ABSTRACT

In this current era, social media plays an important role in data exchange, sharing their

thoughts. Emotional Effect of a person maintains an important role on their day-to-day life.

Product Rating Analysis is a procedure of analysing the opinions and polarity of thoughts of

the person.

Twitter is a main platform on sharing the thought's, opinion and Product Rating on different

occasions. Twitter Product Rating Analysis is method of analysing the emotions from tweets

(message posted by user in twitter).

Tweets are helpful in extracting the Product Rating values from the user. The data

provide the Polarity indication like positive, negative or unbiassed values. It is focused on the

person’s tweets and the hash tags for understanding the situations in each aspect of the

criteria. The paper is to analyse the famous person’s id’s (@realdonaldtrump) or hash tags

(#IPL2018) for understanding the mindset of people in each situation when the person has

tweeted or has acted upon some incidents.

The proposed system is to analyse the Product Rating of the people using PHP, twitter API,

Text Blob (Library for processing text). As the results it helps to analysis the post with a

better accuracy.

1
1
 1.INTRODUCTION

1.1 PROJECT DESCRIPTION

In the era of social media, platforms like Twitter have become invaluable resources for

understanding public sentiment towards various topics, including global crises such as the

COVID-19 pandemic. Sentiment analysis, a subfield of natural language processing (NLP),

enables the automated extraction and categorization of sentiment from text data. This project

aims to apply machine learning techniques to analyse sentiment from COVID-19 related

tweets on Twitter.

1.1.1 Objectives

• Gather a large dataset of tweets related to COVID-19 using Twitter API.

• Preprocess the data to remove noise, such as URLs, special characters, and stop words.

• Utilize machine learning models for sentiment analysis, including but not limited to:

- Naive Bayes

- Support Vector Machines (SVM)

- Recurrent Neural Networks (RNNs)

- Transformers (e.g., BERT)

• Train and fine-tune the chosen models on the pre-processed Twitter data.

• Evaluate the performance of each model using metrics such as accuracy, precision, recall,

and F1-score.

• Visualize the sentiment trends over time using time-series analysis techniques.

1.1.2 Methodology
2
2
• Data Collection

- Utilize the Twitter API to collect a large volume of tweets related to COVID-19 using

relevant keywords and hashtags.

- Store the collected tweets in a suitable format for further processing.

• Data Preprocessing

- Remove noise from the tweets, including URLs, special characters, and stop words.

- Tokenize the text and perform lemmatization or stemming to normalize the words.

- Encode the text data into numerical representations suitable for machine learning models.

• Model Training:

- Split the pre-processed data into training and testing sets.

- Implement and train various machine learning models for sentiment analysis, including

traditional algorithms like Naive Bayes and SVM, as well as deep learning models like RNNs

and BERT.

- Fine-tune the hyperparameters of the model's using techniques like grid search or random

search.

• Model Evaluation:

- Evaluate the performance of each model using standard evaluation metrics such as

accuracy, precision, recall, and F1-score.

- Compare the performance of different models to identify the most effective approach for

sentiment analysis of COVID-19 related tweets.

• Visualization and Analysis:

3
3
 - Visualize the sentiment trends over time using techniques such as time-series analysis and

sentiment analysis dashboards.

- Analyse the findings to gain insights into public sentiment towards COVID-19 and related

topics on Twitter.

1.1.3 Deliverables

• Finalized dataset of pre-processed COVID-19 related tweets.

• Trained machine learning models for sentiment analysis.

• Evaluation report comparing the performance of different models.

• Visualization of sentiment trends over time.

• Documentation detailing the methodology, findings, and insights gained from the analysis.

2.SYSTEM ANALYSIS

4
4
 2.1 EXISTING SYSTEM

Product Rating analysis is the process of analysis of the text from many levels.

First level is document level, the classification task determines the class of an object

based on its attributes, and after that it can analysed at the sentence level for

classifying the sentence based on the negative, positive and neutral Product Ratings.

