Anxiety Prediction of Student Behaviour Based on Day to Day Life

The prevalence of anxiety level among students has significantly increased in recent years, emphasizing the need of for timely detection and intervention. This study explores the prediction of anxiety level in students using various machine learning algorithms, including K Nearest Neighbors (K-NN) and Naïve Bayes and Logistic Regression. The data set collected through targeted questionnaires encompasses factors such as Age, Gender, University, Department, Year, CGPA, Scholarship, Nervous, Worrying, Relaxing, Irritated, Afraid, Anxiety Value, Anxiety Label, Stress Label and other demographic variables alongside symptoms of anxiety. By transforming these attributes into quantifiable parameters, the models were trained and will be evaluated for their effectiveness in predicting anxiety. Among the algorithm the best one with more high accuracy and less error and best performance will be selected.