Facial Expression-Based Emotion Detection For Adaptive Teaching In Educational Environment

Abstract

Understanding how students interact in educational settings is essential for enhancing academic outcomes and student health. A new student activity categorization method uses facial expression detection technologies according to this research. The proposed system uses facial expression detection technology to monitor student emotions and state before classifying their activities. The research examines deep learning models for face emotion recognition across academic and non-academic activities from a single dataset. The system establishes the ability to detect four emotional states including happiness and sorrow as well as rage and surprise. The system utilizes extracted emotional traits to analyze student actions which demonstrate engagement alongside attentiveness along with puzzlement and indifference and other potential states. This student-tracking methodology can forecast real-time student interactions which enables teachers to make necessary adjustments that enhance academic results and learning quality. The framework presents opportunities to develop customized educational assistance alongside intelligent educational systems. We will develop a system for extracting face characteristics through this investigation. using the Grassmann method. The system detects student emotions during specific circumstances. The system uses emotion categorisation to predict active states before generating administration reports. Through this technique researchers can develop adaptive learning systems which dynamically alter instruction based on student emotional responses. Through student emotional responses a virtual tutor could alter exercise difficulty thereby creating a flexible and interactive learning scenario.