2.2 PROPOSED SYSTEM

Twitter Product Rating analysis comes under the category of text and opinion

mining. It focuses on analysing the Product Ratings of the tweets and feeding the data

to a machine learning model to train it and then check its accuracy, so that we can use

this model for future use according to the results.

It comprises of steps like data collection, text preprocessing, Product Rating

detection, Product Rating classification, training and testing the model. This system

has evolved during the last decade with models reaching the efficiency of almost

85%-90%. But it still lacks the dimension of diversity in the data. Along with this it

has a lot of application issues with the slang used and the short forms of words. Many

analysers don’t perform well when the number of classes are increased. Also, it’s still

not tested that how accurate the model will be for topics other than the one in

consideration. Hence Product Rating analysis has a very bright scope of development

in future.

2.3 FEASIBILITY STUDY

5
5
 In this method we use text blob as a method to find the polarity of the text

(positive text, negative text or neutral text).

The tweets are imported from the Twitter using the (API) provided by the Twitter

Developer. From these API various fields like tweets, source, retweets, likes,

language, user etc. can be scrapped. After collecting these data, we can analyse the

various famous person thoughts on an event or occasion.

3.SYSTEM CONFIGURATION

6
6
3.1 HARDWARE CONFIGURATION

HDD: >90GB

PROCESSOR: >Pentium IV 2.4GHz

SYSTEM TYPE: 32bit / 64 bit

RAM: >2GB

OS: WINDOWS 7/8/8.1/10

3.2 SOFTWARE CONFIGURATION

TOOL: XAMPP, PHP, MYSQL

3.3 SOFTWARE DESCRIPTION

PHP

PHP started out as a small open-source project that evolved as more and more people
found out how useful it was. Rasmus Lerdorf unleashed the first version of PHP way back in
1994.

• PHP is a recursive acronym for "PHP: Hypertext Preprocessor".

• PHP is a server side scripting language that is embedded in HTML. It is used to

manage dynamic content, databases, session tracking, even build entire e-commerce
sites.

• It is integrated with a number of popular databases, including MySQL, PostgreSQL,

Oracle, Sybase, Informix, and Microsoft SQL Server.

7
7
 • PHP is pleasingly zippy in its execution, especially when compiled as an Apache
module on the Unix side. The MySQL server, once started, executes even very
complex queries with huge result sets in record-setting time.

• PHP supports a large number of major protocols such as POP3, IMAP, and LDAP.
PHP4 added support for Java and distributed object architectures (COM and
CORBA), making n-tier development a possibility for the first time.

• PHP is forgiving: PHP language tries to be as forgiving as possible.

• PHP Syntax is C-Like.

Common uses of PHP

• PHP performs system functions, i.e. from files on a system it can create, open, read,
write, and close them.

• PHP can handle forms, i.e. gather data from files, save data to a file, through email
you can send data, return data to the user.

• You add, delete, modify elements within your database through PHP.

• Access cookies variables and set cookies.

• Using PHP, you can restrict users to access some pages of your website.

• It can encrypt data.

Characteristics of PHP

Five important characteristics make PHP's practical nature possible

• Simplicity
• Efficiency
• Security
8
8
 • Flexibility
• Familiarity

"Hello World" Script in PHP

To get a feel for PHP, first start with simple PHP scripts. Since "Hello, World!" is an
essential example, first we will create a friendly little "Hello, World!" script.

As mentioned earlier, PHP is embedded in HTML. That means that in amongst your normal
HTML (or XHTML if you're cutting-edge) you'll have PHP statements like this −

Live Demo
<html>

<head>
<title>Hello World</title>
</head>

<body>
<?php echo "Hello, World! ";?>
</body>

</html>

It will produce following result −

Hello, World!

If you examine the HTML output of the above example, you'll notice that the PHP code is
not present in the file sent from the server to your Web browser. All of the PHP present in
the Web page is processed and stripped from the page; the only thing returned to the client
from the Web server is pure HTML output.

All PHP code must be included inside one of the three special markup tags ATE are
recognised by the PHP Parser.

<?php PHP code goes here?>

<?PHP code goes here?>

9
9
<script language = "php"> PHP code goes here </script>

A most common tag is the <?php...?> and we will also use the same tag in our tutorial.

