CHAPTER - I

INTRODUCTION

1
 CHAPTER - I
INTRODUCTION

The Internet has become an inevitable part of the lives of people today. Gone are the
days when people would browse the net only to retain and even enhance their social lives
through Social Networking Sites. By being aware of your cyber-surroundings and who you
are talking to, you should be able to safely enjoy social networking online. Our intension is
directed at the issue of privacy risk and user behavior in order to suggest viable solutions for
users to both improve their privacy protection, and be able to deploy the social functions
expected from these types of network.
Every human being in the world wants to communicate to their society regarding their
emotions and feelings. There are various mediums existing in the society nowadays for the
same. Like for example Facebook, Twitter etc. Peoples are communicating not only their
personal issues and feelings but also the issues which are happening around the world and
which are relevant to the current society. So any matter or discussions or issues which they
are communicating in this social medias are commonly known as posts .There are two types
of posts. It can be analyze and find out whether it is good or bad. We are trying to analyze
various types of posts through this project.
In recent years, with the growing volume of online reviews available on the Internet,
sentiment analysis and opinion mining, as a special text mining task for determining the
subjective attitude (i.e., sentiment) expressed by the text, is becoming a hotspot in the field of
data mining and natural language processing. Sentiment classification is a basic task in
sentiment analysis, with its aim to classify the sentiment (e.g., positive or negative) of a given
text. The general practice in sentiment classification follows the techniques in traditional
topic-based text classification, where the Bag-of-words (BOW) model is typically used for
text representation. In the BOW model, a review text is represented by a vector of
independent words. The statistical machine learning algorithms (such as naïve Bayes,
maximum entropy classifier, and support vector machines) are then employed to train a
sentiment classifier.

2
1.2 MODULES
 User Login And Registration
 Profile Creation
 Abuse Report
 Admin Login
 User Management
 Review And Reports
 Comment Management
 Sentimental Analysis
 Lexical Dictionary

1.3 MODULE DESCRIPTION

1.3.1USER LOGIN AND REGISTRATION
User can input to system & can access the features after successful registration on
system.

1.3.2 PROFLE CREATION

User creates profile with his personal details, provided with personal images fields
like name, address, place, contact etc. User is identified with this profile info to other users
in system.

1.3.3ABUSE REPORT
In case of content uploaded a user can send a abuse to other users, admin can view
this report per views.

1.3.4ADMIN LOGIN
From provided credentials admin may able to login & can manage users.

1.3.5USER MANAGEMENT
User can be blocked or deactivated with this management interface provided to
admin. Admin makes decision with help of abuse module.

3
1.3.6 REVIEW AND REPORTS
Every human being in the world wants to communicate to their society regarding
their emotions and feelings. There are various mediums existing in the society nowadays
for the same. Like for example Facebook , Twitter etc. Peoples are communicating not only
their personal issues and feelings but also the issues which are happening around the world
and which are relevant to the current society. so any matter or discussions or issues which
they are communicating in this social medias are commonly known as posts. There are two
types of posts. It can be analyze and find out whether it is good or bad. We are trying to
analyze various types of posts through this project.

1.3.7 COMMENT MANAGEMENT

We can comment to a post we can also view, edit, delete it as per our wish.

1.3.8 SENTIMENTAL ANALYSIS

Sentiment Analysis is process of computationally identifying and categorizing
opinions expressed in a piece of text, especially in order to determine whether the writer's
attitude towards a particular topic, product, etc. is positive, negative, or neutral. “Sentiment
Analysis is the task of identifying positive and negative opinions, emotions, and
evaluations”. Sentiment Analysis has many names. It’s often referred to as subjectivity
analysis, Opinion mining, and appraisal extraction, with some connections to affective
computing (computer recognition and expression of emotion).

DUAL SENTIMENTAL ANALYSIS

A model called dual sentiment analysis (DSA), to address this problem for sentiment
classification. We first propose a novel data expansion technique by creating a sentiment-
reversed review for each training and test review. On this basis, we propose a Dual
Training(DT)algorithm to make use of original and reversed training reviews in pairs for
learning a sentiment classifier, and a dual prediction algorithm to classify the test reviews
by considering two sides of one review.
When we post an article it first extracts the text, means it takes only subject, verb and
object others are eliminated. Using DT algorithm creates reversed review. Using lexical
dictionary sentimental classification will take place. There are three values 1,-1,0 for
positive, negative and neutral words correspondingly. Finally it calculated the overall sum
it must be either 1,-1,0.If it is negative it didn’t posted, otherwise inserted to the home.
4
POSITIVE SENTIMENTS
These are the good words about the target in consideration. If the positive sentiments
are raised, it is indicated to be good. In case of commodity reviews, if the positive reviews
about the commodities are more, it is bought by many customers.

