CLASSIFYING MESSAGE APPLICATION

USING KOTLIN

CS8611- MINI PROJECT

Submitted by

RAGHUL S (113020104303)
SIVAKUMAR P (113020104307)
ANAND KUMAR Y (113020104301)
SARAN SANJAY R (113020104306)

In partial fulfillment for the award of the

degree of

BACHELOR OF ENGINEERING

IN

COMPUTER SCIENCE AND ENGINEERING

VEL TECH HIGH TECH

Dr. RANGARAJAN Dr. SAKUNTHALA ENGINEERING COLLEGE
An Autonomous Institution

VEL TECH HIGH TECH DR.RANGARAJAN DR.

SAKUNTHALA ENGINEERING COLLEGE, AVADI

An Autonomous Institution
Approved by AICTE,New Delhi/ Affiliated to Anna University, Chennai –
600025 MAY 2023

1
 VEL TECH HIGH TECH
Dr. RANGARAJAN Dr. SAKUNTHALA ENGINEERING COLLEGE
An Autonomous Institution

Approved by AICTE-New Delhi, Affiliated to Anna University, Chennai

Accredited by NBA, New Delhi & Accredited by NAAC with “A” Grade & CGPA of 3.27

BONAFIDE CERTIFICATE

Certified that this mini project entitled “CLASSIFYING MESSAGE

APPLICATION USING KOTLIN” is the bonafide work of “Raghul S,
Sivakumar P , Anandkumar Y, Saran Sanjay R” who carried out the work under
my supervision.

SIGNATURE SIGNATURE
Dr. DURGA DEVI, B.E., M.E., PhD., Mr.Parthiban M.A
HEAD OF THE DEPARTMENT ASSISTANT PROFESSOR
Computer Science and Engineering Computer Science and Engineering
Dept. of Computer Science and Engg.Vel Dept. of Computer Science and Engg.Vel
Tech High Tech Dr.Rangarajan Dr.Sakunthala Tech High Tech Dr.Rangarajan Dr.Sakunthala
Engineering College Avadi, Chennai - Engineering College Avadi, Chennai -
600062 600062

2
 ACKNOWLEDGMENT

We wish to express our sincere thanks to the people who extended their help
during the course of our Mini Project work.

First of all we would like to express our deep gratitude to our beloved and
respected FOUNDER & CHAIRMAN Col. Prof. Vel. Shri. Dr. R.
RANGARAJAN B.E. (Elec.), B.E (Mech.), M.S (Auto.), DSC, and FOUNDRESS
& VICE CHAIRMAN Dr. SAKUNTHALA RANGARAJAN M.B.B.S. We also
record sincere thanks to our Honourable Principal, Dr. E.KAMALANABAN B.E.,
M.E., Ph.D., for his kind support for his Mini Project.

We are thankful and extremely grateful to our Dean-SoEC Dr. V. RAVI and Head
of the department Dr. S. DURGADEVI, B.E., M.E., Ph.D., for their support and
motivation feed to us for doing the Mini Project.

We would like to extend our sincere thanks to our guide Mr.PARTHIBAN M.A,
for her technical support during this project. Her stupendous encouragement enabled
us to complete our Mini Project successfully.

We would like to extend our sincere thanks to our Project Coordinator Dr. M.
MALATHY B.E., M.E., Ph.D., for their continuous support over this Mini Project.

3
 TABLE OF CONTENTS
CHAPTER NO TITLE PG NO
ABSTRACT 6
1 INRODUCTION 7
2 LITERATURE REVIEW 10
2.1 INTRODUCTION
2.2 Short Message Service (SMS)
2.3 BULK SMS
2.4 TEXTLOCAL
2.5 LOGONUTILITY
3 KEY POINTS 11
3.1 ANDROID
3.2 ABOUT ANDROID APP
3.3 KOTLIN THE PROGRAMMING LANGUAGE
3.4 GOOGLE FIREBASE
3.4.1 WHY FIREBASE OVER SQL
3.5 SECURE SOCKETS LAYER
3.6 REAL TIME DATABASE
3.7 XML
4 EXISTING AND PROPOSED SYSTEM 14
4.1 EXISTING SYSTEM
4.2. PROPOSED SYSTEM
5 MODULES 17
5.1 ANDROID APP STUDIO
5.2 SPAM FILTERING PROCESS

5.3 OTP DETECTION

5.4 TRANSCATION DETECTION
6 SYSTEM ARCHITECTURE 20
7 SOURCE CODE 21
8 IMPLEMENTATIONS 26
9 SAMPLE OUTPUT SCREENSHOTS 27

4
 9.1 SAMPLE XML SCREEN
9.2 SMS INTERFACE
9.3 SMS OTP DETECTION
9.4 SMS TRANSACTION
9.5 SMS SPAM DETECTION
10 RESULT 30
11 CONCLUSION 31
12 REFERENCES 32

5
 Abstract

The use of short message service (SMS) has grown tremendously in the past few
years. Billions of users use this service to send text messages. Various applications
have been introduced by service providers, e.g., mobile banking, summons
checkpoint, SMS chat, etc., all of which have become a huge success. This chapter
gives an overview of how this service is provided and discusses various SMS
applications offered to the user. We explore the reasons behind its success and the
issues that must be addressed to provide these applications. We also examine future
trends and the challenges that must be overcome in order to enhance this service. We
hope that this chapter gives a better understanding of how SMS applications are
provided and what may be expected in future applications given the enhancement on
the current SMS and technology advancementAlthough it is a widely used
communication mechanism for cell phone users, SMS is far more than just a
technology for teenage chat. SMS technology evolved out of the global system for
mobile communications standard, an internationally accepted cell phone network
specification the European Telecommunications Standards Institute created. The 3rd
Generation Partnership Project maintains the SMS standard. SMS messages are
handled via a short message service center that the cellular provider maintains for
the end devices. The SMSC can send SMS messages to the end device using a
maximum payload of 140 octets. This defines the upper bound of an SMS message
to be 160 characters using 7-bit encoding. It is possible to specify other schemes
such as 8-bit or 16-bit encoding, which decreases the maximum message length to
140 and 70 characters, respectively.

6
 Chapter 1

1.1 Introduction

Short Message Service (SMS) is the most frequently and widely used
communication medium. The term “SMS” is used for both the user activity and all
types of short text messaging in many parts of the world. It has become a medium of
advertisement and promotion of products, banking updates, agricultural information,
flight updates and internet offers. SMS is also employed in direct marketing known
as SMS marketing. Sometimes SMS marketing is a matter of disturbance to users.
These kinds of SMSs are called spam SMS. Spam is one or more unsolicited
messages, which is unwanted to the users, sent or posted as part of a larger collection
of messages, all having substantially identical content. The purposes of SMS spam
are advertisement and marketing of various products, sending political issues,
spreading inappropriate adult content and internet offers. That is why spam SMS
flooding has become a serious problem all over the world. SMS spamming gained
popularity over other spamming approaches like email and twitter, due to the
increasing popularity of SMS communication. However, opening rates of SMS are
higher than 90% and opened within 15 minutes of receipt whereas opening rate in
email is only 20-25% within 24 hours of receipt . Thus, a proper SMS spam
detection technique has significant necessity. There are several researches on email,
twitter, web and social tagging spam detection techniques. However, a very few
researches have been conducted on SMS spam detection. Spam SMS detection is
more challenging than email spam detection because of the restricted length of SMS,
use of regional content and shortcut words and SMS contains less header
information than an email

7
 Chapter 2
Literature survey

2.1 Introduction:
We are visit www.textlocal.in and www.logonutility.com for get the some
information about the bulk SMS. In this literature survey we are understand about
the bulk message sender and how to send bulk amount of message in any
organization for information alert about the organization. Textlocal is says that the
bulk message sender are most useful in big commercial agencies for sending the
bulk amount of messages. Logon Utility has a Bulk SMS gateway that pushes the
simple message to mobile phones. In other words, we have an effective tool that
sends the Bulk SMS through the internet to the people on the handheld device.