From the next chapter we will start with PHP Environment Setup on your machine and then
we will dig out almost all concepts related to PHP to make you comfortable with the PHP
language.

MySQL

My SQL is an open-source relational database management system (RDBMS) that enables

users to store, manage, and retrieve structured data efficiently.it is widely used for various
applications, from small-scale projects to large-scale websites and enterprise-level solutions

There are a few elements of MySQL. Let’s take a closer look at them:

Database

In relation to MySQL, a database is a structured collection of data organized and stored in

tables. It serves as a central repository where information is efficiently managed, allowing

users to store, retrieve, update, and delete data. MySQL provides the software framework to

create, maintain, and interact with these databases, making data storage and retrieval

seamless and reliable.

Client-Server Model

Computers that install and run RDBMS software are called clients. Whenever they need to
access data, they connect to the RDBMS server.
MySQL is one of many RDBMS software options. RDBMS and MySQL are often thought to
be the same because of MySQL’s popularity. A few big web applications like Facebook,
Twitter, YouTube, Google, and Yahoo! all use MySQL for data storage purposes. Even
though it was initially created for limited usage, it is now compatible with many important
computing platforms like Linux, macOS, Microsoft Windows, and Ubuntu.

10
10
MySQL and are not the same Be aware that MySQL is one of the most popular RDBMS
software’s brand names, which implements a client-server model.
The client and server use a domain-specific language – Structured Query Language (SQL) to
communicate in an RDBMS environment. If you ever encounter other names that have SQL
in them, like Postgres and Microsoft SQL server, they are most likely brands which also use
Structured Query Language syntax. RDBMS software is often written in other programming
languages but always uses SQL as its primary language to interact with the database. MySQL
itself is written in C and C++.
SQL tells the server what to do with the data. In this case, SQL statements can instruct the
server to perform certain operations:

• Data query – requesting specific information from the existing database.

• Data manipulation – adding, deleting, changing, sorting, and other operations to
modify the data, the values or the visuals.
• Data identity – defining data types, e.g. changing numerical data to integers. This
also includes defining a schema or the relationship of each table in the database
• Data access control – providing security techniques to protect data. This includes
deciding who can view or use any information stored in the database

11
11
xampp

XAMPP is an abbreviation where X stands for Cross-Platform, A stands for Apache, M

stands for MYSQL, and the Ps stand for PHP and Perl, respectively. It is an open-source
package of web solutions that includes Apache distribution for many servers and command-
line executables along with modules such as Apache server, MariaDB, PHP, and Perl.

XAMPP helps a local host or server to test its website and clients via computers and laptops
before releasing it to the main server. It is a platform that furnishes a suitable environment to
test and verify the working of projects based on Apache, Perl, MySQL database, and PHP
through the system of the host itself. Among these technologies, Perl is a programming
language used for web development, PHP is a backend scripting language, and MariaDB is
the most vividly used database developed by MySQL. The detailed description of these
components is given below

Components of xampp

As defined earlier, XAMPP is used to symbolize the classification of solutions for different
technologies. It provides a base for testing of projects based on different technologies through
a personal server. XAMPP is an abbreviated form of each alphabet representing each of its
major components. This collection of software contains a web server named Apache, a
database management system named MariaDB and scripting/ programming languages such
as PHP and Perl. X denotes Cross-platform, which means that it can work on different
platforms such as Windows, Linux, and macOS.

Many other components are also part of this collection of software and are explained below.

• Cross-Platform: Different local systems have different configurations of operating systems

installed in it. The component of cross-platform has been included to increase the utility and
audience for this package of Apache distributions. It supports various platforms such as
packages of Windows, Linus, and MAC OS.

• Apache: It is an HTTP a cross-platform web server. It is used worldwide for delivering web
content. The server application has made free for installation and used for the community of
developers under the aegis of Apache Software Foundation. The remote server of Apache
delivers the requested files, images, and other documents to the user.

