Apppublic

SerialGuy/ai-vs-human

sourceHugging Faceupdated 1y agoView on Hugging Face

4likes

App README

🧠 AI vs Human Text Detector

This project is a machine learning-based system designed to distinguish between text written by a human and that generated by an AI language model (e.g., ChatGPT). It uses deep learning and text embeddings to analyze writing patterns and classify them accurately.

📌 Features

—✅ Binary classification: AI-generated vs Human-written text
—📈 Achieved 92% accuracy and 0.89 F1-Score
—🔍 Embedding + Deep Learning model
—📊 Evaluation on real-world prompts and datasets
—🧪 Trained and tested using clean, balanced samples

🚀 Live Demo

🔗 [Try it on Hugging Face Spaces](https://huggingface.co/spaces/SerialGuy/ai-vs-human)

Enter a piece of text and the model will predict whether it's written by an AI or a human.

📂 Repository Structure

bash

.
├── train_model.ipynb      # Notebook to preprocess and train the model
├── requirements.txt       # (Optional) Dependencies
└── README.md              # Project overview and instructions