Prediction of Mental Stress, Depression and Suicidal Symptoms in Students using Machine Learning Techniques

---

Abstract

Mental stress is also a major issue nowadays, especially among students & youngsters. The age, that was considered once most carefree, is now under a large amount of stress. Stress increase nowadays leads to many problems like depression, suicide, heart attack, and stroke. Trying to calculate the mental stress of students, in various situations, viz, one week before the exam and during the usage of the internet. Its objective is to analyze stress in school students at different points in his/her life. The effects, that exam pressure or selection in good institutions, break-ups, socio economic issues, loneliness and many more, are significant. In Stress, anxiety, depression has on the student which often goes unnoticed. We will perform an analysis on how these factors affect the mind of a student and will also correlate this stress with the time spent on the internet. Academic & relationship stress and depression are also the burning causes of suicide and suicidal attempts for students. There are lots of cases reported by media about the students’ suicide in daily newspapers that cause too much pressure and stress on parents, society, institutions of types: Private, Charity and maybe government. Keeping in this view it is today’s need to investigate the causal factors that are affecting students’ mentality psychologically, which can help us to understand that what kind of thoughts are running inside the mind of students. Because of this, mission is to study these factors among students, with certain numbers of boys & girl students, of certain age range. We divided the dataset into training and testing sets and used 10-fold cross-validation to evaluate the performance of each algorithm. Authors measured the accuracy, precision, recall, F1 score, and ROC-AUC score to determine the best performing algorithm and found that the random forest algorithm performed the best with an accuracy of 90%, precision of 92%, recall of 89%, F1 score of 90%, and ROC-AUC score of 0.96. The decision tree algorithm had the lowest performance with an accuracy of 78%, precision of 79%, recall of 78%, F1 score of 78%, and ROC-AUC score of 0.81.

---

Keywords

Artificial Intelligence, Machine Learning, ROC- AUC, Mental Stress, Suicide, Heart Attack, Depression