DR. B. C.

ROY ENGINEERING COLLEGE

SYNOPSIS
On
“EMAIL/SMS SPAM CLASSIFIER SYSTEM”
of Minor Project and viva-voce (MCAN-381) submitted in fulfilment of the requirements
for the degree of Master of Computer Application

UNDER GUIDANCE OF
UDAY KUMAR BANERJEE SIR
(Asst. prof. of MCA dept., BCREC)

SUBMITTED BY
RAJDEEP CHAKRABORTY (12071023030)
ANANTA SUTRADHAR (12071023003)
SUVAM ASH (12071023050)

2024-25
ABSTRACT:
In the digital age, unsolicited and unwanted messages, commonly known as spam, have
become a significant nuisance, affecting both personal and professional communication.
This paper presents a machine learning-based spam classifier system designed to
accurately distinguish between spam and legitimate messages. The proposed system
leverages natural language processing (NLP) techniques and various machine learning
algorithms, including Naive Bayes, Support Vector Machines (SVM), and Random Forest,
to analyze and classify text data. The classifier is trained on a comprehensive dataset
comprising thousands of labeled messages, ensuring robust performance across diverse
spam types. Key features of the system include text preprocessing, feature extraction,
and model training and evaluation. Experimental results demonstrate high accuracy,
precision, and recall, highlighting the system’s effectiveness in mitigating spam-related
issues. This spam classifier system offers a scalable and efficient solution for enhancing
communication security and user experience.

INTRODUCTION:
In today’s interconnected world, email and messaging platforms are essential tools for
communication. However, the proliferation of spam messages poses a significant
challenge, disrupting user experience and potentially leading to security risks. Spam
messages, often unsolicited and irrelevant, can clutter inboxes, waste time, and even
carry malicious content. To address this issue, we propose a robust spam classifier
system that leverages advanced machine learning techniques to accurately identify and
filter out spam messages.
The spam classifier system utilizes natural language processing (NLP) to analyze the
content of messages and extract meaningful features. By employing a combination of
machine learning algorithms such as Naive Bayes, Support Vector Machines (SVM), and
Random Forest, the system is trained to distinguish between legitimate and spam
messages with high accuracy. The classifier is built on a comprehensive dataset of
labeled messages, ensuring its ability to handle various types of spam, from
promotional content to phishing attempts.
This system not only enhances the efficiency of communication by reducing the volume
of spam but also improves security by preventing potential threats from reaching users.
Through rigorous testing and evaluation, the spam classifier demonstrates its
effectiveness in maintaining a clean and safe messaging environment. The following
sections will delve into the system’s architecture, implementation details, and
performance metrics, providing a comprehensive overview of its capabilities and
benefits.
STEPS OF EMAIL/SMS SPAM CLASSIFIER SYSTEM:
1. Email/SMS selection
2. Email/SMS processing
3. Analysing the Email/SMS
4. Classifying the Email/SMS

Technology Used: AI-ML

Hardware Required:
Processor: Intel core i3 or above
RAM: Minimum 225 MB or more
Hard Disk: Minimum 2 GB space
Input Device: keyboard
Output Device: screen of a mobile,laptop

Software Required:
Operating System: Windows or Linux
Anaconda: 3.5
Python: 3.11
IDE: Jupiter Notebook
Data Set: .csv File
Backend: Collection of Email/SMS stored in directory
OBJECTIVE:
The primary objective of the spam classifier system is to develop an efficient and
accurate machine learning model capable of distinguishing between spam and
legitimate messages. This system aims to enhance user experience by significantly
reducing the volume of unsolicited and potentially harmful messages in email and SMS
communications. By leveraging advanced natural language processing (NLP) techniques
and robust machine learning algorithms, the system seeks to achieve high precision and
recall rates, ensuring minimal false positives and false negatives. Ultimately, the spam
classifier system aspires to provide a scalable and reliable solution that improves
communication security and efficiency for users across various platforms.

Team Members:
Rajdeep Chakraborty 12071023030……………………………..
Ananta Sutradhar 12071023003……………………………..
Suvam Ash 12071023050………………………………

PROJECT GUIDE:
UDAY KUMAR BANERJEE SIR……………………………………….
(Asst. prof. of MCA dept., BCREC)