roberta-spam Open-source Text Classification Model - Accurately Identify Spam Emails/Messages with Nearly 99% Accuracy

Roberta Spam

Developed by mshenoda

A text classification model fine-tuned on RoBERTa, specifically designed to identify spam emails/messages with an accuracy of 99.06%

Text Classification

Transformers

EnglishOpen Source License:MIT #High-precision spam detection #Multi-source dataset fusion #Financial-grade security protection

Downloads 38.82k

Release Time : 6/4/2023

Model Overview

This model efficiently identifies and filters spam, establishing a security barrier for organizations to prevent potential financial losses, legal risks, and reputational damage.

Model Features

High-accuracy detection

Achieves 99.06% accuracy and 99.71% precision on test datasets

Multi-source dataset training

Incorporates labeled data from three sources: SMS, Telegram, and Enron Corporation

Industrial-grade application

Specifically designed to protect organizations from security threats posed by spam emails

Model Capabilities

Spam email identification

Text classification

Malicious content filtering

Use Cases

Enterprise security

Email system protection

Integrated into corporate email systems to automatically filter spam

Reduces spam email reception by over 99%

Customer service systems

Automatically identifies and blocks spam in customer service channels

Reduces time costs for customer service personnel handling invalid messages

Personal applications

Mobile SMS filtering

Used on mobile devices to identify and block spam messages

Effectively screens out scam and advertisement messages

🚀 RoBERTa based Spam Message Detection

Spam messages often contain malicious links or phishing attempts, posing significant threats to both organizations and their users. Our RoBERTa-based spam message detection system can effectively enhance an organization's security infrastructure.

🚀 Quick Start

Spam messages frequently carry malicious links or phishing attempts posing significant threats to both organizations and their users. By choosing our RoBERTa-based spam message detection system, organizations can greatly enhance their security infrastructure. Our system effectively detects and filters out spam messages, adding an extra layer of security that safeguards organizations against potential financial losses, legal consequences, and reputational harm.

✨ Features

Found this model useful:

Your feedback is important and would help keep this relevant.

📚 Documentation

Metrics

Loss	Accuracy(0.9906)	Precision(0.9971) / Recall(0.9934)	Confusion Matrix
Train / Validation	Validation	Validation	Testing Set

Model Output

0 is ham
1 is spam

Dataset

The dataset used for this model can be found at https://huggingface.co/datasets/mshenoda/spam-messages. It is composed of messages labeled as ham or spam, merged from three data sources:

SMS Spam Collection https://www.kaggle.com/datasets/uciml/sms-spam-collection-dataset
Telegram Spam Ham https://huggingface.co/datasets/thehamkercat/telegram-spam-ham/tree/main
Enron Spam: https://huggingface.co/datasets/SetFit/enron_spam/tree/main (only used message column and labels)

The prepare script for enron is available at https://github.com/mshenoda/roberta-spam/tree/main/data/enron. The data is split 80% for training, 10% for validation, and 10% for testing. The scripts used to split and merge the three data sources are available at: https://github.com/mshenoda/roberta-spam/tree/main/data/utils.

Dataset Class Distribution

Training 80%	Validation 10%	Testing 10%
Class Distribution	Class Distribution	Class Distribution

Architecture

The model is a fine-tuned RoBERTa.

roberta-base: https://huggingface.co/roberta-base
paper: https://arxiv.org/abs/1907.11692

Code

The code for this project can be found at https://github.com/mshenoda/roberta-spam.

📄 License

This project is licensed under the MIT license.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご