Detecting Stress Based on Social Interactions in Social
Networks
Under the Guidance Presented By
G. SRICHAKRINI
name
17G21F0013
Designation
MCA-III YEAR
Abstract
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 paper, 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.
Existing System
In the existing system, the research on user-level emotion detection in social networks has been
studied. While tweet-level emotion detection reflects the instant emotion expressed in a single
tweet, people’s emotion or psychological stress states are usually more enduring, changing over
different time periods.
Existing work also implemented to detect users psychological stress states from social media by
learning user-level presentation via a deep convolution network on sequential tweet series in a
certain time period.
Disadvantages
• Can analyze only Single user tweets
• There is no option to tweet based on user emotions
Proposed System
• In the proposed system, the system finds 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.
• The system first defines a set of stress-related textual, visual, and social attributes from various
aspects, and then proposes a novel hybrid model - a factor graph model combined with
Convolutional Neural Network to leverage tweet content and social interaction information for
stress detection.
Advantages
• Can analyze bulk tweet data at a time
• User can tweet based on human emotions, actions and stress
Requirements
• Hardware Requirement
Processor : Dual Core 1.6 GHz
RAM : 2 GB
Hard Disk : 500 GB
• Software Requirement
Operating System : Window 7 or above
Programming Language : JAVA
Front End : HTML, CSS
Back End : JSP, Servlets
Database : MySQL 5.0
Server : Apache Tomcat
Architecture
Modules
Admin
User
Find Stress Emotions
Module Description
ADMIN
• In this module, the Admin has to login by using valid user name and password. After login
successful he can do some operations such as View all End Users and Authorize, View all friend
request and Response, Add Tweet Category like Positive, Negative, Stressed ,Select Tweet
Category and Add Tweet Filter and list all filters below, List all Tweets micro-blog with its user
details, View Positive (+)Emotion Tweets Emotions ,View negative (-)Emotion Tweet
Emotions ,View Stress Emotion Tweets, View total tweets and find number of pos, neg and
stressed tweets ,List of search history, Find No. Of +ve,or –ve or stressed Tweets emotion in
chart.
Module Description
USERS
• In this module, there are n numbers of users are present. User should register before doing any
operations. Once user registers, their details will be stored to the database. After registration
successful, he has to login by using authorized user name and password. Once Login is successful user
will do some operations like View your profile, Search Friends and Req, Friend. View all Your Friends,
Create Tweet by Tweet name, Tweet description, Tweet Image, Tweet date, View all your created
Tweets and find pos,neg, Stress emotions on your Tweets, View all your friends tweets and retweet by
feeding your sentiments or comment.
Module Description
FIND STRESS EMOTIONS
• In this module, the admin can see all Positive and Negative Emotions posted by all users for cross
domain Micro Blogs. The Review is considered either as Positive or Negative based on the Positive
and Negative list of words which are used to find the review as positive or negative. In this the Positive
and Negative words will be highlighted in blue color and in italics style.
Yo u
a n k
T h
