Machine learning for stress prediction

Abstract

Emotional, psychological, and social well-being are all part of mental health. Stress, social anxiety, depression, and personality disorders are just a few of the elements that build up mental health issues that lead to mental illness. Mental illness is at an all-time high in today’s fast-paced world, and it’s on the rise. Early detec tion of mental disorders is critical for preventing mental illness and maintaining a balanced life. Machine Learning (ML) may open up new avenues for recognizing human behavior patterns, as well as detecting irregular mental health symptoms and risk factors. This study gives a systematic view of machine learning approaches to mental health problem prediction. We scan credible resources for research ar ticles and studies relating to machine learning methodologies in predicting mental illness. Machine learning is used in various ways to anticipate mental illness and respond accordingly. Machine learning methods and approaches will aid in the pre diction of mental illnesses. To summarize, this thesis attempts to have an impact on the healthcare industry by using machine learning approaches to detect mentally ill patients using large data. We will collect data from the internet through Google form, pre-process the data and use machine learning algorithms to make a model that will predict stress from our selected features. This research work proposes to experiment with various machine learning algorithms (for example scatter matrix plots, decision trees, and logistic regression), compare their performance, and final ize a model to identify the state of mental health status from an organized dataset.