CHARACTERIZING THE PROPAGATION OF SITUATIONAL

INFORMATION IN SOCIAL MEDIA DURING COVID-19

EPIDEMIC: A CASE STUDY ON WEIBO

Department of Computer Science and Engineering

Under the Supervision of
Mr. T.P.SHEKHAR
Associate Professor
PRESENTED BY
SREELA MOTURI (H.T.N0: 18N01A0598)
R.VAISHNAVI REDDY (H.T.N0: 18N01A0593)
R.PALANI BHAVESH (H.T.N0: 18N01A0594)
R.ROSELIN (H.T.N0: 18N01A0592)
A.SRIKANTH REDDY (H.T.N0: 17N01A0506)
 CONTENTS

ABSTRACT
INTRODUCTION
SCOPE OF THE PROJECT
EXISTING SYSTEM
PROPOSED SYSTEM
SYSTEM ANALYSIS
SYSTEM REQUIREMENTS
SYSTEM DESIGN
MODULES
SYSTEM TESTING
RESULTS
CONCLUSION
FUTURE IMPLEMENTAION
 ABSTRACT

During the ongoing outbreak of coronavirus disease (COVID-19), people

use social media to acquire and exchange various types of information at a
historic and unprecedented scale.
Only the situational information are valuable for the public and authorities
to response to the epidemic. Therefore, it is important to identify such
situational information and to understand how it is being propagated on
social media, so that appropriate information publishing strategies can be
informed for the COVID-19 epidemic.
The results provide data-driven insights into the information need and
public attention.
 INTRODUCTION

• BURST out in Wuhan, China, the ongoing outbreak of

Coronavirus disease (COVID-19) has caused regional and global
public health crisis During a crisis like the COVID-19 epidemic, the
public tends to social media platforms to acquire needed information
and exchange their opinions.
• There are many different types of information on social media
platforms, and the situational information, the information that helps
the concerned authorities or individuals to understand the situation
during emergencies (including the actionable information such as help
seeking, the number of affected people), is useful for the public and
authorities to guide their responses.
•Identifying these types of information and predicting its propagation
scale would benefit the concerned authorities to sense the mood of the
public, the information gaps between the authority and the public, and
the information need of the public. It would then help the authorities
come up with proper emergency response strategies.
 SCOPE OF THE PROJECT

 The selected features for different types of situational

information could also help the authorities learn how to
organize their COVID-19-related posts to enlarge or
decrease the reposted amount of their posts.
 In addition, the definitions of the situational information
will be useful for researchers or practitioners who aim to
build effective social-media-based emergence response
programs and crisis information systems.
 EXISTING SYSTEM

 Rudra et al. defined situational information as those

notifications of the casualties or injured/stranded people
or helping relief operations and categorized
sympathizing with the victims, praising or criticizing the
relief operation, post analysis of the reasons the crisis
happens, and donation-related information into non
situational information.
 While in the study by Vieweg (2012), the non situational
information defined by Rudra et al. was categorized into
situational information.
 Specifically,she categorized situational information into social
environment information, built environment information, and
physical environment information.
 The social environment information contains advice, caution,
evacuation, fatality, injury, medical attention, people missing,
and offering help.
 Built environment information contains damages caused by the
crisis and the status of infrastructures. Physical environment
information includes environmental impact, general area
information (status of the hazard), and general hazard
information (e.g., weather report).
 PROPOSED SYSTEM
 The system is proposed to find the key features that can
accurately predict the propagation scale (reposted
amount) of each type of situational information, we
extracted five groups of features as summarized in the
literature. The extracted features (with the name in italic
format) are as follows.
 Emotional factors: affect, negative emotion (negemo),
positive emotions (posemo), anxiety (anx), anger, and
sadness words (sad) in the posts and Perception-related
factors: percept, see, hear, and feel.
 Affiliation-relatedfactors: affiliation, achieves, power, reward,
and risk. 4) User-related features: followers’ amount
(Followers (log)), followees’ amount (Followees (log)), near
the event or not (NearCity), live in developed city or not
(BigCity), and verified users or not.
 Content-related factors: whether hashtag/URL contained
(URL, Hash), the length of the post (length), and the
publishing timing of the post (hours).
 SYSTEM ANALYSIS
The first and foremost strategy for development of a
project starts from the thought of designing a mail enabled
platform for a small firm in which it is easy and
convenient of sending and receiving messages, there is a
search engine ,address book and also including some
entertaining games. When it is approved by the
organization and our project guide the first activity, ie.
preliminary investigation begins. The activity has three
parts:
 Request Clarification
 Feasibility Study
 Request Approval
 SYSTEM REQUIREMENTS
H/W System Configuration:-
➢Processor - Intel Core 2 du0
➢RAM - 4 GB (min)
➢Hard Disk - 500 GB
➢Key Board - Standard Windows Keyboard
➢Mouse - Two or Three Button Mouse
➢Monitor - LED
Software Requirements
•Operating System - Windows XP
•Coding Language - Java/J2EE(JSP,Servlet)
•Front End - J2EE
•Back End - MySQL
 SYSTEM DESIGN
INPUT DESIGN
 Input Design plays a vital role in the life cycle of software
development, it requires very careful attention of developers.
The input design is to feed data to the application as accurate
as possible. So inputs are supposed to be designed effectively
so that the errors occurring while feeding are minimized.
According to Software Engineering Concepts, the input forms
or screens are designed to provide to have a validation control
over the input limit, range and other related validations.
  This system has input screens in almost all the modules. Error
messages are developed to alert the user whenever he commits
some mistakes and guides him in the right way so that invalid
entries are not made. Let us see deeply about this under
module design.
OUTPUT DESIGN

