• K.MALARVIZHI

Psychological stress is putting people's health at risk. Finding stress in time for proactive care is non-trivial. With the popularity of social media, people are accustomed to sharing their daily activities and interacting with friends on social media platforms, making it possible to leverage online social network data to detect stress. In this paper, we find that user stress state is closely related to his or her friends in social media, and we use large-scale datasets from real-world social platforms to systematically study the correlation of users' stress states and social Let's use Conversation. We first define a set of text, visual and social features related to stress from different aspects, and then propose a novel hybrid model - to leverage tweet content and social interaction information for stress detection. A factor graph model combined with a convolution neural network. Experimental results show that the proposed model can improve the recognition performance in F1-score by 6-9%. By further analyzing the social connection data, we also find a number of intriguing phenomena, i.e. the number of social structures with sparse connections (i.e. those with no delta connections) of stressed users is approximately 14% higher than that of non-stressed users, this shows that the social structure of friends of stressed users is less connected and less complex than that of non-stressed users.

Human Stress,social interactions

"HUMAN STRESS DETECTION BASED ON SOCIAL INTERACTIONS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 3, page no.h554-h559, March-2023, Available :http://www.jetir.org/papers/JETIR2303775.pdf

"HUMAN STRESS DETECTION BASED ON SOCIAL INTERACTIONS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 3, page no. pph554-h559, March-2023, Available at : http://www.jetir.org/papers/JETIR2303775.pdf