2.2 Short Message Service (SMS)?

SMS stand for short message service. It is technology that enables the sending
and receiving of message between mobile phones. SMS first appeared in European
1992. One SMS message can contain at most 140 bytes of data, so one SMS
message
can contain up to 160 characters .once a message is sent it is received by a SMSC
(short message service center) which must then get it to the appropriate mobile
device.

2.3 Bulk SMS ?

The Bulk SMS is very popular to send bulk amount of the message in the
organization & Used in Marketing and Banking. Bulk SMS is often used by Big &

8
small business owners, E-commerce industry, media Companies, Banks for Alerts,
Marketing and Fraud control alerts, Reminders, Marketing of products and services.
It’s also commonly used between staffs of company or bank and their clients. One
advantage of Bulk Messaging is that it delivers your message directly to the mobile
handsets anywhere around World.

2.4 Textlocal:

We are visit www.textlocal.in for get the some information about the bulk
SMS. In this literature survey we are understand about the bulk message sender and
how to send bulk amount of message in any organization for information alert about
the organization. www.textlocal.in is says that the bulk message sender are most
useful in big commercial agencies for sending the bulk amount of messages.
Bulk SMS or bulk messaging refers to businesses sending SMS to one or
more recipients via software platforms such as Textlocal. Bulk SMS can scale up to
millions of recipients in the case of informational or promotional broadcasts.
Alternatively, bulk SMS can also mean individual SMS sent to customers upon an
action e.g. receiving an alert on credit card transaction. Both these activities can be
easily carried out from bulk SMS platforms as they allow businesses to create,
schedule, send and track SMS campaigns.

2.5 Logonutility:

In this digital world, while exploring on the internet, we got the names of
many Bulk SMS service providers and picked up one randomly, hence
disappointments. To get the best Bulk SMS service provider is a somehow daunting
task. But today, this barrier will be overcome by the Logon Utility. It is an IT
company that has a robust SMS reseller network of 1200+ and handling over 15000+
clients in India. Utility’s success is entirely shown on an official website
9
logonutility.com where you can look at our best setup, services, infrastructure, and
veteran professionals as well.
The Logon utility have free Bulk SMS credits for first time signup clients so
visit our contact page and fill inquiry form to get more benefits. During sign up a
question come in mind that How to send Bulk SMS than we also have complete
information available on website. Send Bulk text messages online and also know
what
is SMS messaging.

10
 Chapter 3
Key Words and Definitions
3.1 Android

Android is a mobile operating system based on a modified version of the Linux

kernel and other open-source software, designed primarily for touch screen mobile
devices. Android is developed by a consortium of developers known as the Open
Handset Alliance and commercially sponsored by Google.

3.2 About Android App

Android App is software designed to run on an Android device or emulator. The

term also refers to an APK file which stands for Android package. This file is a Zip
archive containing app code, resources, and meta information. Android apps can be
written in Kotlin, Java, and C++ and are run inside Virtual Machine.

3.3 Kotlin the Programming Language

Kotlin is a cross-platform, statically typed, general-purpose programming

language with type inference. Kotlin is designed to interoperate fully with Java, and
the JVM version of Kotlin's standard library depends on the Java Class Library but
type inference allows its syntax to be more concise. Kotlin mainly targets the JVM,
but also compiles to Java Script or native code via LLVM Language development
costs are borne by JetBrains, while the Kotlin Foundation protects the Kotlin
trademark.

Kotlin is used by over 60% of professional Android developers that helps boost
productivity, developer satisfaction, and code safety.

On 7 May 2019, Google announced that the Kotlin programming language is now its
preferred language for Android app developers. Since the release of Android
Studio 3.0 in October 2017, Kotlin has been included as an alternative to the
standard Java compiler.

11
3.4 Google firebase

Firebase is a set of hosting services for any type of application (Android, iOS, Java
script, Node.js, Java, Unity, PHP, C++ ...). It offers NoSQL and real-time hosting of
databases, content, social authentication (Google, Face book, Twitter and Github),
and notifications, or services, such as a real-time communication server.
Firebase is a Backend-as-a-Service (BaaS) app development platform that provides
hosted backend services such as a real time database, cloud storage, authentication,
crash reporting, machine learning, remote configuration, and hosting for your static
files. Firebase supports Android App Studio.

3.4.1Why Firebase over SQL

Firebase is the one kind of NoSQL databases The Firebase database is just a big
JSON object where you can store whatever you want inside. Unlike SQL there's no
schema for the database, no tables, no columns, it's just a combination of key/value
pairs. SQL's predefined schemas determine the structure of data before you use it,
which can be restrictive.
Another great advantage of the Firebase framework is its swift and secure hosting
services. Firebase Hosting has extended support for all content types such as web
applications, static and dynamic content. Furthermore, the Firebase Hosting provider
ensures high security of the content using zero-configuration SSL.

3.5 Secure Sockets Layer

SSL stands for secure sockets layer. Protocol for web browsers and servers that
allows for the authentication, encryption & decryption of data sent over the internet.

3.6 Real time Database

12
Fire Base is a Real time Data Base. Having a real-time database is the standout
feature of the Firebase framework. Firebase caters to a cloud-hosted database in
which the data is stored as JSON and further synchronized constantly to each
associated client. Having a real-time database instance that updates the current data
is essential for modern applications.

3.7 XML

XML stands for eXtensible Markup Language, which is a way of describing data
using a text-based document. Because XML is extensible and very flexible, it's used
for many different things, including defining the UI layout of Android apps.
Other resources like strings for your app are also defined in an XML file
called strings.xml. You describe the view hierarchy of UI elements on the screen.
For example, a Constraint Layout can contain Buttons, Text Views, Image Views, or
other views. Remember, Constraint Layout is a subclass of View Group. It allows
you to position or size child views in a flexible manner.
We can see there are three sections at top right corner
1. Code
2. Split
3. Design

Code option allows us to view the entire code the working slide. Split is useful when
we want to check both the code and design side by side. Design is used to view the
design of the screen generated and allows us to make changes According to that it
will modify the code.

13
 Chapter 4
Existing and proposed system

4.1Existing system

India has one of the densest and prospective markets for cellular phones, and
mobile service providers have a strict policy about providing access to their
customer
bases. Many consumers activate “Do Not Disturb” services that disallow mass
publicity calls and messages. However, Bulk SMS service provider in Mumbai
maintain databases of people who are open to mass messages. This means that a
company engaging in this kind of marketing can actually reach out to a target
audience more efficiently. Not all bulk SMS reseller providers have extensive
resources however, and it is up to you to select the right vendor.
Bulk SMSs reach the target audience with greater efficiency than television
or print advertising because they reach the client directly. A message on your phone
is
something that you can always refer to later; and it doesn’t go ignored as marketing
calls often do. On the other side of the playing field, a bulk SMS reseller provider
can
reach out to thousands of people within a limited cost. While conventional
advertising
cannot guarantee the attention of your intended target audience, bulk SMSs will
allow
you a deeper reach into the market without spending as much as you would when
engaging in conventional marketing!
Moreover, in this digital world, smartphones are the best partner. Without it,
nobody survives. Even the old aged or illiterate people used to have smartphones and
they try to read all messages. These people never read email as they don’t have an
email account.

