[go: up one dir, main page]
Scribd
Upload
107 views4 pages

Detecting Stress Based On Social Interactions in Social Networks

Uploaded by

Harikrishnan Shunmugam

This document discusses detecting psychological stress based on social interactions in social networks. It proposes using a hybrid model combining a factor graph model and convolutional neural network to leverage tweet content and social interaction information to detect stress. The model improves stress detection performance by 6-9% over existing methods. Analysis found stressed users have 14% more sparse social connections than non-stressed users, indicating their social structures are less connected.

Copyright:

© All Rights Reserved
Download as DOCX, PDF, TXT or read online from Scribd
Download as docx, pdf, or txt

Detecting Stress Based On Social Interactions in Social Networks

Uploaded by

Harikrishnan Shunmugam
107 views4 pages
This document discusses detecting psychological stress based on social interactions in social networks. It proposes using a hybrid model combining a factor graph model and convolutional neural network to leverage tweet content and social interaction information to detect stress. The model improves stress detection performance by 6-9% over existing methods. Analysis found stressed users have 14% more sparse social connections than non-stressed users, indicating their social structures are less connected.

Original Title

Abstract2.docx

Copyright

© © All Rights Reserved

Available Formats

DOCX, PDF, TXT or read online from Scribd

Did you find this document useful?

Is this content inappropriate?

This document discusses detecting psychological stress based on social interactions in social networks. It proposes using a hybrid model combining a factor graph model and convolutional neural network to leverage tweet content and social interaction information to detect stress. The model improves stress detection performance by 6-9% over existing methods. Analysis found stressed users have 14% more sparse social connections than non-stressed users, indicating their social structures are less connected.

Copyright:

© All Rights Reserved
Download as DOCX, PDF, TXT or read online from Scribd
Download as docx, pdf, or txt
107 views4 pages

Detecting Stress Based On Social Interactions in Social Networks

Uploaded by

Harikrishnan Shunmugam
This document discusses detecting psychological stress based on social interactions in social networks. It proposes using a hybrid model combining a factor graph model and convolutional neural network to leverage tweet content and social interaction information to detect stress. The model improves stress detection performance by 6-9% over existing methods. Analysis found stressed users have 14% more sparse social connections than non-stressed users, indicating their social structures are less connected.

Copyright:

© All Rights Reserved
Download as DOCX, PDF, TXT or read online from Scribd
Download as docx, pdf, or txt
You are on page 1/ 4

DETECTING STRESS BASED ON SOCIAL INTERACTIONS IN SOCIAL NETWORKS

ABSTRACT:

Psychological stress is threatening people's health. It is non-trivial to detect stress timely


for proactive care. With the popularity of social media, people are used to sharing their daily
activities and interacting with friends on social media platforms, making it feasible to leverage
online social network data for stress detection. In this project, we find that users stress state is
closely related to that of his/her friends in social media, and we employ a large-scale dataset
from real-world social platforms to systematically study the correlation of users' stress states and
social interactions. We first define a set of stress-related textual, visual, and social attributes from
various aspects, and then propose a novel hybrid model - a factor graph model combined with
Convolutional Neural Network to leverage tweet content and social interaction information for
stress detection. Experimental results show that the proposed model can improve the detection
performance by 6-9 percent in F1-score. By further analyzing the social interaction data, we also
discover several intriguing phenomena, i.e., the number of social structures of sparse connections
(i.e., with no delta connections) of stressed users is around 14 percent higher than that of non-
stressed users, indicating that the social structure of stressed users' friends tend to be less
connected and less complicated than that of non-stressed users.
EXISTING SYSTEM:

Psychological wellness conditions influence a noteworthy level of the world’s adult


population every year. Including depression, eating disorders like anorexia and bulimia,
bipolar disorder and post-traumatic stress disorder (PTSD). Endless anxiety expands the
danger of creating medical issues, for example, a sleeping disorder, corpulence, heart
ailments so on. Hence, there is noteworthy significance to identify stress some time
before it transforms into serious issues. Conventional mental stress recognition is
predominantly based on interviews, self-report surveys or wearable sensors. With the
increase the use of social networks individual’s shares their day to day occasions,
inclinations, and interact with companions through the social media. As these online networking
information auspicious mirror’s client’s genuine states and feelings in an auspicious way.

DISADVANTAGES:

 More time consuming.


 It is a challenge to construct a dataset with reliable ground truth labels from large-scale
noisy social media data.
 A manual labeling method is not feasible due to the uncontrollable cost and quality.
PROPOSED SYSTEM:

In this project, we presented a framework for detecting users’ psychological stress states
from users’ weekly social media data, leveraging tweets’ content as well as users’ social
interactions. Employing real-world social media data as the basis, we studied the correlation
between user’ psychological stress states and their social interaction behaviors. To fully leverage
both content and social interaction information of users’ tweets, we proposed a hybrid model
which combines the factor graph model (FGM) with a convolutional neural network (CNN).

In this work, we also discovered several intriguing phenomena of stress. We found that the
number of social structures of sparse connection (i.e., with no delta connections) of stressed
users is around 14 percent higher than that of non-stressed users, indicating that the social
structure of stressed users’ friends tend to be less connected and less complicated than that of
non-stressed users. These phenomena could be useful references for future related studies.

ADVANTAGES:

 It improves the detection performance.


 Less time consuming.
 The social structures of stressed users are less connected and less complicated than those
of non-stressed users.

You might also like