Scribd
Upload
10 views13 pages

Group Project

The document outlines the development of an Intelligent Spam Classifier using machine learning to detect and filter spam in communications such as emails, SMS, and calls. It details the project's objectives, system design, methodology, and future enhancements, emphasizing the need for automation in spam detection for improved accuracy and user experience. The classifier employs algorithms like Naive Bayes and Random Forest, and features a user-friendly web interface built with Flask.

Uploaded by

chinthakesava9
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
10 views13 pages

Group Project

The document outlines the development of an Intelligent Spam Classifier using machine learning to detect and filter spam in communications such as emails, SMS, and calls. It details the project's objectives, system design, methodology, and future enhancements, emphasizing the need for automation in spam detection for improved accuracy and user experience. The classifier employs algorithms like Naive Bayes and Random Forest, and features a user-friendly web interface built with Flask.

Uploaded by

chinthakesava9
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 13

Intelligent Spam Classifier

Using Machine Learning for Spam Detection

Presented by : Batch 17
Guide - Kada Sudha Gayathri (21A31A1213)
Mrs.T Ganga Bhavani B.Tech.,M.Tech.,(Ph.D.) Akhil Bolle (21A31A1235)
Assistant Professor, HoD-CS Mohammad Abdul Samad (21A31A1250)
Sai Keerthika Kadiyala (21A31A1226)
CONTENTS :
Introduction
Project Objective
Functional & Non-Functional Requirements
System Design
Existing System
UML Diagrams
Methodology
User Interface
Future Scope
Conclusion
Introduction

Definition of Spam: Unwanted, unsolicited messages sent via Calls, Mails and
SMS.
Importance: Protects users from fraud, phishing, and unwanted
advertisements.
Need for Automation: Manual filtering is inefficient; machine learning
enhances accuracy.
Project Objective

Develop a classifier that detects and


filters spam in Mails, SMS, and Calls.
Use machine learning algorithms to
improve detection accuracy.
Provide a user-friendly web interface
for classification.
Functional & Non-Functional Requirements
Functional:
Users can input SMS, Mail, or Call logs for analysis.
The system classifies messages as spam or non-spam.
Displays results with confidence scores.
Non-Functional:
High accuracy and efficiency in spam detection.
Secure data processing and storage.
User-friendly web interface.
System Design

Architecture Overview: Workflow:


Frontend: Flask-based web application. User submits text (SMS/Mail/Call log)
Backend: Python-based ML model for Preprocessing and feature extraction
classification. Model prediction
Database: SQLite for storing user queries and Results displayed on the web interface
classification results.
Existing System
1. Rule-Based Spam Filters
2. Blacklist & Whitelist-Based Filters
3. Statistical & Machine Learning-Based Spam Detection
4. AI-Powered Spam Filters
5. Network-Based Spam Filtering
UML Daigrams

Input Data Start

User Input Data


Preprocess Data

Preprocessing
Clasiffy Data
ML Model Clasifier
User
System
Display Result
Display Result

Stores feedback Store Data

Use Case Diagram Activity Diagram


Methodology
Machine Learning Model
Algorithms Used:
Naive Bayes (for SMS and emails).
Random Forest (for call classification).
Implementation
Steps in Execution:
User enters input data.
Model processes and classifies the message.
Display results and allow feedback (optional).
Code Implementation:
Python (NLTK, Scikit-learn, Pandas).
Flask for web integration.
User Interface
The UI will be designed for simplicity and efficiency, allowing
users to classify SMS, emails, and calls as spam or not spam.
Built using Flask (Backend) + HTML/CSS (Frontend) for an
interactive experience.
Future Scope
Support for multiple languages.
Integration with messaging platforms like WhatsApp and
Telegram.
Extending the system to detect multimedia spam like Audio,
Video, and Images etc
Mobile App Integration.
Adaptive Learning with User Feedback.
Conclusion
Summary of the spam classification approach.
Key takeaways: Spam filtering is essential for security and efficiency.
Future improvements to make the system more robust.
Thank you

You might also like