14
Hence, there may be no doubt that Bulk SMS service will assist you to
connect with your audiences better. Get your Bulk SMS service through us
thousands
of your audience at the same time. It is believed that an SMS is opened within five
minutes of its receipt, making it an effective medium to attain out on your target
market.ies

4.2 Proposed system

The proposed system used advanced methodologies to facilitate ease of use and
makes the messages more filtered and cleaner to view .
The transactions from various apps (like gpay , phonepe , paytm etc) are arranged
dynamically based on the content they possess .
Otp’s(One Time Passwords ) are automatically from the device after a specified
amount of time which makes it more secure and helps the comtribute to the free
space on the device .
These messages are automatically converted into modules based on a timed basis as
all messages from a certain timeline are clubbed together enabling to view it easier.

Spam messages are automatically seperated from the other essential messages
which makes it easier to identify messages we dont actually need.
These spam messages are also converted into seperated folders to make them to be
deleted easier.

15
 Chapter 5
Modules

The system is an App-based approach. We are going to use Android App Studio
which is a platform to make Android Apps.

5.1 Android App Studio

Android Studio provides a unified environment where you can build apps for
Android phones, tablets, Android Wear, Android TV, and Android Auto.
Structured code modules allow you to divide your project into units of
functionality that you can independently build, test, and debug.

It provides Gradle-based build support. Android-specific refactoring and quick fixes.

Lint tools to catch performance, usability, version compatibility and other problems.
It contains Templates to create Android designs and components. A rich layout
editor that allows users to drag-and-drop components even has Option to preview
layouts on multiple screen configurations. It has Built-in support for Google Cloud
Platform, enabling integration with Firebase Cloud Messaging and Google App
Engine. It even contains a Virtual Device (Emulator) to run and debug apps in the
Android studio.

5.2 Spam Filtering Process

A manually classified spam and ham messages are input or training set for a spam
filtering algorithm. The algorithm consists of the following steps

Preprocessing:
Removing irrelevant contents like stop words are the part of data preprocessing.

Tokenization:
Segmenting the message according to words, characters or symbols called tokens.
16
There are different tokenization approaches such as word tokenization, sentence
tokenization, word or character Ngrams and orthogonal sparse bigrams.

Representation:
Conversion to attribute value pairs. Selection: Selecting important attribute values
which have impact on classification rather than choosing all pairs of attribute value.

Training:
Train the algorithm with the selected attribute values.

Testing: Test the newly arrived data with the training model.

5.3 OTP Detection

Privacy concerns have always been an issue for Android users. Before Android 6
Marshmallow devices, accessing almost anything was possible from user's devices
which makes users privacy violated and vulnerable. But since Android released
request application permission before actually using it made it secure in some
manners.

Two of the major dangerous level permissions i.e., SMS and Location permissions
are most of the privacy concerning permissions. And now it's almost impossible for
new and old apps having these permissions to be published without having a very
strong use-case.

SMS / OTP detection requires SMS permissions from user. And its a common use
case for apps to auto-detect OTP while logging in through mobile verification. But
since READ_SMS and RCEIVE_SMS are not so much easier to get published on
the play store, Google launched SMS Verification APIs which does the task in-place.

17
5.4 Transaction Detection
Transactional Monitoring in today’s world is necessary to implement variable plans
and tiers of services to our customer base. With intelligent systems being put into
place at every junction of the transactional process from payment till the evaluation
of end numbers of purchases, we sought to find an intelligent source of digital data
that can drive insight generation like no other in the market.

The transactional SMS’s from a whole lot of messages are filtered out.
Virtual passbook is created by applying ML algorithms to the messages. SMS
transaction extractor solution applies its intelligence to categorize the messages into
various expense types across products & services, purchase patterns, and credit &
insurance risks.
Duplications are removed and filtered out.
If there are any incomplete values in the data, then they are filled.

18
 Chapter 6
System Architecture

19
 Chapter 7
Source code

SMS Read/Write:

Permission:

<!-- To use SMS based services -->

<uses-permission android:name="android.permission.RECEIVE_SMS" />
<uses-permission android:name="android.permission.READ_SMS" />
<uses-permission android:name="android.permission.SEND_SMS" />

Read SMS:

package com.example.readmessage;
import android.content.BroadcastReceiver;
import android.content.Context;
import android.content.Intent;
import android.os.Bundle;
import android.telephony.SmsMessage;

public class MessageReceiver extends BroadcastReceiver {

private static MessageListener mListener;

@Override
public void onReceive(Context context, Intent intent) {
Bundle data = intent.getExtras();
Object[] pdus = (Object[]) data.get("pdus");
for(int i=0; i<pdus.length; i++){
SmsMessage smsMessage = SmsMessage.createFromPdu((byte[]) pdus[i]);
String message = "Sender : " + smsMessage.getDisplayOriginatingAddress()
+ "Email From: " + smsMessage.getEmailFrom()
+ "Emal Body: " + smsMessage.getEmailBody()
+ "Display message body: " + smsMessage.getDisplayMessageBody()
+ "Time in millisecond: " + smsMessage.getTimestampMillis()
+ "Message: " + smsMessage.getMessageBody();
mListener.messageReceived(message);
}
}

20
 public static void bindListener(MessageListener listener){
mListener = listener;
}
}

Wirte SMS:

package com.example.sendsms;
import android.os.Bundle;
import android.app.Activity;
import android.app.PendingIntent;
import android.content.Intent;
import android.telephony.SmsManager;
import android.view.Menu;
import android.view.View;
import android.view.View.OnClickListener;
import android.widget.Button;
import android.widget.EditText;
import android.widget.Toast;

public class MainActivity extends Activity {

EditText mobileno,message;
Button sendsms;
@Override
protected void onCreate(Bundle savedInstanceState) {
super.onCreate(savedInstanceState);
setContentView(R.layout.activity_main);

mobileno=(EditText)findViewById(R.id.editText1);
message=(EditText)findViewById(R.id.editText2);
sendsms=(Button)findViewById(R.id.button1);

//Performing action on button click

sendsms.setOnClickListener(new OnClickListener() {

@Override
public void onClick(View arg0) {
String no=mobileno.getText().toString();
String msg=message.getText().toString();

//Getting intent and PendingIntent instance

Intent intent=new Intent(getApplicationContext(),MainActivity.class);

21
 PendingIntent pi=PendingIntent.getActivity(getApplicationContext(), 0,
intent,0);

//Get the SmsManager instance and call the sendTextMessage method to

send message
SmsManager sms=SmsManager.getDefault();
sms.sendTextMessage(no, null, msg, pi,null);

Toast.makeText(getApplicationContext(), "Message Sent successfully!",

Toast.LENGTH_LONG).show();
}
});
}

@Override
public boolean onCreateOptionsMenu(Menu menu) {
// Inflate the menu; this adds items to the action bar if it is present.
getMenuInflater().inflate(R.menu.activity_main, menu);
return true;
}

OTP Detection:

import android.content.BroadcastReceiver;
import android.content.Context;
import android.content.Intent;
import android.os.Bundle;

import com.google.android.gms.auth.api.phone.SmsRetriever;
import com.google.android.gms.common.api.CommonStatusCodes;
import com.google.android.gms.common.api.Status;

import java.util.regex.Matcher;
import java.util.regex.Pattern;

