This paper provides an automatic system for detecting mental stress of users in social networks and data mining algorithms have been applied here. Data mining is usually defined as the extraction of non-trivial implicit that are unknown previously and the most valuable information present in the data. It is commonly known as the knowledge discovery from the databases(KDD). In data mining, on examining data for recurrent then/if forms association rules could be formed through consuming Confidence & Support measures to detect most significant associations in the data. Support is exactly how regularly the items perform in the folder, while self-assurance is the sum of times then/if declarations are precise. In this automated system, firstly a set of stress-related textual, visual, and social attributes from various aspects are evaluated. We detected the correlation between the states of user’s stress and their social interaction behavior in social networks by utilizing real world social media data. In this work, evaluated polarity of sentiments from social media data to identify phenomena of stress among the users. The proposed methodology provides the best performance results, when it compared to the existing methods.
CITATION STYLE
Sharma, S., Sharma, I., & Sharma, A. K. (2020). Automated System for Detecting Mental Stress of Users in Social Networks Using Data Mining Techniques. In Lecture Notes on Data Engineering and Communications Technologies (Vol. 49, pp. 769–777). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-43192-1_85
Mendeley helps you to discover research relevant for your work.