Predicting Mental Health Risk Using Machine Learning Based on Instagram Usage Patterns

Abstract

The rapid growth of social media platforms has significantly changed the way people communicate, interact, and share information in modern society. Among these platforms, Instagram has become one of the most widely used social networking applications, especially among young adults and students. Although social media offers benefits such as communication, entertainment, and self-expression, excessive usage has also been associated with mental health issues including stress, anxiety, depression, loneliness, and low self-esteem. Early identification of such mental health risks is important to provide timely support and preventive care. This research proposes a machine learning-based approach to predict mental health risk using Instagram usage behaviour. Important behavioural features such as daily Instagram usage time, posting frequency, average likes per post, follower count, and night-time activity are analysed to identify potential risk patterns among users. Several machine learning classification algorithms including Logistic Regression, Decision Tree, Support Vector Machine (SVM), and Random Forest are implemented using the Scikit-learn library. The models are evaluated using performance metrics such as accuracy, precision, recall, and F1-score. Experimental results show that the Random Forest classifier achieved the highest prediction accuracy compared to other models. The findings demonstrate that machine learning techniques combined with social media behavioural analysis can contribute to early mental health risk detection and support the development of intelligent preventive healthcare systems.