Open AccessDetecting Stress Based on Social Networking Interactions
Author(s) -
P.C.Senthil Mahesh,
Ch.Rupa Kalpana,
M.Rudra Kumar
Publication year - 2019
Publication title -
international journal of innovative technology and exploring engineering
Language(s) - English
Resource type - Journals
ISSN - 2278-3075
DOI - 10.35940/ijitee.k1734.0981119
Subject(s) - computer science , reputation , social media , stress (linguistics) , schedule , social network (sociolinguistics) , convolutional neural network , variety (cybernetics) , set (abstract data type) , artificial intelligence , machine learning , world wide web , social science , linguistics , philosophy , sociology , programming language , operating system
Stress is a kind of demand to respond to any in your body's manner. It can be based on experiences that are both good and bad. Psychological stress threatens the health of individuals. People are used to exchanging their schedule and daily operations with colleagues on social media platforms with the reputation of a social media network, creating it possible to hold online social network information for stress detection. For a variety of applications data mining methods are used. Data mining plays a significant role in the detection of stress in sector. We proposed a new model in this article to detect stress. Initially, in this model, discover a correlation between stress states of user and effective public interactions. This describes a set of textual, visual and social characteristics related to stress from different elements and proposes a new hybrid model coupled with Convolutional Neural Network (CNN) to efficiently hold tweet content and data on social interaction to detect stress. The suggested model can enhance the detection efficiency by 97.8 percent, which is quicker than the current scheme, from the experimental outcomes