STRESS DETECTION BASED ON SOCIAL INTERACTION IN SOCIAL NETWORKS

Sarath Santhosh Kasukurthi , Sai Teja , Sandeep Lanka , Nitin Karumuri

Mental Pressure, Convolution Neural System, Factor charts, Social connections.

Mental pressure is undermining individuals' wellbeing. It is non-inconsequential to distinguish pressure opportune for proactive care. With the prevalence of web-based social networking, individuals are accustomed to imparting their day by day exercises and associating to companions via web-based networking media stages, making it plausible to use online informal community information for push recognition. In this paper, we find that clients push state is firmly identified with that of his/her companions in web-based social networking, and we utilize a substantial scale dataset from certifiable social stages to deliberately contemplate the relationship of clients' pressure states and social connections. We initially characterize an arrangement of stress-related literary, visual, and social traits from different viewpoints, and afterward propose a novel cross breed show - a factor chart demonstrate joined with Convolution Neural System to use tweet substance and social cooperation data for push identification. Exploratory outcomes demonstrate that the proposed model can enhance the identification execution by 6-9 percent in F1-score. By additionally dissecting the social communication information, we likewise find a few charming marvels, i.e., the quantity of social structures of scanty associations (i.e., with no delta associations) of focused on clients is around 14 percent higher than that of non-focused on clients, showing that the social structure of focused on clients' companions have a tendency to be less associated and less confounded than that of non-focused on clients.

Volume 6 Issue 1, March-2018

Pages : 759-764