Abstract

Abstract:  In today’s world, it is undeniable that socialmedia plays an important role in impacting our culture, our economy and ouroverall view of the world. Social media is a new forum that brings people toexchange idea, connect with, relate to, and mobilize for a cause, seek advice,and offer guidance. Most research on social network mining focuses ondiscovering the knowledge behind the data for improving people’s life. WhileOSNs seemingly expand their user’s capability in increasing social contacts,they may actually decrease the face-to-face interpersonal interactions in thereal world. Due to the epidemic scale of these phenomena, new terms such asPhubbing (Phone Snubbing) and Nomo phobia (No Mobile Phone Phobia) have beencreated to describe those who cannot stop using mobile social networking apps.Some social network mental disorders (MDDSMAs), Journal of Psychiatry havereported that excessive use, depression, social withdrawal, and a range ofother negative repercussions. We propose a machine learning framework, namely,Social Network Mental Disorder Detection (MDDSMAD) that exploits featuresextracted from social network data to accurately identify potential cases ofMDDSMAs. We also exploit multi-source learning in MDDSMAD and propose a newMDDSMA-based Tensor Model (STM) to improve the accuracy. We can find out thestressed users on social media platforms.