NEGATIVE SENTIMENTS
These are the bad words about the target in deliberation. If the negative sentiments
are increased, it is discarded from the optional list. In case of commodity reviews, if the
negative reviews about the commodities are more, no one intend to buy it.

MAIN STEPS OF SENTIMENTAL ANALYSIS

 Text Extraction – This step involves extracting words from text that influence the
outcome of the result.
 Text Refinement – This step involves refining text in form of relevant phrases,
words etc.
 Text Classification – This step includes classification of text into its
class(positive/negative/neutral).
 Score Aggregation – This step collects total scores from classifier and then
aggregates it further to produce the total sentiment score.

POLARITY SHIFT
Polarity shift is a kind of linguistic circumstance which can reverse the sentiment
polarity of the text. Negation is the most essential type of polarity shift. For example, by
adding a negation word “don’t” to a positive text “I like this book” since the word “like”,
the sentiment of the text will be reversed from positive to negative. Anyhow, the two
sentiment-opposite texts are acknowledged to be very similar by the BOW representation.
The main reason why standard machine learning algorithms often decline under the
circumstance of polarity shift. Several methods have been proposed in the literature to
indicate the polarity shift problem.

1.3.9LEXICAL DICTIONARY
In the languages where lexical resources are abundant, a straightforward way is to get
the antonym dictionary directly from the well-defined lexicons, such as WordNet in English.
WordNet is a lexical database which groups English words into sets of synonyms called
5
synsets, provides short, general definitions, and records the various semantic relations
between these synonym sets. Using the antonym it is possible to obtain the words and their
opposites. The WordNet antonym dictionary is simple and direct. However, in many
languages other than English, such an antonym dictionary may not be readily available. Even
if we can get an antonym dictionary, it is still hard to guarantee vocabularies in the dictionary
are domain consistent with our tasks. To solve this problem, we furthermore develop a corpus-
based method to construct a pseudo-antonym dictionary. This corpus-based pseudo-antonym
dictionary can be learnt using the labeled training data only. The basic idea is to first use
mutual information to identify the most positive-relevant and the most negative-relevant
features, rank them in two separate groups, and pair the features that have the same level of
sentiment strength as pair of antonym words.

6
 CHAPTER - II
SYSTEM STUDY AND SPECIFICATION

7
 CHAPTER - II
SYSTEM STUDY AND SPECIFICATION

2.1 EXISTING SYSTEM

The general practice in sentiment classification follows the techniques in traditional
topic-based text classification, where the Bag-of words (BOW) model is typically used for
text representation. In the BOW model, a review text is represented by a vector of
independent words. The statistical machine learning algorithms (such as naïve Bayes,
maximum entropy classifier, and support vector machines) are then employed to train a
sentiment classifier.
Although the BOW model is very simple and quite efficient in topic-based text
classification, it is actually not very suitable for sentiment classification because it disrupts
the word order, breaks the syntactic structures, and discards some semantic information.
Consequently, a large number of researches in sentiment analysis aimed to enhance
BOW by incorporating linguistic knowledge. However, due to the fundamental deficiencies
in BOW, most of these efforts showed very slight effects in improving the classification
accuracy. One of the most well-known difficulties is the polarity shift problem.
DISADVANTAGES:
 Polarity shift problem.
 Disrupts the word order.
 Breaks the syntactic structure and discards some semantic information.

2.2PROPOSED SYSTEM
In this paper, we propose a simple yet efficient model, called dual sentiment analysis
(DSA), to address the polarity shift problem in sentiment classification. By using the
property that sentiment classification has two opposite class labels (i.e., positive and
negative), we first propose a data expansion technique by creating sentiment reversed
reviews. The original and reversed reviews are constructed in a one-to-one correspondence.
Thereafter, we propose a dual training (DT) algorithm and a dual prediction (DP)
algorithm respectively, to make use of the original and reversed samples in pairs for training
a statistical classifier and make predictions. In DT, the classifier is learnt by maximizing a
combination of likelihoods of the original and reversed training data set. In DP, predictions
are made by considering two sides of one review. That is, we measure not only how
positive/ negative the original review, but also how negative/ positive the reversed review.

8
 We further extend our DSA framework from polarity (positive vs. negative)
classification to 3-class (positive vs. negative vs. neutral) sentiment classification, by taking
the neutral reviews into consideration in both dual train in and dual prediction. To reduce
DSA’s dependency on an external antonym dictionary, we finally develop a corpus-based
method for constructing a pseudo-antonym dictionary. The pseudo antonym dictionary is
language-independent and domain- adaptive. It makes the DSA model possible to be applied
into a wide range of applications.
When a user posting an article using post button it checks whether it’s sentiments is
positive or negative by clicking itself. If it is negative , it will be terminated otherwise posted
on the wall. if a user try to insert an article about another user using @tag , a notification is
going to that person whose id is following the @tag. When a third person commented to that
post a notification is going to both one who posted that article and also the person whom the
article represents.