12
12
• MariaDB: Originally, MySQL DBMS was a part of XAMPP, but now it has been replaced
by MariaDB. It is one of the most widely used relational DBMS, developed by MySQL. It
offers online services of data storage, manipulation, retrieval, arrangement, and deletion.

• PHP: It is the backend scripting language primarily used for web development. PHP allows
users to create dynamic websites and applications. It can be installed on every platform and
supports a variety of database management systems. It was implemented using C language.
PHP stands for Hypertext Processor. It is said to be derived from Personal Home Page tools,
which explains its simplicity and functionality.

• Perl: It is a combination of two high-level dynamic languages, namely Perl 5 and Perl 6.
Perl can be applied for finding solutions for problems based on system administration, web
development, and networking. Perl allows its users to program dynamic web applications. It
is very flexible and robust.

• phpMyAdmin: It is a tool used for dealing with MariaDB. Its version 4.0.4 is currently
being used in XAMPP. Administration of DBMS is its main role.

• OpenSSL: It is the open-source implementation of the Secure Socket Layer Protocol and
Transport Layer Protocol. Presently version 0.9.8 is a part of XAMPP.

• XAMPP Control Panel: It is a panel that helps to operate and regulate upon other
components of the XAMPP. Version 3.2.1 is the most recent update. A detailed description of
the control panel will be done in the next section of the tutorial.

• Webalizer: It is a Web Analytics software solution used for User logs and provide details
about the usage.

• Mercury: It is a mail transport system, and its latest version is 4.62. It is a mail server,
which helps to manage the mails across the web.

• Tomcat: Version 7.0.42 is currently being used in XAMPP. It is a servlet based on JAVA
to provide JAVA functionalities.

13
13
• FileZilla: It is a File Transfer Protocol Server, which supports and eases the transfer
operations performed on files. Its recently updated version is 0.9.41.

14
14
 4.SYSTEM DESIGN
4.1 Detailed design

Detailed design takes the high-level system architecture and breaks it down into intricate
details. It focuses on how each component works internally, how they talk to each other, and
what data they use. This refined blueprint, often with diagrams, ensures a smooth transition
from design to development for a well-functioning system.

4.1.1 Architectural Diagram:

An architectural diagram is a visual representation that maps out the physical

implementation for components of a software system. It shows the general structure of the
software system and the associations, limitations, and boundaries between each element

15
15
4.1.2 UML diagram:

StarUML is the successor of an object-oriented modelling software called Plastic.

Plastic
1.0 was published in 1997 to support the OMT notation. The version 1.1 published in
1998 dropped the OMT to support in favor of UML. The last version under this brand was
called Agora Plastic 2005 and was published by the Korean company Plastic Software
Inc, Seoul. It was an internationalized product, compliant with UML 1.4, and claiming to
support the Object Management Group's MDA approach.

The software was renamed StarUML 5.0 in 2005 with a view to publishing it as
open source. The aim was to provide UML 2.0 support as well as the capability to use
third-party plugins. The first public release was published in August 2006 on Source
Forge under GNU GPL license. The source code included multiple copyright notices for
the period 2002-2005 by Plastic Software Inc. The software targeted at that time the
Win32 platform and was essentially written in Delphi. The software evolved over several
years as an open-source project and was recognized as an MDA tool with a capability to
assist in reverse-engineering existing code. The last open-source version is published in
2010. It may still be used nowadays, but according to the owner of the product, it would
no longer be maintained nor supported.
A crowdfunding campaign was launched in 2014 to finance a revival of the project
under the name StarUML 2. The aim of the initiative was to add support for other
languages than Java and other modeling notations than UML. The campaign failed to
raise the needed funds: less than 1000 USD were collected, that is 1% of the campaign's
target.

16
16
 StarUML offers object-oriented modelling capabilities. It supports most of the
diagram types specified in UML 2.0.:

‣ Class diagrams

‣ Composite structure diagrams

‣ Component diagrams

‣ Object diagrams

‣ Package diagrams

‣ Use-case diagrams

‣ Activity diagrams

‣ Sequence diagrams

‣ Communication diagrams

‣ Timing diagrams

‣ State diagrams

‣ Information flow diagrams

‣ Interaction overview diagrams

‣ Profile diagrams

17
17
4.1.2.1 USE CASE DIAGRAM:

Use case diagrams are considered for high level requirement analysis of a system.
So, when the requirements of a system are analyzed, the functionalities are captured in
use cases. So, we can say that uses cases are nothing, but the system functionalities
written in an organized manner.

