About this document

AI Cyberbullying Detection with Explainability by ridiculous.antidote is a document available to read on EtoBox.

This study presents an AI model for detecting cyberbullying severity by integrating user-specific psychological, demographic, and behavioral factors with social media comments. The proposed LSTM model achieves high accuracy (98%) and utilizes explainable AI techniques (SHAP and LIME) to interpret its decision-making process, revealing that certain demographic groups are more vulnerable to cyberbullying. The findings aim to enhance automated detection and intervention strategies to create safer digital envir

Author

ridiculous.antidote

Language

EN