Cyberbullying Detection Based on Emotion

Due to the detrimental consequences caused by cyberbullying, a great deal of research has been undertaken propose effective techniques resolve this reoccurring problem. The presented in paper is motivated fact that negative emotions can be cyberbullying. This proposes cyberbullying detection models are trained based on contextual, and sentiment features. An Emotion Detection Model (EDM) was constructed using Twitter datasets have improved terms its annotations. Emotions were extracted from EDM lexicons based. Two Wikipedia respectively further comprehensive annotation emotion results show anger, fear guilt major associated with Subsequently, used as features addition contextual train for detection. demonstrate performance detecting 0.5 0.6 recall. proposed also outperformed state-of-the-art 0.7 f1-score. main contribution work two-fold, which includes emotion-annotated dataset detection, an empirical proof