18
18
4.1.2.2 SEQUENCE DIAGRAM:

A sequence diagram or system sequence diagram (SSD) shows Process

interactions arranged in time sequence in the field of software engineering. It depicts the
processes involved and the sequence of messages exchanged between the processes
needed to carry out the functionality.

19
19
4.1.2.3 DATAFLOW DIAGRAM:

DFD is the abbreviation for Data Flow Diagram. The flow of data of a system or a
process is represented by DFD. It also gives insight into the inputs and outputs of each entity
and the process itself. DFD does not have control flow and no loops or decision rules are
present. Specific operations depending on the type of data can be explained by a flowchart. It
is a graphical tool, useful for communicating with users, managers and other personnel. it is
useful for analysing existing as well as proposed system.

20
20
4.1.2.4 TABLE DESIGN:

Table Design is a powerful feature in SAP Analysis for Microsoft Office. It brings more
flexibility in designing and editing the crosstabs and enables formatting and lay outing
reports while keeping the ability for OLAP navigation. The changes made using
Table Design persist after navigation steps that force a rebuild of the crosstab, such as a
refresh or swapping axes.

The following Table Design options are available to edit the crosstabs:

• New lines
• Formats
• Formulas (also formulas to input-enabled planning data cells)
• Text

5.SYSTEM IMPLEMENTATION
21
21
4.1 MODULE LIST

➢ Twitter Extraction

➢ Classification of the tweets

➢ Product Rating Analysis

4.2 MODULE DESCRIPTION

Twitter Extraction - It facilitates interrelation among the system and the client. The

client has privileges to create account and access his/her feeds from the system.

Classification of the tweets - Using Naïve Baye's algorithm, the data can be analysed

and can recognize the patterns used for the classification and regression analysis. After pre-

processing the extracted data, it is then classified into keyword related tweets. It classifies and

predicts the group and clusters according to the user group. The same clusters are grouped

under a classification. All the positive tweets are clustered into a positive classification, all

the negative tweets are clustered into a negative classification, tweets containing a mixture of

both the positive and the negative are clustered into a mixed classification and all the neutral

tweets are clustered into a neutral classification. The classification of the tweets makes easier

to find the score point for each classification. And hence the polarity of each classification

can be represented.

Product Rating Analysis - The Product Rating analysis is used comparatively to

categorise the positive, negative, mixed and neutral comments related with the text

categorization. Product Rating analysis has the complexity like conveying the assumptions in

different ways. In opinion texts, the lexical content might get misloaded. Intra-textual and
22
22
sub-sentential reversals and negation topics can be commonly interpreted. The below are the

possibilities that need to be classified as Users, Texts, Sentences (paragraphs, chunks of text),

Predetermined descriptive phrases (, etc), Words, Tweets/updates. Product Rating-oriented

data sets are scope sensitive, and it is challenging to create/collect the data from large

domain. Representations of the Product Rating needs more attention on elements to classify

and scale the domain-appropriate annotated data is available or not. This work deals with the

analysis of the tweets, and it checks for the behaviour of the tweets posted by the user

6.SYSTEM TESTING

23
23
 System testing usually consists of a layered process, including the user interface (UI)

layer, the business layer, the data access layer and the database itself. The UI layer deals with

the interface design of the database, while the business layer includes databases

supporting business strategies.

Databases, the collection of interconnected files on a server, storing information, may not

deal with the same type of data, i.e. databases may be heterogeneous. As a result, many kinds

of implementation and integration errors may occur in large database systems, which

negatively affect the system's performance, reliability, consistency and security. Thus, it is

important to test in order to obtain a database system which satisfies the ACID properties

(Atomicity, Consistency, Isolation, and Durability) of a database management system.

