• Sonali Alange
• Sujay Bhavsar
• Sarang Lahkar
• Pratiksha Biradar
• Prof. Archana Jadhav

Psychological stress is threatening people’s health. It's non-trivial to discover stress timely for proactive care. With the recognition of social media, folks are wont to sharing their daily activities and interacting with friends on social media platforms, creating it possible to leverage on-line social network knowledge for stress detection. During this paper, we discover that users stress state is closely associated with that of his/her friends in social media, and that we use a large-scale dataset from real-world social platforms to consistently study the correlation of users’ stress states and social interactions. We tend to 1st outline a group of stress-related matter, visual, and social attributes from numerous aspects, then propose a completely unique hybrid model - an element graph model combined with Convolutional Neural Network to leverage tweet content and social interaction data for stress detection. Experimental results show that the projected model will improve the detection performance by 6-9% in F1-score. By any analyzing the social interaction knowledge, we tend to conjointly discover many intriguing phenomena, i.e. the amount of social structures of thin connections (i.e. with no delta connections) of stressed users is around 14 July beyond that of non-stressed users, indicating that the social system of stressed users’ friends tend to be less connected and fewer sophisticated than that of non-stressed users.

Stress detection, factor graph model, micro-blog, social media, healthcare, social interaction.

"Detecting Stress Based on Social Interactions in Social Networks", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 5, page no.302-306, May-2019, Available :http://www.jetir.org/papers/JETIR1905O47.pdf

"Detecting Stress Based on Social Interactions in Social Networks", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 5, page no. pp302-306, May-2019, Available at : http://www.jetir.org/papers/JETIR1905O47.pdf