Classification AI vs Human text

This Data Science project aims to classify text as either AI-generated or human-written. The dataset utilized in this project is sourced from Kaggle, comprising over 400,000 samples of both AI and human-generated text.

Libraries used

The project is implemented in Python 3.

• Matplotlib
• NLTK
• NumPy
• Optuna
• Pandas
• Gensim
• Scikit-learn
• WordCloud

To install the required libraries, run the following command:

pip install -r requirements.txt

Authors

This project was carried out as part of a university project with @tomasnp and @PierreDerathe.