Explainable AI Approach Towards Toxic Comment Classification
Aditya Mahajan, Divyank Shah, Gibraan Jafar
Topics & Concepts
InterpretabilityComputer scienceOffensiveArtificial intelligenceTrustworthinessReliability (semiconductor)Machine learningThe InternetSocial mediaSelection (genetic algorithm)Natural language processingInternet privacyOperations researchEngineeringWorld Wide WebPower (physics)Quantum mechanicsPhysicsAdversarial Robustness in Machine LearningHate Speech and Cyberbullying DetectionSoftware Engineering Research