/**
* BroadcastReceiver to wait for SMS messages. This can be registered either
* in the AndroidManifest or at runtime. Should filter Intents on
* SmsRetriever.SMS_RETRIEVED_ACTION.
*/
public class MySMSBroadcastReceiver extends BroadcastReceiver {

22
 private OTPReceiveListener otpReceiveListener;

public MySMSBroadcastReceiver() {
}

public void init(OTPReceiveListener otpReceiveListener) {

this.otpReceiveListener = otpReceiveListener;
}

@Override
public void onReceive(Context context, Intent intent) {
if (SmsRetriever.SMS_RETRIEVED_ACTION.equals(intent.getAction())) {
Bundle extras = intent.getExtras();
if (extras != null) {
Status status = (Status) extras.get(SmsRetriever.EXTRA_STATUS);
if (status != null)
switch (status.getStatusCode()) {
case CommonStatusCodes.SUCCESS:
// Get SMS message contents
String message = (String)
extras.get(SmsRetriever.EXTRA_SMS_MESSAGE);
if (message != null) {
Pattern pattern = Pattern.compile("(\\d{4})");
// \d is for a digit
// {} is the number of digits here 4.
Matcher matcher = pattern.matcher(message);
String val = "";
if (matcher.find()) {
val = matcher.group(0); // 4 digit number
if (this.otpReceiveListener != null)
this.otpReceiveListener.onOTPReceived(val);
} else {
if (this.otpReceiveListener != null)
this.otpReceiveListener.onOTPReceived(null);
}
}
break;
case CommonStatusCodes.TIMEOUT:
if (this.otpReceiveListener != null)
this.otpReceiveListener.onOTPTimeOut();
break;
}

23
 }
}
}

interface OTPReceiveListener {
void onOTPReceived(String otp);

void onOTPTimeOut();
}
}

Colour Values:

<?xml version="1.0" encoding="utf-8"?>

<resources>
<color name="purple_200">#FFBB86FC</color>
<color name="purple_500">#FF6200EE</color>
<color name="purple_700">#FF3700B3</color>
<color name="teal_200">#FF03DAC5</color>
<color name="teal_700">#FF018786</color>
<color name="black">#FF000000</color>
<color name="white">#FFFFFFFF</color>
<color name="dark_gray">#1f1f1f</color>
<color name="gray">#373737</color>
<color name="light_gray">#d3d3d3</color>
</resources>

24
 Chapter 8
Implementation

This application is designed based on Kotlin and the application is designed use to
classify the messages received.
All messages are screened and are placed on the concerned categories. This helps for
a more user -friendly and reliable use case of the application.
SMSManager class manages operations like sending a text message, data message,
and multimedia messages (MMS). For sending a text message method
sendTextMessage() is used likewise for multimedia message
sendMultimediaMessage() and for data message sendDataMessage() method is used.
The details of each function are:
sendTextMessage():
sendTextMessage(String destinationAddress, String scAddress, String text,
PendingIntent sentIntent,PendingIntent deliveryIntent, long messageId)

sendDataMessage():
sendDataMessage(String destinationAddress, String scAddress, short
destinationPort, byte[] data,PendingIntent sentIntent, PendingIntent deliveryIntent)

sendMultimediaMessage():
sendMultimediaMessage(Context context, Uri contentUri, String locationUrl,
Bundle configOverrides, PendingIntent sentIntent

25
 Chapter 9
Sample output screenshots

9.1 SAMPLE XML SCREEN

9.2 SMS INTERFACES

26
9.3 SMS OTP DETECTION :

9.4 SMS TRANSACTION DETECTION :

27
9.5 SMS SPAM DETECTION :

28
 Chapter 10
Result
This project is widely use full in any organizations, colleges, banking,
companies,E-Commerce, Market News, Government & Public Utilities,
Logistics, Media & Entertainment, Travel & Tourism Industry etc. Alert your
customer/user about the new updates of organization/colleges. In Logistics it use
to send the shipping updates, invoices, bills, tracking detail web URLs and much
more via an SMS. Media & Entertainment it use to invite the audience to an
FM/TV show or ask the audience to vote for their favorite contestants in your
reality show. and it also used in Travel & Tourism Industry Become a travel
buddy of your customer by sending all the itineraries and travel routes via an
SMS to make their journey more hassle-free.

29
 Chapter 11
Conclusion

As there is increase in usage of text messaging day by day, the problem of SMS
spam is becoming more prevalent. Filtering SMS spam has been a major
problem in recent years. In this research work, we have used six different
machine learning algorithms such as decision tree, naive Bayes, random forest,
KNN, SVM, and AdaBoost in which ten features from the dataset are used.
There are 5574 tagged data in the sample, including 4827 messages belonging to
ham messages and 747 messages belonging to spam messages collected. With
accuracy of 99.9%, the random forest classification algorithm outperforms all
other classification algorithms. The accuracy may further be enhanced by using
hybrid soft computing models.

30
 Chapter 13
Refernces

1. K. Yadav, S. K. Saha, P. Kumaraguru, and R. Kumra,“Take control of your

smses: Designing an usable spam sms filtering system,” in 2012 IEEE 13th
InternationalConference on Mobile Data Management. IEEE, 2012, pp. 352–355.

2. S. J. Warade, P. A. Tijare, and S. N. Sawalkar, “An approach for sms

spam detection.”

3. A. Narayan and P. Saxena, “The curse of 140 characters: evaluating the efficacy
of sms spam detection on android,” in Proceedings of the Third ACM workshop
on Security and privacy in smartphones & mobile devices. ACM, 2013, pp. 33–
42.

4. A. S. Onashoga, O. O. Abayomi-Alli, A. S. Sodiya, and D. A. Ojo, “An adaptive

and collaborative server side sms spam filtering scheme using artificial immune
system,” Information Security Journal: A Global Perspective, vol. 24, no. 4-6,
pp. 133–145, 2015

5. L. Leung, "Unwillingness-to-communicate and college student's motives in SMS

mobile messaging," Telematics and Informatics, vol. 24, pp. 115-129, 2007.

6. Almeida, Tiago, José María Gómez Hidalgo, and Tiago Pasqualini Silva.
"Towards sms spam filtering: Results under a new dataset." (2013): 1-18.

7. Mujtaba, G., and M. Yasin. "SMS spam detection using simple message content
features." J. Basic Appl. Sci. Res 4 (2014): 275-279

31
8. Q. Sun, H. Qiao, and Z. Luo, “The feature updating algorithm for short
message content filtering,” Information Technology Journal, vol. 7, no. 5, pp. 790–
795, 2008.

9. I. Ahmed, D. Guan, and T. C. Chung, “Sms classification based on naïve

bayes classifier and apriori algorithm frequent itemset,” International Journal of
machine Learning and computing, vol. 4, no. 2, p. 183, 2014.

10. T. M. Mahmoud and A. M. Mahfouz, “Sms spam filtering technique based on

artificial immune system,” IJCSI International Journal of Computer Science Issues,
vol. 9, no. 1, pp. 589–597, 2012.

11. K. Yadav, P. Kumaraguru, A. Goyal, A. Gupta, and V. Naik, “Smsassassin:

crowdsourcing driven mobile-based system for sms spam filtering,” in Proceedings
of the 12th Workshop on Mobile Computing Systems and Applications. ACM, 2011,
pp. 1–6.

12. T. A. Almeida, J. M. G. Hidalgo, and A. Yamakami, “Contributions to the

study of sms spam filtering: new collection and results,” in Proceedings of the 11th
ACM symposium on Document engineering. ACM, 2011, pp. 259–262.

