Unmasking Depression: Analyzing Disclosure Behavior on Social Media
DOI:
https://doi.org/10.47392/IRJAEM.2024.0329Keywords:
user health, classification, neural network, sentiment analysis, stress-related attributes;, large-scale dataset, stress state correlation, social media, stress detection, web-based social networking, early detection, Mental stressAbstract
Mental stress is a significant concern in today's fast-paced world, and detecting and addressing it in its early stages is challenging. However, the rise of web-based social networks presents a unique opportunity to tackle this issue. By analyzing the correlation between users' stress states and their social interactions, a system is developed to understand the dynamics at play. The system uses a dataset gathered from real-world social platforms to analyze sentiment analysis on social media posts. This analysis allows for deeper insights into users' emotions and mental states, enabling the system to classify whether users are currently experiencing stress or not. Once a user's stress state is identified, the system takes proactive steps to offer support. It provides recommendations for nearby hospitals on a map, ensuring users in distress can access immediate assistance if necessary. Additionally, administrators send users a precautionary list via email, offering guidance and tips to promote healthier and happier lives. In conclusion, this system represents a holistic approach to addressing stress detection and management in the digital age. By examining the relationship between users' stress states and their social interactions, the system can provide early intervention and support. This system contributes to enhancing the overall well-being of individuals in an increasingly interconnected digital world.
Downloads
Downloads
Published
Issue
Section
License
Copyright (c) 2024 International Research Journal on Advanced Engineering and Management (IRJAEM)
![Creative Commons License](http://i.creativecommons.org/l/by-nc/4.0/88x31.png)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.