DETECTION OF CYBERBULLYING IN SOCIAL NETWORKS: COMPARING MACHINE LEARNING AND TRANSFER LEARNING METHODS
Keywords:
Cyberbullying detection, DistilBert, machine learning, pre-trained language models (PLMs), transfer learning, toxicity features, AMiCa dataset, LIWC, empath.Abstract
Information and Communication Technologies have revolutionized communication, but cyberbullying
poses severe challenges, demanding automated solutions for effective detection on social media platforms. The
PROJECT emphasizes feature extraction and selection techniques to enhance the model's understanding of
cyberbullying instances, incorporating both traditional Machine Learning and Transfer Learning approaches. The
project leverages diverse models, including LinearSVC, Logistic Regression, DistilBert, DistilRoBerta, and Electra,
encompassing Machine Learning, Transfer Learning, and Deep Learning methodologies for robust cyberbullying
detection.
Downloads
Published
2024-08-28
Issue
Section
Articles
How to Cite
DETECTION OF CYBERBULLYING IN SOCIAL NETWORKS: COMPARING MACHINE LEARNING AND TRANSFER LEARNING METHODS. (2024). International Journal of Engineering and Science Research, 14(3), 239-257. https://www.ijesr.org/index.php/ijesr/article/view/925
