Cognitive Flux Detection and Adaptive Emotional Modulation

The rapid rise of social networking sites has led to unusual usage patterns that contribute to various social network-related mental disorders, including Cyberrelationship Addiction, Information Overload, and Net Compulsion. These disorders often go unnoticed until they reach advanced stages, resulting in delayed intervention. To address this issue, this project introduces a new depression detection model that identifies signs of depression based on users' online social behavior, particularly through the analysis of tweets. Unlike traditional methods that depend on surveys completed by respondents, this model employs machine learning techniques to analyze social media data, facilitating the early detection of depressive tendencies.Additionally, the model incorporates a classification technique that utilizes Term Frequency-Inverse Document Frequency (TF-IDF) for feature extraction. The tweets undergo preprocessing, which includes the removal of Unicode characters, and both KNN and SVM models are utilized to achieve accurate classification. Developed in Python 3.7, the system enhances the detection of depression, serving as an early intervention tool to initiate personalized mental health care. This approach introduces a new method that could serve as a regular and non-intrusive way to identify depressed states and related social network mental disorders by analyzing social media activity.