• M.P.R.Pravallika
• K.Samson Paul

Mental stress is becoming a threat to people’s health now days. With the rapid pace of life, more and more people are feeling stressed. It is not easy to detect user’s stress in an early stage to protect user. With the popularity of web-based social networking, individuals are used to share their day by day movements and interacting with friends via web-based networking media stages. It make possible to use online social network data for stress detection. In this paper, we proposes framework of detect users stress states is closely related to that of his/her friends in social media, and employ a large-scale data sheets from real-world social platforms to systematically study the correlation of users’ stress states and social interactions. We first define a set of stress-related textual, visual, and social attributes from various aspects, then convolutional neural network (CNN) is used for topic extraction. Using CNN we can perform sentiment analysis of post after formation of topic. The contribution work is detecting users are stressed or not by using support vector method (SVM). Experimental results show that the proposed model can improve the detection performance .With the help of enumeration we build a website for the users to identify their stress rate level and can check other related activities.

"STRESS DETECTION BASED ON SOCIAL INTERACTIONS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 7, page no.163-167, July-2018, Available :http://www.jetir.org/papers/JETIR1807623.pdf

"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.5, Issue 7, page no. pp163-167, July-2018, Available at : http://www.jetir.org/papers/JETIR1807623.pdf