13. M. Poorshahsavari and O. Pourgalehdari, “Enhancing the rate of accuracy and

precision in spam filtering in farsi sms.”
14. Hidalgo JMG, Bringas GC, Sánz EP, García FC (2006) Content based SMS
spam filtering. In: ACM symposium on document engineering, pp 107–114. ACM.
https://doi.org/10.1145/116 6160.1166191

15. 3.A. A. Badawi, L. Hoang, C. F. Mun, K. Laine,

16. (2015). Wechat-free messaging& calling app [Online]. Available:

http://www.wechat.com/

17. (2015). Whatsapp web [Online]. Available: http://web.whatsapp. com/

18. T. Sto€ber, M. Frank, J. Schmitt, and I. Martinovic, “Who do you

19. sdsync you are?: Smartphone fingerprinting via application behav- iour,” in
Proc. 6th ACM Conf. Security Privacy Wireless Mobile Netw., 2013, pp. 7–12.

20. M. Conti, L. V. Mancini, R. Spolaor, and N. V. Verde, “Can’t you hear me

knocking: Identification of user actions on android apps via traffic analysis,” in Proc.
5th ACM Conf. Data Appl. Security Pri- vacy, 2015, pp. 297–304.
32
 Parthiban M A /Data Analytics and Artificial Intelligence 3(1) 2023, 129-135

Data Analytics and Artificial Intelligence

Vol: 3(1), 2023
REST Publisher; ISBN: 978-81-948459-4-2
Website: http://restpublisher.com/book-series/daai/
DOI: https://doi.org/10.46632/daai/3/1/22

Classifying Message Application Using Kotlin

*Parthiban M A, AnandKumar.Y, Raghul.S, Saran Sanjay.R, SivaKumar.P
Veltech high-tech Dr.Rangarajan Dr, Sakunthala Engineering College, Chennai, Tamil Nadu, India.
*Corresponding Author Email: [email protected]

Abstract: Over the past few years, short message service (SMS) usage has significantly increased. This service is
used to deliver text messages by billions of people. Service providers have launched a number of popular applications,
including mobile banking, summons checkpoints, SMS chat, and others. This chapter explores the numerous SMS
applications that are available to users and provides an outline of how this service isprovided. We examine the causes
of its success and the problems that need to be solved. We also look at upcoming trends and the difficulties that to
improve this service, certain obstacles must be overcome. This chapter should help you understand how SMS
applications work and what to expect from them going forwards given the improvements to current SMS and
technological advancement. We propose a privacy-preserving Naive Bayes classifier and apply it to the problem of
private text classification. In this setting, a party (Alice) holds a text message, while another party (Bob) holds a
classifier. At the end of the protocol, Alice will only learn the result of the classifier applied to her text input and Bob
learns nothing. Our solution is basedon Secure Multiparty Computation (SMC). Our Rust implementation provides
a fast and secure solution for the classification of unstructured text. Applying our solution to the case of spam detection
(the solution is generic, and can be used in any other scenario in which the Naive Bayes classifier can be employed),
we can classify an SMS as spam or ham in less than 340 ms in the case where the dictionary size of Bob’s model
includes all words (n 5200) and Alice’s SMS has at most m 160 unigrams. In the case with n 369 and m 8 (the
average of a spam SMS in the database), our solution takes only 21 ms.
Keywords: Android, Kotlin, Firebase, XML, Android App Studio.

1. INTRODUCTION
The most common and popular form of communication is the short message service (SMS). In many regions of the world,
the term "SMS" is used to refer to both user activity and all forms of short text messaging. It is being used as a platform for
online offerings, banking updates, agricultural information, and product advertising and promotion. SMS marketing, often
known as direct marketing, uses SMS technology. There are times when SMS marketing causes users to be disturbed. Spam
SMS is the term used to describe these SMSs. One or more unwanted, unsolicited messages are referred to as spam. sent or
posted to the users as part of a bigger group of messages with essentially the same content SMS spam serves commercial
and marketing reasons. disseminating inappropriate pornographic content and internet offers, as well as the marketing of
numerous items. Because of this, the global issue of spam SMS floods has gotten much worse. Because SMS communication
is becoming more and more popular, SMS spamming has surpassed previous spamming strategies like email and twitter.
Although email opens only 20 to 25 percent of the time within 24 hours of receipt, SMS opens more than 90% of the time
and within 15 minutes of reception. Consequently, there is a clear need for an effective SMS spam detection method.
Numerous studies have been done on spam detection methods for email, Twitter, the web, and social media. On the other
hand, very few studies on SMS spamdetection have been carried out. Detecting spam SMS ismore difficult than detecting
spam email. due to SMS's limited length, use of regional content and abbreviations, and lack of header information compared
to email We consider the scenario in which there are two parties: one possesses the private data to be classifiedand the other
party holds a private model used to classify such data. In such a scenario, the party holding the data (Alice) is interested
in obtaining the classification result of such data against a model held by a second party (Bob) so that, at the end of the
classification protocol, Alice knows solely the input data and the classification result, and Bob knows nothing beyond the
model itself. This scenario is a very relevant one. There are many situations where a data owner is not comfortable sharing
a piece of data that needs classification (think of psychological or health related data). Also,a machine learning model
holder might not want to/cannot reveal the model in the clear for intellectual property issues or because the model reveals
information about the data set used to train it. Thus, both parties have proper incentivesto participate in a protocol

Copyright@ REST Publisher 129

 Parthiban M A /Data Analytics and Artificial Intelligence 3(1) 2023, 129-135

providing the joint functionality of private classification. Due to these concerns, mechanisms such as Secure Mul- tiparty
Computation (MPC) [20], Differential Privacy (DP) and Homomorphic Encryption (HE) can be used to build privacy-
preserving solutions. MPC allows two or more parties to jointly compute a function over their private inputs without
revealing any information to the other party,whereas HE is an encryption scheme that allows per- forming computations
on encrypted data without having to decrypt it. And, DP is a technique that adds ran- dom noise to queries, toprevent an
adversary from learn- ing information about any particular individual in the data set.
Our main goal is to propose protocols for privacy-preserving text classification. By carefully selecting cryptographic engi-
neering optimizations, we improve upon previous results by Reich et al. [55] by over an order of magnitude achieving, to
the best of our knowledge, the fastest text-classification results in the available literature (21ms for an average sample of
our data set). More specifically, we propose a privacy- preserving Naive Bayes classification (PPNBC) based on MPCwhere
given atrained model we classify/predict an example without revealing any additional information to the parties other than
the classification result, which canbe revealed to one specified party or both parties. We then apply our solution to a text
classification problem: classifying SMSes as spamor ham.