ADVANTAGES:
 Allow positive reviews and block negative reviews.
 We can change negative reviews.
 Notification for both negative and positive reviews and comments.

9
2.3 SOFTWARE SPECIFICATION
 Operating system : Windows 7 Ultimate.
 Coding Language : ASP.Net with C#.
 Front-End : Visual Studio 2012 Professional.
 Data Base : SQL Server 2008.
 Design Language : HTML, JavaScript.

2.4HARDWARE SPECIFICATION
 System : Pentium IV 2.4 GHz.
 Hard Disk : 40 GB.
 Floppy Drive : 1.44 Mb.
 Monitor : 14’ Color Monitor.
 Mouse : Optical Mouse.
 Ram : 512 Mb.

10
 CHAPTER - III
DESIGN AND DEVELOPMENT

11
 CHAPTER – III
DESIGN AND DEVELOPMENT

3.1INPUT FORM DESIGNS

3.1.1 SIGN UPAND LOGIN

3.1.2 CREATE ARTICLE

12
3.1.3 COMMENT

3.1.4MESSAGE

3.1.5 PROFILE MANAGEMENT

13
3.2 DATA FLOW DIAGRAM

Level 0:

SENTIMENTALA
User name NALYSIS OF user name
Admin USER’S User
REVIEWS AND
User name COMMENTS ON user name
SOCIAL MEDIA

Fig3.2.1.Data Flow Diagram Level0

14
 LEVEL1 OF USER:

Register
User user

View Login
Log Search
Friend
Manage
comment
Profile
log Managemen
t
Manage
comment Friend
Message
Request
Friend
View
notificatio
Post n
review
Friend Message
Abuse
Photo Report
Upload

Request Abuse

Photo Gallery

Fig.3.2.2.Data Flow Diagram Level1 For User

15
LEVEL 1 OF ADMIN:

ADMIN LOGIN ADMIN

BLOCK
USER
CHANGE
VIEW PASSWORD
VIEW ABUSE
LOG REPORT

USER
LOG ABUSE

Fig3.2.3.Data Flow Diagram level1 For Admin

16
LEVEL 2 REGISTRATION
u_id

us_name

us_pwd

REGISTRATION
name_user AND User
LOGIN

personal_info

Place

Address
Fig3.2.4.Data Flow Diagram level2 For Registration

LEVEL 2 COMMENT

cmnt_id

post_cmnt
COMMENT
Comment
photo_id

user_id

cmnt_rslt

Fig3.2.5.Data Flow Diagram level2 Forcomment

17
LEVEL 2 REVIEW

url

Status

share_with

u_id

REVIEW
Review
person_on_post_id

art_cont
ent
art_reslt
Fig3.2.6.Data Flow Diagram level2 Forreview

LEVEL 2 MESSAGE

Msg_id

MESSAGE
U_id Message

Friend_id

Dat_tdy

message

Fig3.2.7.Data Flow Diagram level2 Formessage

18
3.3 ENTITY RELATIONSHIP DIAGRAM
url u_id
message ab_id
pwd u_name u_id

us_name
manage abuse
has
N us_pwd
admin
1 by_u_id user
ab_datetime
1 name_
user
manage
address
contact
a_id
view log has

place
log_id block_user_id

u_id log_datetime status

has
manag has
view have e
u_id u_id

Message Friend Photo

Request gallery Comment

fr_id
status post_
fr_id
cmnt
status
Share user_id
_with
message url
u_id
photo_id
u_id
dat_tdy friend_id req_id art_rslt
cmnt_id

to_id photo art_content

msg_id _id cmnt_rslt
Fig.3.3.1 ER Diagram`

19
3.4SYSTEM ARCHITECTURE

DUAL SENTIMENTAL ANALYSIS

POST
User

Original review Reversed review

Dual training classification

Original test review Reversed test review

Dual prediction

Admin

20
 Negative Word
Positive Post
Post features

Training set

Feature
extractor
Post

Classifier

Positive

Negative

Fig 3.4.1System architecture

21
 3.5 TABLE DESIGN

3.5.1 PHOTO_GALLERY
Field Data type Definition Constrains

photo_id Int Id of the photo Primary

Key
url varchar(50) url of photo Not null

Status Int To store status Not null

share_with Int Id of the user Not null

share with
u_id Int User id Not null

art_content Text Content of article Not null

art_reslt varchar(50) Result of article Not null

person_on_post_id Int Id of the person Not null

on the post

3.5.2 TBL_ADMIN
Field Data type Definition Constrain
a_id Int Id of admin Primary Key
u_name varchar(50) Username of admin Not null
Pwd varchar(50) Password Not null