One of the most critical layers is the data access layer, which deals with databases

directly during the communication process. Database testing mainly takes place at this layer

and involves testing strategies such as quality control and quality assurance of the product

databases. Testing at these different layers is frequently used to maintain consistency of

database systems, most commonly seen in the following examples:

Data is critical from a business point of view. Companies such as Google or

Symantec, who are associated with data storage, need to have a durable and consistent

database system. If database operations such as insert, delete, and update are performed

without testing the database for consistency first, the company risks a crash of the entire

system.

Some companies have different types of databases, and also different goals and

missions. In order to achieve a level of functionality to meet said goals, they need to test their

database system.

24
24
 The current approach of testing may not be sufficient in which developers formally

test the databases. However, this approach is not sufficiently effective since database

developers are likely to slow down the testing process due to communication gaps. A

separate database testing team seems advisable.

Database testing mainly deals with finding errors in the databases so as to eliminate

them. This will improve the quality of the database or web-based system.

Database testing should be distinguished from strategies to deal with other problems

such as database crashes, broken insertions, deletions or updates. Here, database refactoring

is an evolutionary technique that may apply.

TYPES OF TESTINGS AND PROCESSES

The figure indicates the areas of testing involved during different database testing

methods, such as black-box testing and white-box testing.

➢ WHITE BOX TESTING: White-box testing (also known as clear box testing, glass

box testing, transparent box testing, and structural testing) is a method of testing

software that tests internal structures or workings of an application, as opposed to its

functionality (i.e. black-box testing). In white box testing an internal perspective of

25
25
 the system, as well as programming skills, are used to design test cases. The tester

chooses inputs to exercise paths through the code and determine the expected outputs.

This is analogous to testing nodes in a circuit, e.g. in-circuit testing (ICT). White-box

testing can be applied at the unit, integration and system levels of the software testing

process. Although traditional testers tended to think of white box testing as being

done at the unit level, it is used for integration and system testing more frequently

today. It can test paths within a unit, paths between units during integration, and

between subsystems during a system–level test. Though this method of test design can

uncover many errors or problems, it has the potential to miss unimplemented parts of

the specification or missing requirements.

➢ BLACK BOX TESTING: Black-box testing is a method of software testing that

examines the functionality of an application without peering into its internal structures

or workings. This method of test can be applied virtually to every level of software

testing: unit, integration, system and acceptance. It is sometimes referred to as

specification-based testing. Test cases are built around specifications and

requirements, i.e., what the application is supposed to do. Test cases are generally

derived from external descriptions of the software, including specifications,

requirements and design parameters. Although the tests used are primarily functional

in nature, non-functional tests may also be used.

• SCREENSHOT

26
26
 Source code

const firstName = document.querySelector('#firstName');

const lastName = document.querySelector('#lastName');

const email = document.querySelector('#email');

27
27
const username = document.querySelector('#username');

const bio = document.querySelector('#bio');

const dob = document.querySelector('#dob');

const curentPassword = document.querySelector('#currentPassword');

const password = document.querySelector('#password');

const confirmPassword = document.querySelector('#confirmPassword');

const personalInfoForm = document.querySelector('#personalInfoForm');

const changePasswordForm = document.querySelector('#changePasswordForm');

firstName.addEventListener('keyup', validateFirstName);

lastName.addEventListener('keyup', validateLastName);

email.addEventListener('keyup', validateEmail);

username.addEventListener('keyup', validateUsername);

bio.addEventListener('keyup', validateBio);

dob.addEventListener('keyup', validateDob);

currentPassword.addEventListener('keyup', validateCurrentPassword);

password.addEventListener('keyup', validatePassword);

confirmPassword.addEventListener('keyup', validateConfirmPassword);

function validateFirstName() {

validateNames(firstName);

function validateLastName() {

validateNames(lastName);

28
28
function validateNames(elem) {

const text = elem.value;

const re = /^[a-z]{3,15}$/i;

if(!re.test(text) ) {

elem.classList.add('is-invalid');

return true;

