Using EEG to Explore Teachers’ Emotional Responses to Problem Behaviours in Learners with Autism Spectrum Disorder

This study aimed to investigate the emotional changes in the brain activity of 34 special education teachers using electroencephalography (EEG) signals in response to common problem behaviours observed in students with Autism Spectrum Disorder (ASD), such as self-harm, aggression, tantrums, and stereotyped behaviours. Vignettes with Turkish narration and stimulus videos were used for each behaviour type to trigger emotions. EEG data were collected from the frontal, temporal, parietal, and occipital regions, and subjected to pre-processing steps such as band-pass filtering (0.5–40 Hz) and Independent Component Analysis (ICA), and various spectral and statistical features were extracted. To improve classification performance, feature selection was performed using the Least Absolute Shrinkage and Selection Operator (LASSO) method, and Support Vector Machine (SVM), Artificial Neural Network (ANN), Linear Discriminant Analysis (LDA), and Random Forest (RF) algorithms were used for classification. The machine learning techniques used achieved success rates of up to 97.66% F1 score in classifying teachers’ brain activity in response to different behavioural patterns. Teachers showed strong negative emotional responses to self-harm, aggression, and tantrums, while showing less response to the stereotypical behaviours. It is recommended that the study be replicated with different signals and teachers.