3.5.3 TBL_ABUSE
Field Data type Definition Constrain
ab_id Int Abuse id Primary Key
u_id Int Abused user id Not Null
by_u_id Int Abuser id Not Null
message varchar(50) Abused message Not Null
ab_datetime Datetime Abused date time Not Null

22
3.5.4 TBL_REQUEST
Field Data type Definition Constrain
req_id Int Request id Primary key
u_id Int User id Not Null
to_id Int Requested user id Not Null
Command varchar(50) Command to the Not Null
user
Status Int Not Null

3.5.5 TBL_COMMENTS
Field Data type Definition Constrain
cmnt_id Int id of Comment Primary Key
post_cmnt Text Command Not Null
photo_id Int Post/photo id Not Null
user_id Int Id of user Not Null
cmnt_rslt varchar(50) Command result Not Null

3.5.6 TBL_FRIEND
Field Data type Definition Constrain

fr_id Int Id of friend table Primary Key

u_id Int Id of user Not Null

friend_id Int Id of friend Not Null

Status Int status Not Null

3.5.7 TBL_LOG
Field Data type Definition Constrain

log_id Int User login id Primary Key

log_datetime Datetime User login date time Not Null

u_id Int Id of user Not Null

block_user_id Int Blocked user id Not Null

23
3.5.8 TBL_MESSAGE
Field Data type Definition Constrain

msg_id Int Message id Primary Key

u_id Int Id of user Not Null

friend_id Int Id of friend Not Null

dat_tdy Datetime Message date time Not Null

message varchar(50) Message to the Not Null

friend

3.5.9 TBL_USER
Field Data type Definition Constrain
u_id Int User id Primary Key
us_name varchar(50) Username of user Not Null
account
us_pwd varchar(50) Password of user Not Null
account
name_user varchar(50) Name of the user Not Null
Contact varchar(50) Phone number Not Null
personal_info varchar(50) Personal details Not Null
Address Text Address of user Not Null
Place varchar(50) Place of user Not Null
url varchar(50) User photo url Not Null
Status Int status Not Null

24
 CHAPTER - IV
CODING AND DEPLOYMENT

25
 CHAPTER – IV
CODING AND DEPLOYMENT

User_home.aspx.cs

using System;
usingSystem.Collections.Generic;
usingSystem.Linq;
usingSystem.Web;
usingSystem.Web.UI;
usingSystem.Web.UI.WebControls;
usingSystem.Data;
publicpartialclassUser_user_home : System.Web.UI.Page
{ dbcondb = newdbcon();
protectedvoidPage_Load(object sender, EventArgs e)
{ if (!IsPostBack)
{ fill();
// getArticle();
upload_Photo();
btnDelet();
DataTabledt = db.getdatatable("select * from tbl_friend where u_id=" + Session["usr_id"]+"
and status=1");
if (dt.Rows.Count> 0)
{ lbl_frnds.Text = "Friends" + dt.Rows.Count; }
else
{ lbl_frnds.Text = "0 Friends"; } } }

publicvoid fill()
{ DataTabledt = db.getdatatable("select * from tbl_user where u_id=" + Session["usr_id"]);

lbl_name.Text = dt.Rows[0]["name_user"].ToString();
lbl_adrs.Text = dt.Rows[0]["address"].ToString();
lbl_phn.Text = dt.Rows[0]["contact"].ToString();
lbl_plac.Text = dt.Rows[0]["place"].ToString();
Image1.ImageUrl = "../assets/example/" + dt.Rows[0]["url"].ToString();

// Image1.ImageUrl = "../images/unnamed.png" ;

}
publicvoidupload_Photo()
{
stringuser_id = Session["usr_id"].ToString();

DataTabledt = db.getdatatable("select * from photo_gallery order by photo_iddesc");

if (dt.Rows.Count> 0)

26
{ DataList1.DataSource = dt;
DataList1.DataBind();
}}
protectedvoidbtn_upload_Click(object sender, EventArgs e)
{ Response.Redirect("photo_upload.aspx"); }
protectedvoidbtn_report_Command(object sender, CommandEventArgs e)
{ Response.Redirect("abuse.aspx?val="+e.CommandArgument.ToString()); }
protectedvoidbtn_delet_Command(object sender, CommandEventArgs e)
{ stringstr = e.CommandArgument.ToString();
string[] str2;
str2 = str.Split(';');
string q = "delete photo_gallery where photo_id=" + str2[1] + "";
int n = db.Ins_Up_Del(q);
if (n > 0)
{
upload_Photo();
btnDelet();
} }
publicvoidbtnDelet()
{ foreach (DataListItem item in DataList1.Items)
{
Buttonbtn = item.FindControl("btn_delet") asButton;
stringstr = btn.CommandArgument;
string[] str2 ;
str2 = str.Split(';');
if (str2[0] == Session["usr_id"].ToString())
{ btn.Visible = true; } } }
protectedvoidbtn_post_Click(object sender, EventArgs e)
{ Response.Redirect("add_articles.aspx"); } }

