999 Language, Communication and Culture not elsewhere classified; 200408 Linguistic Structures (incl. Grammar, Phonology, Lexicon, Semantics); 08 Information and Computing Sciences; 10 TechnologyDate
2020Type
Conference Contribution - Published (Conference Paper)Collections
© 2020 The Authors. Published by Elsevier B.V.