 The Output from the computer is required to mainly create an efficient

method of communication within the company primarily among the
project leader and his team members, in other words, the administrator and
the clients.
 The output of VPN is the system which allows the project leader to
manage his clients in terms of creating new clients and assigning new
projects to them, maintaining a record of the project validity and providing
folder level access to each client on the user side depending on the projects
allotted to him.
 After completion of a project, a new project may be assigned to the client.
User authentication procedures are maintained at the initial stages itself. A
new user may be created by the administrator himself or a user can himself
register as a new user but the task of assigning projects and validating a
new user rests with the administrator only.
 MODULES

Admin
 In this module, the Tweet Server has to login by using
valid user name and password. After login successful he
can do some operations such as View All Users And
Authorize, View All Friend Request and Response, Add
Filter, View All Tweets with Comments, View All
Tweets Based on Location, View Characterizing Of All
Tweets Propagation, View Propagation Analysis in
Chart, View Tweet Scores in Chart.
View and Authorize Users
 In this module, the admin can view the list of users who all registered. In
this, the admin can view the user’s details such as, user name, email,
address and admin authorizes the users.

User
 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 My Profile, Search Friend Track and Find
Friend Request, View All My Friends, Create Your Tweet, View All My
Tweets, View All My Friends Tweets and Retweet.
 SYSTEM TESTING
 The purpose of testing is to discover errors. Testing is
the process of trying to discover every conceivable fault
or weakness in a work product. It provides a way to
check the functionality of components, sub assemblies,
assemblies and/or a finished product It is the process of
exercising software with the intent of ensuring that the
 Software system meets its requirements and user
expectations and does not fail in an unacceptable
manner. There are various types of test. Each test type
addresses a specific testing requirement.
TYPES OF TESTS
 Unit Testing.
 Integration Testing.
 User Acceptance Testing.
 Output Testing.
 Validation Testing.
RESULTS
 CONCLUSION
 The findings of this article indicate the necessity of
using different information publishing strategies for
different types of situational information.
 The selected features for different types of situational
information could also help the authorities learn how
to organize their COVID-19-related posts to enlarge or
decrease the reposted amount of their posts.
 In addition, the definitions of the situational
information will be useful for researchers or
practitioners who aim to build effective social-media-
based emergence response programs and crisis
information systems.
 FUTURE IMPLEMENTAION
 This article has limitations. First, we only obtained a subset
of social media data for the constrains of Sina API. In future,
we will collaborate with the data providers to obtain a larger
amount of data. Second, in training the classifiers to identify
the content types of situational information, we only trained
three traditional NLP-based classifiers due to limited data.
 In future, we will use more data and train deep learning
methods to identify the content types with higher accuracy.
Third, the manual labeling of the crisis data is time-
consuming and might influence the efficiency of
characterizing crisis information sharing. In future, we plan
to apply automatic labeling methods to avoid this limitation.
THANK YOU