2. LITERATURE SURVEY
SMS spam detection for Indian messages: The growth of the mobile phone users has led to adramatic increase in SMS
spam messages. Thoughin most parts of the world, mobile messaging channel is currently regarded as “clean” and trusted,
on the contrast recent reports clearly indicate that the volume of mobile phone spam is dramatically increasing year by
year. It is an evolving setback especially in the Middle East and Asia. SMS spam filtering is a comparatively recent errand
to dealsuch a problem. It inherits many concerns and quickfixes from Email spam filtering. However, it fronts its own
certain issues and problems. This paper inspires to work on the task of filtering mobile messages as Ham or Spam for the
Indian Users by adding Indian messages to the worldwide available SMS dataset. The paper analyses different machine
learning classifiers on large corpus of SMS messages for Indian people. Due to these concerns, mechanisms such as Secure
Mul- tiparty Computation (MPC) [20], Differential Privacy (DP) and Homomorphic Encryption (HE) can beused to
build privacy-preserving solutions. MPC allows two or more parties to jointly compute a function over their private
inputs without revealing any information to the other party, whereas HE is an encryption scheme that allows per- forming
computations on encrypted data without having to decrypt it. And, DP is a technique that adds ran- dom noise to
queries, to prevent an adversary from learn- ing information about any particular individual in the data set. SMS is one of
the most used telecommunication service in the world. It allows mobile phone users to send and receive a short text (which
has 160 7-bit characters maximum). Due to advantages such as reliability (since the message reaches the mobile phone
user), low cost to send an SMS (especially if bought in bulk), the possibility of personalizing, and immediate delivery,
SMS is a widely used communication medium for commercial purposes, and mobile phone users are flooded with
unsolicited advertising. SMSes are also used in scams, where someone triesto steal personal information, such as credit
card details, bank account information, or social security numbers. Usually, the scammer sends an SMS with a link that
invites a person to verify his/her accountdetails, make a payment, or that claims that he/she hasearned some amount of
money and needs to use the link to confirm. In all cases, such SMSes can be classified as spam. Machine learning
classifiers can be used to detect whether an SMS is a spam or not (ham). During the training phase, these algorithms learn
a model from a data set of labeled exam- ples, and later on, are used during the classification/prediction phase to classify
unseen SMS es. In a Naive Bayes classifier, the model is based on the frequency that each word occurs in the training
data set. In the classification phase, based on these frequencies, the model predicts whether an unseen SMS is spam or
not. A concern with this approach is related to Alice’s privacy since she needs to make her SMSes available to the spam
filtering service provider, Bob, whichowns the model. SMSes may contain sensitive information that the user would not
like to share with the service provider. Besides, the service provider also does not want to reveal what parametersthe
model uses (in Naive Bayes, the words and their frequencies) to spammers and concurrent service providers. Our privacy-
preserving Naive Bayes classification based on MPC, provides an extremely fast secure solution for both parties to clas-
sify SMSes as spam or ham without leaking any additional information while maintaining essentially the same accuracy
as the original algorithm performed in the clear. While our experimental treatment is focused on SMS messages, the same
approach can be naturally generalized to classify short messages received over Twitter or instant messengers such as
WhatsApp or Signal.among the best models to be used for a multiclass SMSclassification.
SMS Spam Detection using Machine Learning and Deep Learning Techniques
The number of people using mobile devices increasingday by day. SMS (short message service) is a text message service
available in smartphones as well as basic phones. So, the traffic of SMS increaseddrastically. The spam messages also
increased. The spammers try to send spam messages for theirfinancial or business benefits like market growth, lottery
ticket information, credit card information, etc. So, spam classification has special attention. In this paper, we applied various
machine learning and deep learning techniques for SMS spam detection. we useda dataset from UCI and build a spam

Copyright@ REST Publisher 130

 Parthiban M A /Data Analytics and Artificial Intelligence 3(1) 2023, 129-135

detection model. Our experimental results have shown that our LSTM model outperforms previous models in spam detection
with an accuracy of 98.5%. We used python for all implementations
SMS: The Short Message Service
Although it is a widely used communication mechanism for cell phone users, SMS is far more than just a technology for
teenage chat. SMS technology evolved out of the global system for mobile communications standard, an internationally
accepted cell phone network specification the European Telecommunications Standards Institute created. The 3rd
Generation Partnership Project maintains the SMS standard. SMS messages are handled via a short message service center
that the cellular provider maintains for the end devices. The SMSC can send SMS messages to the end device using a
maximum payload of 140 octets. This defines the upper bound of an SMS message to be 160 characters using 7-bit encoding.
It is possible to specify other schemes such as 8-bit or 16-bit encoding, which decreases the maximum message length to
140 and 70 characters, respectively.
Short Message Service (SMS) Spam Filtering using Machine Learning in Bahasa Indonesia
Short Message Service (SMS) is an essential communication tool in Indonesian society. Companies use SMS as a promotion
tool but unfortunately some individuals use SMS to send spam messages. A smartphone user in Indonesia has had an
experience with these spam and promotional messages. This studypresents a model to classify spam, promotion and ham
messages based on Indonesian text messages. The model was trained with 4,125 text messages, tested with 1,260 text
messages. A 10-fold cross validation method was used to evaluate the classifiers and the results show that Random Forest
(94.62%), Multinomial Logistic Regression (94.57%), SupportVector Machine (94.38%), and XGBoost (94.52%) are

Comparative Study of Machine LearningAlgorithms for SMS Spam Detection

The short message service (SMS) became popular after it was initially provided as a service in the second- generation (2G)
terrestrial mobile network architecture (Global System for Mobile Communication - GSM). Its popularity has been
exploited by some advertising companies and others to spread unwanted advertising, communicate advertising offers, and
send unwanted material to the end users. These undesirable messages, known as spam, make it difficult for the users to
receivethe desirable messages and make them frustration and irritation. Consequently, there are measures that various
experts have implemented in filtering out these spam messages and blocking them from reaching the end users. Most of
the solutions have followed the success of email spam filtering and utilized machine learning techniques to filter spam
messages. The popular machine learning techniques that have successfully been used include logistical regression, Naïve
Bayes algorithms, Support Vector Machine (SVM), and neuralnetworks. The present study adopts these techniques in
filtering spam messages and measures their accuracy to determine the most effective method of filtering spam messages.
Based on the findings, the neural network performs best as the trained classifier model used to classify incoming messages
as ham or spam
SMS spam detection and comparison ofvarious machine learning algorithm
Past few years have seen increase in the number of spam emails and messages. Legal, economic and technical measures
can be used to tackle spam sms's nowadays. A key role is being played by Bayesian filters in stopping this problem. In this
paper, we analyzed and studied the relative strengths of various machine learning algorithms in order to detect spam
messages which are sent on mobile devices. We have acquired the data from on open public dataset and prepared two
datasets for our testing and validation purposes. Accuracy in detecting spam messages was the first priority in ranking
these algorithms. Our resultsclearly demonstrate that different machine learning algorithms under different features tend
to perform differently in classifying spam messages.
3. EXISTING AND PROPOSED SYSTEM
India has one of the densest and prospective markets forcellular phones, and mobile service providers have a strict policy
about providing access to their customer bases. Many consumers activate “Do Not Disturb” services that disallow mass
publicity calls and messages. However, Bulk SMS service provider in Mumbai maintain databases of people who are
open to mass messages. This means that a company engaging in this kind of marketing can actually reach out to a target
audience more efficiently. Not all bulk SMSreseller providers have extensive resources however, and it is up to you to select
the right vendor. Bulk SMSs reach the target audience with greater efficiencythan television or print advertising because
they reach the client directly. A message on your phone is something that you can always refer to later; and it doesn’t go
ignored as marketing calls often do. On the other side of the playing field, a bulk SMS reseller provider can reach out to
thousands of people within a limited cost. While conventional advertising cannotguarantee the attention of your intended
target audience, bulk SMSs will allow you a deeper reach into the market without spending as much as you would when
be engaging in conventional marketing! Moreover, in this digital world, smartphones are the best partner. Without it, nobody
survives. Even the oldaged or illiterate people used to have smartphones and they try to read all messages. These people
never read email as they don’t have an email account. Hence, there may be no doubt that Bulk SMS service will assist you
to connect with your audiences better. Get your Bulk SMS service through us thousands of your audience at the same time.
It is believed that an SMS isopened within five minutes of its receipt, making it an effective mediumto attain out on your
target market.ies

