The objective of this project is to develop a Semi-Structured Distributional Regression (SSMR) model capable of detecting and classifying a user's emotion into Paul Ekman’s Six Universal Emotions: Anger, Disgust, Enjoyment, Fear, Sadness, and Surprise when a user comments somenting on the app. This model will be integrated into the EmotionTrack Tutor app, an educational platform designed for Android devices that utilizes virtual reality (VR) environments. The app aims to engage users emotionally during their learning process through interactive simulations, while reducing the effects of the uncanny valley —a phenomenon where human-like avatars evoke discomfort due to subtle imperfections in realism.