} else {

elem.classList.remove('is-invalid');

return false;

function validateEmail(e) {

const text = email.value;

const re = /^[a-z]([\w\_\-\.])+@([\w\.])+\.(\w){2,5}$/i;

if(!re.test(text)) {

email.classList.add('is-invalid');

return true;

} else {

email.classList.remove('is-invalid');

return false;

29
29
function validateUsername(e) {

const text = username.value;

const re = /^([\w\_]){3,10}$/i;

if(!re.test(text)) {

username.classList.add('is-invalid');

return true;

} else {

username.classList.remove('is-invalid');

return false;

function validateBio() {

const text = bio.value;

const re = /^[\w\W]+$/i;

if(!re.test(text) ) {

bio.classList.add('is-invalid');

return true;

} else {

bio.classList.remove('is-invalid');

return false;

30
30
function validateDob(e) {

const text = dob.value;

const re = /^([\w\s])+\,(\s)([0-9]){4}$/i;

if(!re.test(text)) {

dob.classList.add('is-invalid');

return true;

} else {

dob.classList.remove('is-invalid');

return false;

function validateCurrentPassword(e) {

const text = currentPassword.value;

const re = /^[\w]{6,}$/i;

const uppercase = /[A-Z]/;

const number = /[0-9]/;

if(!re.test(text) || (text.search(uppercase) == '-1') || (text.search(number) == '-1')) {

currentPassword.classList.add('is-invalid');

return true;

} else {

currentPassword.classList.remove('is-invalid');

return false;

31
31
 }

function validatePassword(e) {

const text = password.value;

const re = /^[\w]{6,}$/i;

const uppercase = /[A-Z]/;

const number = /[0-9]/;

if(!re.test(text) || (text.search(uppercase) == '-1') || (text.search(number) == '-1')) {

password.classList.add('is-invalid');

return true;

} else {

password.classList.remove('is-invalid');

return false;

function validateConfirmPassword(e) {

const text = confirmPassword.value;

if(text !== password.value) {

confirmPassword.classList.add('is-invalid');

return true;

} else {

confirmPassword.classList.remove('is-invalid');

return false;

32
32
 }

personalInfoForm.addEventListener('submit', (e) => {

if(validateFirstName() || validateLastName() || validateUsername() || validateEmail() ||

validateBio() || validateDob()) {

validateFirstName();

validateLastName();

validateEmail();

validateUsername();

validateBio();

validateDob();

} else {

return true;

e.preventDefault();

});

changePasswordForm.addEventListener('submit', (e) => {

if(validateCurrentPassword() || validatePassword() || validateConfirmPassword()) {

validateCurrentPassword();

validatePassword();

validateConfirmPassword();

} else {

return true;

33
33
 }

e.preventDefault();

});

const date = new Date();

const monthsShort =

'Jan',

'Feb',

'Mar',

'Apr',

'May',

'Jun',

'Jul',

'Aug',

'Sep',

'Oct',

'Nov',

'Dec'

];

const todaysDate = date.getDate() + ' ' + monthsShort[date.getMonth()] + ', ' +

date.getFullYear();

const currentDate = new Date(todaysDate);

34
34
document.addEventListener('DOMContentLoaded', function() {

var elems = document.querySelector('.datepicker');

var instances = M.Datepicker.init(elems, {maxDate: currentDate});

dob.addEventListener('focus', () => {

instances.open();

});

var sidenav = document.querySelectorAll('.sidenav');

var sideNavInstances = M.Sidenav.init(sidenav);

});

• CONCLUSION.

In machine learning both classifiers achieve the best results when using the features of

the Count_Vectorizer. Overall, Logistic Regression outperforms the Multinomial Naive

Bayes classifier. The best performance on the test set comes from the Logistic Regression

with features from Count_Vectorizer. This can be further implemented using the deep

learning techniques in order to get the more accurate results.

