We are all aware that the proverb “health is wealth” equally applies to mental health. Depression, Anxiety, Stress and Loneliness are examples of mental illnesses that can lead to death. Depression is a serious concern among today’s youngsters. Our project focuses on the individual’s mental health, allowing us to identify the underlying causes of sadness or anxiety. The goal of our project is to forecast state the mental wellbeing of the individual. We have used many approaches for machine learning like a Random Forest Classifier, Bagging, Texting, Stacking, and Logical Regressions. Data was acquired through a survey that we performed by asking participants to fill out a Google form with a variety of questions. To improve accuracy of model, we have label-encoded the data which we have gathered. The data is subjected to a variety of algorithms using machine learning for getting labels. After that, a model for prediction an individual's psychological condition will be built.

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

Machine Learning Approaches for Forecasting Individual Mental Wellbeing: A Comprehensive Study on Depression, Anxiety, Stress, and Loneliness

  • Kurupati Sri Vidya,
  • Meenavalli Sindhura,
  • Kyasani Poojitha,
  • Kakumanu Sruthi Vennela,
  • Chanda Raj Kumar,
  • Pavan Kumar Pagadala

摘要

We are all aware that the proverb “health is wealth” equally applies to mental health. Depression, Anxiety, Stress and Loneliness are examples of mental illnesses that can lead to death. Depression is a serious concern among today’s youngsters. Our project focuses on the individual’s mental health, allowing us to identify the underlying causes of sadness or anxiety. The goal of our project is to forecast state the mental wellbeing of the individual. We have used many approaches for machine learning like a Random Forest Classifier, Bagging, Texting, Stacking, and Logical Regressions. Data was acquired through a survey that we performed by asking participants to fill out a Google form with a variety of questions. To improve accuracy of model, we have label-encoded the data which we have gathered. The data is subjected to a variety of algorithms using machine learning for getting labels. After that, a model for prediction an individual's psychological condition will be built.