Mental health is an important issue in the tech industry, as individuals working in this field are often subject to high levels of stress and pressure. The Mental Health in Tech Survey, conducted by the Open Sourcing Mental Illness (OSMI) organization, aims to understand the attitudes and experiences of individuals working in the tech industry regarding mental health.
The primary objective of this project is to predict the likelihood of a person being affected by mental health issues and to investigate the factors that contribute to mental health challenges in the IT sector. The project will employ data mining techniques such as Logistic Regression and Ensemble methods to analyze the data with a focus on identifying patterns and trends, the predictive analysis will aim to provide meaningful insights and additionally answer the following questions concerning mental health in the technology industry.
• What factors are the most significant predictors of mental health issues in those working in the IT sector?
• How are the probabilities of having a mental health illness vary for other demographic categories (e.g., gender, age, and race)?
• What is the relationship between workplace attitudes regarding mental health and the chance of developing a mental health condition?
The data for this project will be sourced from the Mental Health in Tech Survey conducted by the Open Sourcing Mental Illness (OSMI) organization. The dataset is available for download on Kaggle at the following link: https://www.kaggle.com/datasets/osmi/mental-health-in-tech-survey.
The dataset consists of 1.5k+ data and 27 columns. The variables in the dataset include demographic information (e.g., age, gender, race), information on mental health conditions, and responses to questions on attitudes and experiences related to mental health in the workplace. A sample of the variable names in the dataset include: “Age”, “Gender”, “Country”, “state”, “self-employed”, “family history”, “treatment”, “anonymity”, “benefits”.