TWEETPHISH AI

Advanced Threat Detection System

FOR RESEARCHERS & DEVELOPERS

Get Tweet Data for Analysis

Learn how to obtain Twitter/X data for sentiment analysis and threat detection research

Option 1: X.com Developer API
Get live tweet streams directly from Twitter/X

Access real-time tweet data using the official X (Twitter) Developer API. This is the most reliable method for obtaining live tweet streams for analysis.

Steps:

  1. Sign up for X Developer Account at developer.twitter.com
  2. Create a new app and generate API credentials
  3. Choose your access tier (Basic: $100/month, Pro: $5,000/month)
  4. Use the API to search tweets, get user timelines, or stream real-time data
  5. Export data in JSON or CSV format for analysis
Option 2: Clone GitHub Repository
Self-host and analyze your own tweet datasets

Clone the TweetPhish AI repository and run it locally. Upload your own tweet datasets in JSON or CSV format for sentiment analysis and threat detection.

Quick Start:

# Clone the repository
git clone https://github.com/nilesh1013/tweetphish-ai.git

# Install dependencies
cd tweetphish-ai
pnpm install

# Set up database and run
pnpm db:push
pnpm dev

Upload Your Dataset:

Place your tweet dataset (JSON/CSV) in the project directory and run the import script:

pnpm exec tsx scripts/import-large.mjs
Option 3: Public Datasets
Use existing research datasets for analysis

Access publicly available Twitter datasets from research repositories and academic sources.

Kaggle Datasets

Twitter spam, phishing, and sentiment analysis datasets

GitHub Datasets

Community-contributed tweet collections and research data

Research Paper
Read the original research behind this project

This project is based on published research on real-time phishing detection in tweets. Read the full paper for methodology and technical details.

Questions or need help? Contact me at [email protected]