Add_articles.aspx.cs

using System;
usingSystem.Collections.Generic;
usingSystem.Linq;
usingSystem.Web;
usingSystem.Web.UI;
usingSystem.Web.UI.WebControls;
usingSystem.Data;
using System.Net;
using System.IO;
usingNewtonsoft.Json;
usingNewtonsoft.Json.Linq;

publicpartialclassUser_user_comments : System.Web.UI.Page
{
dbcondb = newdbcon();
staticstringart_reslt = "";

protectedvoidPage_Load(object sender, EventArgs e)

{ if (!IsPostBack)
27
{

// txt_comnt.Text = "Your photo is good " +" \n "+"Change your photo" + "\n" +"photo can
be better";

}
}
protectedvoidbtn_submit_Click(object sender, EventArgs e)
{ if (txt_titl.Text != ""&&txt_comnt.Text != "")
{
//
Response.Redirect("https://api.uclassify.com/v1/uClassify/Sentiment/classify/?readKey=Moiw
yl1rKteB&text="+txt_comnt.Text+ "");

// Create a request for the URL.

WebRequest request = WebRequest.Create(
"https://api.uclassify.com/v1/uClassify/Sentiment/classify/?readKey=Moiwyl1rKteB&text=" +
txt_comnt.Text + "");
// If required by the server, set the credentials.
request.Credentials = CredentialCache.DefaultCredentials;
// Get the response.
WebResponse response = request.GetResponse();
// Display the status.
Console.WriteLine(((HttpWebResponse)response).StatusDescription);
// Get the stream containing content returned by the server.
StreamdataStream = response.GetResponseStream();
// Open the stream using a StreamReader for easy access.
StreamReader reader = newStreamReader(dataStream);
// Read the content.
stringresponseFromServer = reader.ReadToEnd();
//lbl_msg.Text = responseFromServer;
// Display the content.
Console.WriteLine(responseFromServer);
// Clean up the streams and the response.
reader.Close();
response.Close();
stringjson = responseFromServer;
JObjectobj = JObject.Parse(json);
stringstr = obj["negative"].ToString();
string str2 = obj["positive"].ToString();
// string sub = obj.negative;

doubleneg = Convert.ToDouble(str);
doublepos = Convert.ToDouble(str2);
if (pos>neg)
{
art_reslt = "positive";
lbl_msg.Text = str + "<br>" + str2 + "positive";
}
else
{
28
art_reslt = "Negative";
lbl_msg.Text = str + "<br>" + str2 + "Negative";
}

// checking @
stringmsg = txt_comnt.Text;
string[] at_rate = msg.Split('@');
intlen = at_rate.Length;
if (len == 1)
{
insert_articl();

}
else
{
string msg2 = at_rate[1];
string[] strn = msg2.Split(' ');
string msg3 = strn[0];

if (art_reslt == "Negative")
{
lbl_msg.Text = "Negative post about a person is not allowed here";

}
else
{ insert_articl();
}}
// }
else
{
ScriptManager.RegisterStartupScript(this, typeof(Page), "alert", "alert('Fields Can Not Be
Empty');", true);
}
}
publicvoidinsert_articl()
{
stringqry = "insert into photo_gallery (u_id,art_content,ph_name,art_reslt) values(" +
Session["usr_id"] + ",'" + txt_comnt.Text + "','" + txt_titl.Text + "','" + art_reslt + "')";
int n = db.Ins_Up_Del(qry);
if (n > 0)
{
lbl_msg.Text = "Successfully Added";
txt_comnt.Text = "";
txt_titl.Text = "";
}
else
{
lbl_msg.Text = "Insertion failed";
}}}

29
Notification.aspx.cs
using System;
usingSystem.Collections.Generic;
usingSystem.Linq;
usingSystem.Web;
usingSystem.Web.UI;
usingSystem.Web.UI.WebControls;
usingSystem.Data;

publicpartialclassUser_notifications : System.Web.UI.Page
{
dbcondb = newdbcon();

protectedvoidPage_Load(object sender, EventArgs e)

{

if (!IsPostBack)
{

fill();

publicvoid fill()
{
// DataTable dt1 = db.getdatatable("select r.* from tbl_rules r inner join tbl_abusea on
r.allow_user_id = a.by_u_id where r.u_id=" + Session["usr_id"]);

