Volume 13, Number 2

AIPSYCH: A Mobile Application-based Artificial Psychiatrist for Predicting Mental Illness and Recovery Suggestions among Students


Faruk Hossen1, Sajedul Talukder2 and Refatul Fahad3, 1Bangabandhu Sheikh Mujibur Rahman Science and Technology University, Bangladesh, 2Southern Illinois University, USA, 3BSMRSTU, Bangladesh


COVID-19’s outbreak affected and compelled people from all walks of life to self-quarantine in their houses in order to prevent the virus from spreading. As a result of adhering to the exceedingly strict guideline, many people developed mental illnesses. Because the educational institution was closed at the time, students remained at home and practiced self-quarantine. As a result, it is necessary to identify the students who developed mental illnesses at that time. To develop AiPsych, a mobile application-based artificial psychiatrist, we train supervised and deep learning algorithms to predict the mental illness of students during the COVID-19 situation. Our experiment reveals that supervised learning outperforms deep learning, with a 97% accuracy of the Support Vector Machine (SVM) for mental illness prediction. Random Forest (RF) achieves the best accuracy of 91% for the recovery suggestion prediction. Our android application can be used by parents, educational institutes, or the government to get the predicted result of a student’s mental illness status and take proper measures to overcome the situation.