35
35
 • BIBLIOGRAPHY

1. Sadhasivam, J., & Kalivaradhan, R. B. (2019). An empirical

comparison of supervised learning algorithms and hybrid

WDBN algorithm for MOOC courses. Journal of Ambient Intelligence and Humanized

Computing.

https://doi.org/10.1007/s12652-019-01190-9

2. Abdelwahab, O., Bahgat, M., Lowrance, C. J., &Elmaghraby, A.

(2015). Effect of Training Set Size on SVM and Naïve Bayes

for Twitter Product Rating Analysis. IEEE International Symposium on Signal Processing

and Information Technology

(ISSPIT), 46–51.

36
36
3. Andranik, T., Timm, O. S., Philipp, G. S., & Isabell, M. W.

(2010). Predicting Elections with Twitter: What 140 Characters Reveal about Political

Product Rating Andranik. Proceedings

of the Fourth International AAAI Conference on Weblogs

and Social Media Predicting, 30(2), 178–185.

4. Barbosa, L., & Feng, J. (2010). Robust Product Rating Detection

on Twitter from Biased and Noisy Data. Coling, (August),

36–44.

5. Bian, J., Umit, T., & Fan, Y. (2015). Towards Large-scale Twitter Mining for Drug-

related Adverse Events. SHB ’12 Proceedings of the 2012 international workshop on

Smart

health and wellbeing, 20(2), 163–178.

6. Celikyilmaz, A., Hakkani-Tür, D., & Feng, J. (2010). Probabilistic model-based Product

Rating analysis of twitter messages.

2010 IEEE Workshop on Spoken Language Technology, SLT

2010 - Proceedings, 79–84.

7. Cuesta, Á., Barrero, D. F., & R-Moreno, M. D. (2014). A

framework for massive twitter data extraction and analysis.

Malaysian Journal of Computer Science, 27(1), 50–67.

8. Gamallo, P., & Garcia, M. (2014). Citius: A Naive-Bayes Strategy for Product Rating

Analysis on English Tweets. Proceedings

of the 8th International Workshop on Semantic Evaluation

(SemEval 2014), (SemEval), 171–175. Retrieved from

http://aclweb.org/anthology/S14-2026

9. Kamps, J., Marx, M., Mokken, R. J., &Rijke, M. de. (2004).

37
37
Using WordNet to Measure Semantic Orientations of Adjectives. Proceedings of the

Fourth International Conference on

Language Resources and Evaluation (LREC’04), 1115–1118.

Retrieved from http://aclanthology.info/papers/usingwordnet-to-measure-semantic-

orientations-of-adjectives

10. Liu, B., Blasch, E., Chen, Y., Shen, D., & Chen, G. (2013). Scalable Product Rating

classification for Big Data analysis using Naïve Bayes Classifier. 2013 IEEE International

Conference on

Big Data (pp. 99–104).

11. Nakov, P., Rosenthal, S., Ritter, A., & Wilson, T. (2013).

SemEval-2013 Task 2: Product Rating Analysis in Twitter. Proceedings of the

International Workshop on Semantic Evaluation (SemEval-2013), 2(SemEval), 312–320.

12. Neethu, M. S., &Rajasree, R. (2013). Product Rating analysis in

twitter using machine learning techniques. 2013 Fourth International Conference on

Computing, Communications and

Networking Technologies (ICCCNT) (pp. 1–5).

13. Niu, Z., Yin, Z., & Kong, X. (2012). Product Rating classification for

microblog by machine learning. Proceedings - 4th International Conference on

Computational and Information Sciences, ICCIS 2012, 286–289.

14. Pak, A., &Paroubek, P. (2010). Twitter as a Corpus for Product Rating Analysis and

Opinion Mining. In Proceedings of the

Seventh Conference on International Language Resources

and Evaluation, 1320–1326. Retrieved from

http://incctps.googlecode.com/svn/trunk/TPFinal/bibliografia/Pak

and Paroubek (2010). Twitter as a Corpus for Product Rating

Analysis and Opinion Mining.pdf

38
38
15. Sadhasivam, J., & Kalivaradhan, R. B. (2017). Review on

Product Rating Analysis a Learners’ Opinion. Iioab - Emerging

trends in Computer Engineering and Research, 8(2), 298–

303.

39
39