DataTabledt = db.getdatatable("select u.name_user,ab.message,ab.ab_datetime,ab.ab_id from

tbl_abuseab inner join tbl_user u on ab.by_u_id = u.u_id where ab.message='Uploaded' and
ab.u_id=" + Session["usr_id"]);

if (dt.Rows.Count> 0)
{
lbl_notif.Visible = false;

GridView1.DataSource = dt;
GridView1.DataBind();

else
{
lbl_notif.Visible = true;

}
protectedvoid Button1_Command(object sender, CommandEventArgs e)
30
{
string q = "delete tbl_abuse where ab_id="+e.CommandArgument.ToString();

int n = db.Ins_Up_Del(q);

if (n > 0)
{

ScriptManager.RegisterStartupScript(this, typeof(Page), "alert", "alert('Successfully Deleted');",

true);
fill();

}
}

Abuse.aspx.cs

using System;
usingSystem.Collections.Generic;
usingSystem.Linq;
usingSystem.Web;
usingSystem.Web.UI;
usingSystem.Web.UI.WebControls;
usingSystem.Data;

publicpartialclassUser_abuse : System.Web.UI.Page
{
dbcondb = newdbcon();
protectedvoidPage_Load(object sender, EventArgs e)
{

}
protectedvoidbtn_snd_Click(object sender, EventArgs e)
{
stringstr = Request.QueryString["val"];

int n = db.Ins_Up_Del("insert into tbl_abuse values(" + Session["usr_id"] + "," + str + ",'" +

txt_msg.Text + "',getdate())");

if (n > 0)
{

txt_msg.Text = "";

lbl_msg.Text = "Send Successfully . . .";

}}}

31
 CHAPTER – V
TESTING AND IMPLEMENTATION

32
 CHAPTER – V
TESTING AND IMPLEMENTATION

INTRODUCTION
The most important phase in system development life cycle is system testing. The
number and nature of errors in a newly designed system depends on the system specifications
and the time frame given for the design.
A newly designed system should have all the subsystems working together, but in reality
each subsystems work independently. During this phase, all the subsystems are gathered into
one pool and tested to determine whether it meets the user requirements.
Testing is done at two level -Testing of individual modules and testing the entire system.
During the system testing, the system is used experimentally to ensure that the software will
run according to the specifications and in the way the user expects. Each test case is designed
with the intent of finding errors in the way the system will process it.
Testing plays a very critical role in determining the reliability and efficiency of software
and hence is a very important stage in software development. Software testing is done at
different levels. They are the unit testing and system testing which comprises of integration
testing and acceptance testing.

5.1 TESTING METHODOLOGIES

Unit Testing
This is the first level of testing. The different modules are tested against the specifications
produced during the integration. This is done to test the internal logic of each module. Those
resulting from the interaction between modules are initially avoided. The input received and
output generated is also tested to see whether it falls in the expected range of values. Unit
testing is performed from the bottom up, starting with the smallest and lowest modules and
proceeding one at a time.
The units in a system are the modules and routines that are assembled and integrated to
perform a specific function. The programs are tested for correctness of logic applied and
detection of errors in coding. Each of the modules was tested and errors are rectified. They
were then found to function properly.

33
Integration Testing
In integration testing, the tested modules are combined into sub-systems, which are then
tested. The goal of integration testing to check whether the modules can be integrated properly
emphasizing on the interfaces between modules. The different modules were linked together
and integration testing done on them.

Validation Testing

The objective of the validation test is to tell the user about the validity and reliability of
the system. It verifies whether the system operates as specified and the integrity of
important data is maintained. User motivation is very important for the successful performance
of the system.

All the modules were tested individually using both test data and live data. After each
module was ascertained that it was working correctly and it had been "integrated" with the
system. Again the system was tested as a whole. We hold the system tested with different
types of users. The System Design, Data Flow Diagrams, procedures etc. were well
documented so that the system can be easily maintained and upgraded by any computer
professional at a later.

System Testing
The integration of each module in the system is checked during this level of testing. The
objective of system testing is to check if the software meets its requirements. System testing
is done to uncover errors that were not found in earlier tests. This includes forced system
failures and validation of total system as the user in the operational environment implements
it. Under this testing, low volumes of transactions are generally based on live data. This
volume is increased until the maximum level for each transactions type is reached. The total
system is also tested for recovery after various major failures to ensure that no data are lost
during the breakdown.

