International Research Journal of Education and Technology

Emotion-based mental health prediction using chatbots, powered by the Haar Cascade algorithm, represents an innovative approach to mental health care through real-time emotional analysis and prediction. This system leverages computer vision techniques alongside artificial intelligence (AI) to capture and analyze users’ facial expressions and emotions during interactions with the chatbot. By incorporating the Haar Cascade algorithm, which is widely used for object detection, particularly face detection, the system can identify key facial features that correlate with emotional states such as happiness, sadness, anger, and anxiety.The chatbot functions by using a camera to detect and track the user’s face in real time. The Haar Cascade algorithm processes these visual inputs to recognize patterns in facial features and expressions. This data, combined with natural language processing (NLP) for analyzing user text input, allows the chatbot to assess the emotional state of the user accurately. Based on these emotional cues, the system makes predictions about the user's mental health, identifying potential signs of stress, depression, or other psychological conditions. The chatbot then provides appropriate recommendations

or resources to support the user’s mental well-being.This paper focuses on the integration of the Haar Cascade algorithm for emotion detection in mental health prediction chatbots. It examines the methodology behind facial feature extraction, emotional classification, and the predictive model for mental health assessment.