Hybrid Model for Stress Detection in Social Media by Using Dynamic Factor Graph Model and Convolutional Neural Networks

Psychological stress has become a common condition in today's world owing to the busy life style and competitive environment. This has led to increase of suicidal rates in the recent years. Lately, there has been a tremendous increase in interactions in the social networking sites. As people are spending long hours in the virtual world it is easier to detect and analyze the stress levels of the social media users. In this paper, we have proposed a hybrid approach which is a combination of Factor Graph (FG) model and Convolutional Neural Network (CNN) to analyze the textual contents in social media users’ tweets and posts to detect the level of stress of a user. The tweets of an individual user are gathered from Twitter platform which is preprocessed and passed to the cross autoencoder embedded CNN Model which outputs user level attributes. These are then input to the Factor Graph model that detects the stressed tweets. A mechanism has been proposed to inform the friends or relatives of the concerned stressed user if the detected stress level is above the given threshold

Download Full-text

Psychological Stress Detection from Social Media Data using a Novel Hybrid Model

International Journal of Computer Sciences and Engineering ◽

10.26438/ijcse/v6i8.853862 ◽

2018 ◽

Vol 6 (8) ◽

pp. 853-862

Author(s):

Shaikha Hajera ◽

Mohammed Mahmood Ali

Keyword(s):

Social Media ◽

Psychological Stress ◽

Hybrid Model ◽

Stress Detection ◽

Social Media Data ◽

Media Data

Download Full-text

Joint Spatial and Graph Convolutional Neural Networks - A Hybrid Model for Spatial-Spectral Geospatial Image Analysis

IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium ◽

10.1109/igarss39084.2020.9323658 ◽

2020 ◽

Author(s):

Farideh Foroozandeh Shahraki ◽

Saurabh Prasad

Keyword(s):

Neural Networks ◽

Image Analysis ◽

Convolutional Neural Networks ◽

Hybrid Model

Download Full-text

An Attention Factor Graph Model for Tweet Entity Linking

Proceedings of the 2018 World Wide Web Conference on World Wide Web - WWW '18 ◽

10.1145/3178876.3186012 ◽

2018 ◽

Author(s):

Chenwei Ran ◽

Wei Shen ◽

Jianyong Wang

Keyword(s):

Graph Model ◽

Factor Graph ◽

Entity Linking ◽

Factor Graph Model

Download Full-text

Human Stress Detection With Wearable Sensors Using Convolutional Neural Networks

IEEE Aerospace and Electronic Systems Magazine ◽

10.1109/maes.2021.3115198 ◽

2022 ◽

Vol 37 (1) ◽

pp. 60-70

Author(s):

Manuel Gil-Martin ◽

Ruben San-Segundo ◽

Ana Mateos ◽

Javier Ferreiros-Lopez

Keyword(s):

Neural Networks ◽

Convolutional Neural Networks ◽

Wearable Sensors ◽

Stress Detection ◽

Human Stress

Download Full-text

Factor Graph Model Based User Profile Matching Across Social Networks

IEEE Access ◽

10.1109/access.2019.2948073 ◽

2019 ◽

Vol 7 ◽

pp. 152429-152442

Author(s):

Lidong Wang ◽

Keyong Hu ◽

Yun Zhang ◽

Shihua Cao

Keyword(s):

Social Networks ◽

Graph Model ◽

User Profile ◽

Factor Graph ◽

Model Based ◽

Profile Matching ◽

Factor Graph Model

Download Full-text

Individual Doctor Recommendation in Large Networks by Constrained Optimization

International Journal of Web Services Research ◽

10.4018/ijwsr.2015100102 ◽

2015 ◽

Vol 12 (4) ◽

pp. 16-28 ◽

Cited By ~ 2

Author(s):

Jibing Gong ◽

Hong Cheng ◽

Lili Wang

Keyword(s):

Graph Model ◽

Weighted Average ◽

Factor Graph ◽

Patient Relationship ◽

Doctor Patient Relationship ◽

Data Set ◽

Medical Social Network ◽

Doctor Recommendation ◽

Factor Graph Model ◽

Individual Doctor

In this paper, the authors try to systematically investigate the problem of individual doctor recommendation and propose a novel method to enable patients to access such intelligent medical service. In their method, the authors first mine doctor-patient ties/relationships via Time-constraint Probability Factor Graph model (TPFG) from a medical social network. Next, they design a constraint-based optimization framework to efficiently improve the accuracy for doctor-patient relationship mining. Last, they propose a novel Individual Doctor Recommendation Model, namely IDR-Model, to compute doctor recommendation success rate based on weighted average method. The authors conduct experiments to verify the method on a real medical data set. Experimental results show that they obtain better accuracy of mining doctor-patient relationship from the network, and doctor recommendation results of IDR-Model are reasonable and satisfactory.

Download Full-text

Multi-Pattern Data Mining and Recognition of Primary Electric Appliances from Single Non-Intrusive Load Monitoring Data

Energies ◽

10.3390/en12060992 ◽

2019 ◽

Vol 12 (6) ◽

pp. 992 ◽

Cited By ~ 4

Author(s):

Shengli Du ◽

Mingchao Li ◽

Shuai Han ◽

Jonathan Shi ◽

Heng Li

Keyword(s):

Clustering Algorithm ◽

Belief Propagation ◽

Graph Model ◽

Electric Power Industry ◽

Factor Graph ◽

Monitoring And Control ◽

Factor Graph Model ◽

Load Monitoring ◽

Actual Energy Consumption ◽

And Control

The electric power industry is an essential part of the energy industry as it strengthens the monitoring and control management of household electricity for the construction of an economic power system. In this paper, a non-intrusive affinity propagation (AP) clustering algorithm is improved according to the factor graph model and the belief propagation theory. The energy data of non-intrusive monitoring consists of the actual energy consumption data of each electronic appliance. The experimental results show that this improved algorithm identifies the basic and combined class of home appliances. According to the possibility of conversion between different classes, the combination of classes is broken down into different basic classes. This method provides the basis for power management companies to allocate electricity scientifically and rationally.

Download Full-text