Detection of Social Network Mental Disorder via Machine Learning

Ms. Sangeeta R. Kamite, Prof. V.B. Kamble


The brutal enhancement of social networking conducts the intricate usage. It increases the social network mental disorders such as phantom ringing syndrome, Nomophobia, cybersickness, Internet addiction disorder, Online gaming addiction, Cyberchondria etc. The symptoms of these mental disorders generally viewed passively today. In this paper we use machine learning method for the process of obtaining big data from user generated content on social media sites in order to extract patterns, and act upon the information and argue that mining social behavior provides an opportunity to actively identify social network mental disorder at an early stage. It is difficult to discover the social network mental disorder because it is not possible to directly observe from social activity logs. We purpose a machine learning framework for social media mining which requires human data analyst and automated software program to sift through massive amount of raw social media data in order to discover patterns and trends relating to social media usage, online behaviors, sharing of content, connection between individuals, online buying behavior etc. We direct an element investigation, and furthermore apply interpersonal organization mental turmoil on huge scale datasets and examine the qualities of the informal community mental confusion types.

Full Text:



  • There are currently no refbacks.