A school bullying detecting algorithm based on motion recognition and speech emotion recognition

Abstract

School bullying is a common social problem among teenagers. It affects the victims both mentally and physically, and is considered as one of the main reasons for depression, dropping out of school, and adolescent suicide. For this reason, preventing school bullying is significant to the student’s mental and physical health. In order to detect bullying events in time, this paper proposes a bullying detecting algorithm based on motion recognition and speech emotion recognition. People wear an electronic equipment, which is used to collect his/her motion and speech data, to detect bullying events in real-time. In this paper, the authors extract five features from acceleration and gyro data for physical bullying detection. The PLP features are extracted for verbal bullying detection. Then authors use the Relief-F algorithm for feature selection, and the PPCA algorithm is used to reduce the dimensionality of the feature matrix. Finally, the authors use the KNN algorithm as the classifier to train the motion recognition model and the SVM algorithm as the classifier to train the speech emotion recognition model. With cross-validation, the average accuracy of the motion recognition system is 80.61%, whereas that of the speech emotion recognition system is 75.76%. The simulation results of the algorithm indicate that the anti-bullying detecting algorithm could identify the bullying event effectively.