Depression Detection Using Machine Learning Techniques on X/Twitter Data

Abstract

Depression has become a serious problem in this current generation and the number of people affected by depression is increasing day by day. However, some of them manage to acknowledge that they are facing depression while some of them do not know it. On the other hand, the vast progress of social media is becoming their “diary” to share their state of mind. Several kinds of research had been conducted to detect depression through the user post on social media using machine learning algorithms. Through the data available on social media, the researcher can able to know whether the users are facing depression or not. Machine learning algorithm enables to classify the data into correct groups and identify the depressive and non-depressive data. The proposed research work aims to detect the depression of the user by their data, which is shared on social media. The Twitter data is then fed into two different types of classifiers, which are Naïve Bayes and a hybrid model, NBTree. The results will be compared based on the highest accuracy value to determine the best algorithm to detect depression. The primary objective of this proposed research work is to detect depression through users’ posts shared on social media platforms, with a specific focus on Twitter. Twitter was chosen due to its open-access data policies and the concise nature of user posts, making it a rich source of emotional and behavioral indicators. In this study, the collected Twitter/X data is pre-processed and then fed into two different classification models: the Naïve Bayes classifier and a hybrid model known as NBTree, which combines the Naïve Bayes algorithm with decision tree methodologies to enhance prediction capabilities.