34
5.2 SYSTEM IMPLEMENTATION
5.2.1IMPLEMENTATION PROCEDURES
Implementation is the most crucial stage in achieving a successful system and giving the
user’s confidence that the new system is workable and effective. Implementation of a
modified application to replace an existing one. This type of conversation is relatively easy to
handle, provide there are no major changes in the system.
Each program is tested individually at the time of development using the data and has
verified that this program linked together in the way specified in the programs specification,
the computer system and its environment is tested to the satisfaction of the user. The system
that has been developed is accepted and proved to be satisfactory for the user. And so the
system is going to be implemented very soon. A simple operating procedure is included so
that the user can understand the different functions clearly and quickly.
Initially as a first step the executable form of the application is to be created and loaded in
the common server machine which is accessible to all the user and the server is to be
connected to a network. The final stage is to document the entire system which provides
components and the operating procedures of the system.

35
5.3 USER TRAINING
 Install visual studio 2012 on your computer.
 Run the project in local host.
 Click the signup button for registration, after successful registration login to the social account
using your username and password.
 If you are forget the password, then you can click on forget password youwill get that on your
e-mail.
 You can see different options in your account like home,profile,friend,request,message
andblock/unblock etc.
 The home page is same for every user. You can see post button in the home page. Click the
post button. Now you can see the space for write article. Use @ symbol for mention other
user.Then press submit button.
 If you write a positive review then it will uploaded on the home page. A notification is going
to that mentioned user.
 If you write a too negative article which breaks others privacy then it will not posted.A
notification will also going to that one.
 Others can comment to the post.For both negative and positive comments notification is going
to the user.
 In the profile part you can add a profile picture and update the profile.
 You can search a person on the search box and can send friend request,also you can see
requests from other users in the request part,and accept the request.
 You can block/unblock and unfriend a friend.
 The message part is for chat purpose with your friends.
 You can logout the account by clicking logout button.
 If you are not interested being a member, you can deactivate that account.

36
5.4 FINAL TEST CASE REPORT OF ALL MODULES
Test_ID Test Description Test steps Excepted Actual Status
output output
TC-01 Enter registration 1.Enter The user is Same as EO Success
details to sign up registrationdetails registered and
shown
2.click on sign up successfully
registered

TC-02 Enter registration 1.Enter Alert is shown Same as EO Success

details to sign up registrationdetails to type the
incorrect format details in
correct format
2.click on sign up

TC-03 Enter valid 1.enter valid Successful login Same as EO Success

username and username
password
2.enter valid
password

3.click on login
button
TC-04 Enter username 1.Enter username A pop up Same as EO Success
and / or password and password message box to
invalid invalid or enter show an invalid
username or username
password invalid orpassword

2. click on login
button

TC-05 update profile Enter personal Profile is Same as EO Success

and add profile details and click successfully
picture update button to updated. Profile
add profile picture is added.
picture
TC-06 Find a friend Enter friend Friend profile is Same as EO Success
name on search shown
box

Click search
button
TC-07 Find a friend Enter invalid user An alert shown Same as EO Success
name as friend Could not find
name on search name
box

37
 Click search
button
TC-08 Send friend Search friend Friend request Same as EO Success
request user name send
Successfully
Click add friend
TC-09 Accept a person Click on request An alert shown Same as EO Success
as a friend You are friends
Click on accept now
TC-10 Block a friend Click on friend Blocked alert Same as EO Success

Click on block
button
TC-11 unfriend a friend Click on friend Unfriended Same as EO Success
successfully
Click on unfriend
TC-12 Post a review Click on post Successfully Same as EO Success
review is added
Write article to home page.
Notification
Click on submit isgoing to the
user thepost
about whom

TC-13 Post a negative Click on post A message Same as EO Success

review shown negative
Write post about a
negativearticle person is not
allowed here. A
Click on submit notification
going to that
one
TC-14 Commenting to a Write comment Successfully Same as EO Success
post and press enter commented
TC-15 Negative Write negative Successfully Same as EO Success
Commenting to a comment and commented
post press enter
Notification
going to the
user negative
commenting on
a post about you
TC-16 User Login to admin The user is Same as EO Success
management account blocked to the
block user by system
admin if a user is Click on block
abuser
TC-17 Approve a user Click on approve The user can Same as EO Success
to use the system use the system

38
 to the system

TC-18 Message to a Click on message Message Same as EO Success

friend successfully
Enter the content sended

Choose the friend

Click send
TC-19 View a message Click on The messages Same as EO Success
messages are shown

Click on view
messages
TC-20 Deactivate Click on The account is Same as EO Success
account deactivate deactivated
permanently
Click on
conformation
TC-21 Logout from an Click on logout The login page Same as EO Success
account is shown

39
 CHAPTER - VI
SYSTEM MAINTENANCE

40
 CHAPTER - VI
SYSTEM MAINTENANCE

System Maintenance changes the existing system, enhancement adds features to the
existing system, and development replaces the existing system. It is an important part of system
development that includes the activities which corrects errors in system design and
implementation, updates the documents, and tests the data.

