OPINION MINING FOR SOCIAL NETWORKING PLATFORMS

1. Introduction :

Many of the times it happens that the irrelevant posts get viral very fast, the people
forward it without proof-reading the post or without having a look at its comment
section. Social media has become a routine dose of refreshment for many people and
most of the people take it very seriously, so when something is posted it’s necessary
to check its quality so that no bad post gets viral even the bad comments passed for a
particular post should not go viral.
Opinion mining is an important aspect which needs to be considered whenever we are
serious about the post that we are creating. Posts have an immense impact on people
who take it seriously.
So mining this data would make social media little meaningful and thoughtful. The
importance of mining data is very important in this era of big data. Many people uses
social media as a platform to express their feelings out as they feel that it’s a better
platform , but it might happen that a particular bad comment may make a huge impact
on that person if that person take it seriously ; So it’s necessary that we check the post
and think well before so that our comment or post doesn’t have any negative impact
on the people around us.

1.1 Purpose :

The main purpose of this web-app is to do opinion mining along with data cleaning in
an online mode. We want to promote social media which will leave only a positive
impact on its viewer. The negative posts and comments will be removed so that it
becomes more user-friendly and even suitable for the children to use it as it won’t
hamper their brains with some negative and unnecessary stuff.
We want to provide good quality social media which will make the youth of the
country more powerful in some sense ; as the youth takes social media more seriously
than their real life.

1.2 Scope :

To promote the use of social media for a powerful and positive impact on the people
and especially on the youth of the country. To eradicate the negative posts and
comments from social media so that the quality of social media is increased
immensely. The user-friendly tool will definitely prove as a boon for society as most
of the time we are within our phones. This web-app will automatically sort the data
and will even clean it without any disturbance to other users.

1.2.1 Objective :

To develop a highly impactful web-app which will make social media more
meaningful and will remove the negative comments and posts which shouldn’t go
viral.

1.2.2 Study Area

To remove the noisy data we need to get access to the user’s account so that we can
remove the data by stating that it's not within the rule book. User location will be
needed to verify the reality related to that post.

1.3 DEFINITION, ACRONYMS, AND ABBREVIATIONS

The below tables contain the definitions , acronyms and the abbreviations for the web-
app .

Table 1 : Definitions

Term Definition

Opinion Mining It is an approach to natural language

processing that identifies the emotional
tone behind a body of text.

Database A collection of data or information

typically stored on a computer system
and organized to facilitate retrieval and
modification.

Database Management System Software that enables users to define,

create, maintain, and control access to a
database.

Social Media Websites and applications that enable

users to create and share content or to
participate in social networking.

Image Pictorial representation of a scene

recorded by a remote sensing system.

Post Content shared on social media through

a user’s profile.

Comment A comment is a form of engagement in

which a user replies to your social media
post.

Social Networking Platform A social networking site is an online

platform that allows users to create a
public profile and interact with other
users.
Table 2 : Acronyms

Acronyms Meaning

NLP Natural Language Processing

AI Artificial Intelligence

1.4 References :
(1) Opinion Mining for Social Networking Platforms : “ International Conference
on Advances in Social Networks Analysis and Mining, ASONAM 2011,
Kaohsiung, Taiwan, 25-27 July 2011
(2) http://ieeexplore.ieee.org/xpl/articleDetails.jsp?
tp=&arnumber=6285052&queryText
%3DOpinion+Mining+For+Comment+Sentiment+Analysis
(3) http://ieeexplore.ieee.org/xpl/articleDetails.jsp?
tp=&arnumber=6542443&queryText
%3DOpinion+Mining+For+Comment+Sentiment+Analysis

1.5 Overview :

The SRS is organized into two main sections. The first is –“ Overall Description” and
the second is –“Specific Requirements”.
The Overall Description will describe the requirements of the Opinion mining tool
from a general high-level perspective. The Specific Requirements section will
describe in detail the requirements of the system.

2. The Overall Description

The general factors described here affect the product and its requirements. This
section does not state specific requirements. Instead, it provides a background for
those requirements, which are defined in Section 3, and makes them easier to
understand.

2.1 Product Perspective

2.1.1 Detailed Methodology

The methodology of the proposed study is elaborated in the steps below:

Preparation of frontend base layers: The web app will have multiple pages into it
which would be arranged and assembled in a sequential manner. The ground survey
will be conducted to validate the actual roof information with processed data on a
sampling basis.
The user will be starting with the landing page of our web app and eventually, they
need to log in or register as per their requirement. They will be then directed towards
the home page from where they can take control of the entire web app and carry out
the functions as per their requirement.

Through mail id and some other credentials the users all social media handles will be
connected and through which user can even operate them; the user once connected
through our web app they would be displayed all the content that is good for them all
types of toxic, violent, and other illegal content will be removed automatically.

Fig 1.1 Methodology Flowchart

2.1.2 System Interfaces

In order to use this opinion mining tool at the client side following re the minimum
system requirements :
Specification Description
 Web browser Microsoft Internet Explorer v9.0 or,
higher, Mozilla Firefox v12. Or, higher,
Google chrome v27.0.1453.116m or,
higher.
Internet Browsing Speed 512kbps
2.1.2 Interfaces

 User need to login and complete the procedure for accessing the tool.
 User has to provide valid credentials (such as Username, password, email-
id ,etc).
 User can’t change their credentials once registered successfully.

2.1.3 Hardware Interfaces

Hosting Server Configuration(Minimum System Requirements) :

Specifications Particulars
OS Windows 2008 R2 64-Bit
CPU Intel Core i5 – 4 cores
RAM 5 GB
Storage 2 x 1 TB Hard Drive
Bandwidth 4-8 MBPS

2.1.4 Software Interfaces

1) Web Application:
 Frontend frameworks
 PHP and AJAX

2) Database:
Including Open-Source Relational Database (Enterprise version),
 PostgreSQL v8.4.10 or, Higher;
 PostGIS v1.5.3 or, Higher.

2.2 Product Functions :

Sr.no Particulars
1 User Registration
2 User Login
3 User Profile
4 User Logout
5 Website Home Page
6 Select the required social media handle
7 Select the options as directed further

2.3 User Characteristics :