Student Behavior Analysis in Class Room

Abstract

Early the paper titled “Student Behaviour Analysis in Class room” is a smart software system designed to analyse and evaluate the attention level, listening behaviour, and emotional response of students during classroom sessions. In a modern educational environment, understanding how students behave, listen, and react to lessons is an important factor for improving teaching quality and learning outcomes. Teachers often find it difficult to manually observe every student’s attention and mood during lectures, especially in large class rooms. To solve this issue, this project introduces an automated solution that continuously monitors students through a camera and analyses their behaviour using Artificial Intelligence (AI) and Machine Learning (ML) techniques. The systemcaptures real-time video ofstudents and processes their facialexpressions, eye movements, and gestures to determine their level of engagement and emotional state. The main objective of this project is to identify whether a student is attentive, distracted, or disengaged and also to recognize emotions such as happiness, sadness, confusion, or boredom during the class. The software analyses the student’s face and assigns suitable emojis that represent their mood for example, a smiling face for happy or engaged students, as adface for students showing low interest, and a confused face for those who seem lost or inattentive. These visual emojis are displayed on the teacher’s dashboard to help them instantly understand the overall emotional condition of the classroom. By collecting and analysing such behavioural data, the system generates reports that indicate how well students are listening and attending the session. The working of the system involves several modules including video input, face detection, emotion recognition, attention analysis, and visualization. The camera captures live classroom footage, and image-processing algorithms detect each student’s face. Then, the AI model analyses facial land marks such as eyes, mouth, and eye brows to determine emotions and focus levels. Using pre-trained emotion detection models, the system classifies expressions into categories like happy, sad, neutral, angry, or surprised. These results are displayed along with matching emojis to make the output simple and visually understandable. Teachers can view these results in real time to evaluate which parts of the lecture engage students and which cause distraction.