Copyright@ REST Publisher 131

 Parthiban M A /Data Analytics and Artificial Intelligence 3(1) 2023, 129-135

4. PROPOSED SYSTEM
The proposed system used advanced methodologies to facilitate ease of use and makes the messages more filtered and
cleaner to view. The transactions from various apps (like gpay , phonepe , paytm etc) are arranged dynamically based on
the content they possess . Otp’s(One Time Passwords ) are automatically from the device after a specified amount of time
which makes it more secure and helps the comtribute to the free space on the device . Thesemessages are automatically
converted into modules based on a timed basis as all messages from a certain timeline are clubbed together enabling to view
it easier. Spam messages are automatically seperated from the other essential messages which makes it easier to identify
messages we dont actually need. These spam messages are also converted into seperated folders to make them to be deleted
easier.
5. TOOL DESCRIPTION
Android: Android is a mobile operating system based on a modified version of the Linux kernel and otheropen- source
software, designed primarily for touch screen mobile devices. Android is developed by a consortium of developers known
as the Open Handset Alliance and commercially sponsored by Google.
About android app:Android App is software designed to run on anAndroid device or emulator. The term also refers to an
APK file which stands for Android package. This file is a Zip archive containing app code, resources, and meta
information. Android apps can be written in Kotlin, Java, and C++ and are run inside Virtual Machine.
Kotlin the programming language: Kotlin is a cross-platform, statically typed, general- purpose programming language
with type inference. Kotlin is designed to interoperate fully with Java, and the JVM version of Kotlin's standard library
depends on the Java Class Library but type inference allows its syntax to be more concise. Kotlin mainly targets the
JVM, but also compiles to Java Script or native code via LLVM Language development costs are borne by
JetBrains, while the Kotlin Foundation protects the Kotlin trademark.
Google fire base: Firebase is a set of hosting services for any type of application (Android, iOS, Java script, Node.js, Java,
Unity, PHP, C++ ...). It offers NoSQL and real-time hosting of databases, content, social authentication (Google, Face
book, Twitter and Github), and notifications, or services, such as a real-time communication server. Firebase is a Backend-
as-a-Service (BaaS) app development platform that provides hosted backend services such as a realtime database, cloud
storage, authentication, crash reporting, .
Secure socket layer: SSL stands for secure sockets layer. Protocol for web browsers and servers that allows for the
authentication, encryption & decryption of data sent over the internet.\
Real time database: Fire Base is a Real time Data Base. Having a real- time database is the standout feature of the Firebase
framework. Firebase caters to a cloud-hosted database in which the data is stored as JSON and further synchronized
constantly to each associated client. Having a real-time database instance
Android: Android is a mobile operating system based on a modified version of the Linux kernel and other open- source
software, designed primarily fortouch screen mobile devices. Android is developed by a consortium of developers known
as the Open Handset Alliance and commercially sponsored by Google.
About android app: Android App is software designed to run on an Android device or emulator. The term also refers to
an APK file which stands for Android package. This file is a Zip archive containing app code, resources, and meta
information. Android apps canbe written in Kotlin, Java, and C++ and are run inside Virtual Machine.
Kotlin the programming language: Kotlin is a cross-platform, statically typed, general- purpose programming language
with type inference. Kotlin is designed to interoperate fully with Java, and the JVM version of Kotlin's standard library
depends on the Java Class Library but type inference allows its syntax to be more concise. Kotlin mainly targets the
JVM, but also compiles to Java Script or native code via LLVM Language development costs are borne by JetBrains,
while the Kotlin Foundation protects the Kotlin trademark.
Google fire base: Firebase is a set of hosting services for any type of application (Android, iOS, Java script, Node.js, Java,
Unity, PHP, C++ ...). It offers NoSQL and real-time hosting of databases, content, social authentication (Google, Face
book, Twitter and Github), and notifications, or services, such as a real-time communication server. Firebase is a Backend-
as-a-Service (BaaS) appdevelopment platform that provides hosted backend services such as a realtime database, cloud
storage, authentication, crash report
Secure socket layer: SSL stands for secure sockets layer. Protocol for web browsers and servers that allows for the
authentication, encryption & decryption of data sent over the internet.\
Real time database: Fire Base is a Real time Data Base. Having a real- time database is the standout feature of the Firebase
framework. Firebase caters to a cloud-hosted database in which the data is stored as JSON and further synchronized
constantly to each associated client. Having a real-time database instance that updates thecurrent data is essential for
modern applications.
XML: XML stands for eXtensible Mark-up Language, which is away of describing data using a text-baseddocument.
Because XML is extensible and very flexible, it's used for many different things, including defining the UI layout of
Android apps. Other resources like strings for your app arealso defined in an XML file called strings.xml. You describe

Copyright@ REST Publisher 132

 Parthiban M A /Data Analytics and Artificial Intelligence 3(1) 2023, 129-135

the view hierarchy of UI elements on the screen. For example, a Constraint Layout can contain Buttons, Text Views, Image
Views, or other views. Remember, Constraint Layout is a subclass of View Group. It allows you to position or size child
views in a flexible manner.
We can see there are three sections at top right corner
 Code
 Split
 Design
Code option allows us to view the entire code the working slide. Split is useful when we want to checkboth the code and
design side by side. Design is usedto view the design of the screen generated and allows us to make changes According
to that it will modify the code.
6. SYSTEM ARCHITECTURE

FIGURE 1.

Modules: The system is an App-based approach. We are goingto use Android App Studio which is a platform to make
Android Apps.
Android App Studio: Android Studio provides a unified environment where you can build apps for Android phones, tablets,
ndroid Wear, Android TV, and Android Auto. Structured code modules allow you to divide yourproject into units of
functionality that you can independently build, test, and debug. It provides Gradle-based build support. Android- specific
refactoring and quick fixes. Lint tools to catchperformance, usability, version compatibility and otherproblems. It contains
Templates to create Android designs and components. A rich layout editor that allows users to drag-and-drop components
even has Option to preview layouts on multiple screen configurations. It has Built-in support for Google Cloud Platform,
enabling integration with Firebase Cloud Messaging and Google App Engine. It even contains a Virtual Device (Emulator)
to run and debugapps in the Android studio.
Spam Filtering Process: A manually classified spam and ham messages are input or training set for a spam filtering
algorithm. Thealgorithm consists of the following steps Pre-processing: Removing irrelevant contents like stop words are
thepart of data preprocessing.
Tokenization: Segmenting the message according to words, characters or symbols called tokens. There are different
tokenization approaches such as word tokenization, sentence tokenization, word or character Ngrams and orthogonal sparse
bigrams.
Representation: Conversion to attribute value pairs. Selection: Selecting important attribute values which have impacton
classification rather than choosing all pairs of attribute value. Using the conditional probability, we can calculate the
probability of an event using its prior knowledge.
Training: Train the algorithm with the selected attribute values.Testing: Test the newly arrived data with the trainingmodel.
SMS Spam/Ham classifier using Naive Bayesalgorithm: Using the conditional probability, we can calculate the
probability of an event using its prior knowledge

