PROJECT TITLE :

A Comprehensive Study on Social Network Mental Disorders Detection via Online Social Media Mining - 2018

ABSTRACT:

The explosive growth in popularity of social NetWorking ends up in the problematic usage. An increasing number of social network mental disorders (SNMDs), like Cyber-Relationship Addiction, Information Overload, and Internet Compulsion, have been recently noted. Symptoms of these mental disorders are usually observed passively today, ensuing in delayed clinical intervention. During this Project, we tend to argue that mining on-line social behavior provides an chance to actively establish SNMDs at an early stage. It is challenging to detect SNMDs as a result of the mental standing cannot be directly observed from on-line social activity logs. Our approach, new and innovative to the observe of SNMD detection, does not rely on self-revealing of these mental factors via questionnaires in Psychology. Instead, we have a tendency to propose a Machine Learning framework, particularly, Social Network Mental Disorder Detection (SNMDD), that exploits features extracted from social network information to accurately determine potential cases of SNMDs. We have a tendency to also exploit multi-source learning in SNMDD and propose a brand new SNMD-primarily based Tensor Model (STM) to enhance the accuracy. To increase the scalability of STM, we any improve the efficiency with performance guarantee. Our framework is evaluated via a user study with three,126 online social network users. We tend to conduct a feature analysis, and additionally apply SNMDD on massive-scale datasets and analyze the characteristics of the three SNMD sorts. The results manifest that SNMDD is promising for identifying online social network users with potential SNMDs.