In this Project the after the system design and implementation is done, maintaining the
activities and process done in the new system.
The following are the system maintenance process in this project:

 Collecting Errors.
 Checking whether the project meets user’s requirements.
 Testing with sample data.
 Documenting the manual.
 Update the process in the existing system.
 Hardware and Software Maintenance.

41
 CHAPTER -VII
CONCLUSION /SCOPE FOR FUTURE
ENHANCEMENT / BIBLIOGRAPHY

42
 CHAPTER – VII
CONCLUSION
The “SENTIMENTAL ANALYSIS OF USER’S REVIEWS AND COMMENTS
ON SOCIAL MEDIA” is developed using c# with ASP.Net. It fully meets the objective of
the proposed system which it have been developed. The system has reached a steady state
where all the bugs have been eliminated. The system is operated at a high level of efficiency
and all the teachers and the users associated with the system understand its advantages.
Online social networks help people to socialize with the world. But users should be
aware of threats that can be faced due to lack of proper privacy settings. In this paper a novel
method for collaborative sharing of data in OSNs is discussed as well as a method to resolve
privacy conflicts that can occur while multiple persons share a data. Evaluation results show
that privacy risk and data sharing loss are minimized in this approach. Various websites offer
services such as uploading, hosting, and managing for photo-sharing (publicly or privately).
These functions are provided by websites and applications that facilitate the upload and
display of images. The term may even be useful for online photo galleries that are positioned
up and managed by individual users, including photo blogs.
In this work, we propose a novel data expansion approach, called dual sentiment
analysis (DSA), to address the polarity shift problem in sentiment classification. The basic
idea of DSA is to create reversed reviews that are sentiment-opposite to the original reviews,
and make use of the original and reversed reviews in pairs to train a sentiment classifier and
make predictions. DSA is highlighted by the technique of one-to-one correspondence data
expansion and the manner of using a pair of samples in training (dual training) and prediction
(dual prediction).A wide range of experiments demonstrate that the DSA model is very
effective for polarity classification and it significantly outperforms several alternative methods
of considering polarity shift. In addition, we strengthen the DSA algorithm by developing a
selective data expansion technique that choosestraining reviews with higher sentiment degree
for data expansion. The experimental results show that using a selected part of training
reviews for data expansion can yield better performance than that using all reviews.

43
 SCOPE FOR FUTURE ENHANCEMENT

In this project, we focus on creating reversed reviews to assist supervised sentiment

classification. In the future, we can generalize the DSA algorithm to a wider range of sentiment
analysis tasks. We also plan to consider more complex polarity shift patterns such as
transitional, subjunctive and sentiment-inconsistent sentences in creating reversed reviews.
We can extract the sentiment of imuchies and also implement it in translations(in different
languages). In this dual sentimental analysis we can only analyze the text which is written in
english language. In the future part we can expand it to analyze the sentiments of text which is
written in other languages.we use more imuchies in chatting, so in the further part we can also
analyze the sentiment of imuchies.

44
 BIBLIOGRAPHY

BOOK REFERENCES

 “Dual Sentiment Analysis: Considering Two Sides of One Review”,Rui Xia, FengXu,
ChengqingZong, Qianmu Li, Yong Qi, and Tao Li ,IEEE Transactions on Knowledge
and Data Engineering DOI 10.1109/TKDE.2015.2407371.
 “Principles of Software Engineering”. RohitKhurna,vikas publishing ,2014.
 ”Review of Dual Sentiment Analysis”Bhagyashri Ramesh Jadhav,
ManjushriMahajanInternational Journal of Science and Research (IJSR) 2013.
 ”Sentiment Analysis For Two Sides Of Reviews Using Dual Prediction
Algorithm”G.GraceRanjitham, S.Mohana, B.Vinothini , IJARTET, 2016.

WEBSITES REFERENCES

 Face book help centre.http://www.facebook.com/help/.

 http://www.facebook.com/press/info.php?Statistics, 2010.
 Open Social. website.http://www.opensocial.org, 2010.
 Platform for privacy preferences (p3p) project.http://www.w3.org/P3P/
 World Wide Web Consortium (W3C).

45
 ANNEXURES

46
 OUTPUT DESIGN

POST

NOTIFICATION

47
 SCREEN SHOTS OF EXECUTED RESULTS

WRITING REVIEW

TRY TO POST NEGATIVE REVIEW

48
COMMENTING TO THE POST

TRY TO NEGATIVE COMMENT

POSTED REVIEW

49
NOTIFICATION TO THE USER

ADMIN

50
MANAGING USER

ABUSE REPORT

VIEW LOG

51
 ABBREVIATIONS

DSA DUAL SENTIMENTAL ANALYSIS

BOW BAG OF WORDS

DT DUAL TRAINING

DP DUAL PREDICTION

OSN ONLINE SOCIAL NETWORK

52