Copyright@ REST Publisher 133

 Parthiban M A /Data Analytics and Artificial Intelligence 3(1) 2023, 129-135

OTP Detection: Privacy concerns have always been an issue for Android users. Before Android 6 Marshmallow devices,
accessing almost anything was possible fromuser's devices which makes users privacy violated andvulnerable. But since
Android released request application permission before actually using it made itsecure in some manners. Two of the major
dangerous level permissions i.e., SMS and Location permissions are most of the privacy concerning permissions. And now
it's almost impossible for new and old apps having these permissions to be published without having a verystrong use-case.
SMS / OTP detection requires SMS permissions from user. And its a common use case for apps to auto-detectOTP while
logging in through mobile verification. But since READ_SMS and RCEIVE_SMS are not so mucheasier to get published
on the play store, Google launched SMS Verification APIs which does the task in-place. Transaction Detection Transactional
Monitoring in today’s world is necessary to implement variable plans and tiers of services to our customer base. With
intelligent systems being put into place at every junction of the transactional process frompayment till the evaluation of end
numbers of purchases, we sought to find an intelligent source of digital data that can drive insight generation like no other
in the market. The transactional SMS’s from a whole lot of messagesare filtered out. Virtual passbook is created by applying
ML algorithmsto the messages. SMS transaction extractor solution applies its intelligence to categorize the messages into
various expense types across products & services, purchase patterns, and credit & insurance risks. Duplications are removed
and filtered out. If there are any incomplete values in the data, thenthey are filled.
7. RESULT
This project is widely use full in any organizations, colleges, banking, companies,E-Commerce, Market News, Government
& Public Utilities, Logistics, Media& Entertainment, Travel & Tourism Industry etc. Alert your customer/user about the
new updates of organization/colleges. In Logistics it use to send the shipping updates, invoices, bills, tracking detail web
URLs and much more via an SMS. Media & Entertainment it use to invite the audience to an FM/TVshow or ask the
audience to vote for their favorite contestants in your reality show. and it also used in Travel & Tourism Industry Become a
travel buddy of your customer by sending all the itineraries and travel routes via an SMS to make their journey more hassle-
free.
REFERENCES
[1]. S. Adams et al., “Privacy-preserving trainingof tree ensembles over continuous data,” Proc. Privacy Enhancing Technol., no.
2, 2022.
[2]. A. Agarwal et al., “Protecting privacy of users inbrain-computer interface applications,” IEEE Trans. Neural Syst. Rehabil.
Eng., vol. 27, no. 8,pp. 1546–1555, Aug. 2019.
[3]. N. Agrawal, A. S. Shamsabadi, M. J. Kusner, and A. Gascón, “QUO- TIENT: Two-party secure
[4]. neural network training and prediction,” in Proc.26th ACM SIGSAC Conf. Comput. Commun. Secur., L. Cavallaro,
[5]. K. Yadav, S. K. Saha, P. Kumaraguru, and R.Kumra,“Take control of your smses:
[6]. Designing an usable spam sms filtering system,”in 2012 IEEE 13th InternationalConference on Mobile Data Management.
IEEE, 2012, pp. 352–355.
[7]. J. Kinder, X. Wang, and J. Katz, Eds. New York,NY, USA: ACM Press, Nov. 2019, pp.
[8]. K. M. M. Aung, “PrivFT: Private and fast text classification with homomorphic encryption,” IEEE Access, vol. 8, pp. 226544–
226556, 2020.
[9]. S. J. Warade, P. A. Tijare, and S. N. Sawalkar,“An approach for sms spam detection.”
[10]. A. Narayan and P. Saxena, “The curse of 140 characters: evaluating the efficacy of sms spam detection on android,” in
Proceedings of the ThirdACM workshop on Security and privacy in smartphones & mobile devices. ACM, 2013, pp. 33–42.
[11]. A. S. Onashoga, O. O. Abayomi-Alli, A. S. Sodiya, and D. A. Ojo, “An adaptive and collaborative server side sms spam
filtering scheme using artificial immune system,” Information Security Journal: A Global Perspective, vol. 24, no. 4-6, pp.
133–145, 2015
[12]. 3.A. A. Badawi, L. Hoang, C. F. Mun, K. Laine, L. Leung, "Unwillingness-to-communicate and college

Copyright@ REST Publisher 134

 Parthiban M A /Data Analytics and Artificial Intelligence 3(1) 2023, 129-135

student's motives in SMS mobile messaging," Telematics and Informatics, vol. 24,pp. 115-129, 2007.
[13]. Almeida, Tiago, José María Gómez Hidalgo, andTiago Pasqualini Silva. "Towards sms spam filtering: Results under a new
dataset." (2013): 1-18.
[14]. Mujtaba, G., and M. Yasin. "SMS spam detectionusing simple message content features." J. Basic Appl. Sci. Res 4 (2014):
275-279
[15]. Q. Sun, H. Qiao, and Z. Luo, “The feature updating algorithm for short message content filtering,” Information Technology
Journal, vol. 7,no. 5, pp. 790– 795, 2008.
[16]. I. Ahmed, D. Guan, and T. C. Chung, “Sms classification based on naïve bayes classifier and apriori algorithm frequent
itemset,” InternationalJournal of machine Learning and computing, vol.4, no. 2, p. 183, 2014.
[17]. T. M. Mahmoud and A. M. Mahfouz, “Sms spamfiltering technique based on artificial immune system,” IJCSI International
Journal of ComputerScience Issues, vol. 9, no. 1, pp. 589–597, 2012.
[18]. K. Yadav, P. Kumaraguru, A. Goyal, A. Gupta, and V. Naik, “Smsassassin: crowdsourcing driven mobile-based system for
sms spam filtering,” in Proceedings of the 12th Workshop on Mobile Computing Systems and Applications. ACM, 2011,pp.
1–6.
[19]. T. A. Almeida, J. M. G. Hidalgo, and A. Yamakami, “Contributions to the study of sms spam filtering: new collection and
results,” in Proceedings of the 11th ACM symposium on Document engineering. ACM, 2011, pp. 259–262.
[20]. M. Poorshahsavari and O. Pourgalehdari, “Enhancing the rate of accuracy and precision inspam filtering in farsi sms.”
[21]. Hidalgo JMG, Bringas GC, Sánz EP, García FC (2006) Content based SMS spam filtering. In: ACM symposium on
document engineering, pp 107–114. ACM. https://doi.org/10.1145/116 6160.1166191
[22]. (2015). Wechat-free messaging& calling app[Online]. Available: http://www.wechat.com/
[23]. (2015). Whatsapp web [Online]. Available:http://web.whatsapp. com/
[24]. P. Haffner, S. Sen, O. Spatscheck, and D. Wang, “Acas: Automated construction of application signatures,” in Proc. ACM
SIGCOMM WorkshopMining Netw. Data, 2005, pp. 197–202.
[25]. T. Karagiannis, A. Broido, M. Faloutsos et al., “Transport layer identification of p2p traffic,” in Proc. 4th ACM SIGCOMM
Conf. Internet Meas.,2004, pp. 121–134.
[26]. S. Sen, O. Spatscheck, and D. Wang, “Accurate,scalable in- network identification of p2p trafficusing application signatures,”
in nProc. 13th Int.Conf. World Wide Webn, 2004, pp. 512–521.
[27]. K. P. Dyer, S. E. Coull, T. Ristenpart, and T. Shrimpton, “Peek- a-boo, i still see you: Why efficient traffic analysis counter-
measures fail,” inProc. IEEE Symp. Security Privacy, 2012, pp. 332–346.
[28]. T. Sto€ber, M. Frank, J. Schmitt, and I.Martinovic, “Who do you sync you are?: Smartphone fingerprinting via application
behav- iour,” in Proc. 6th ACM Conf. Security Privacy Wireless Mobile Netw., 2013, pp.7–12.
[29]. M. Conti, L. V. Mancini, R. Spolaor, and . V. Verde, “Can’t you hear me knocking: Identification of user actions on android
apps via traffic analysis,” in Proc. Data Appl. Security Pri-vacy, 2015, pp. 297–304.

Copyright@ REST Publisher 135