This repository contains code for CSC522 Final Project This project aims to detect if a text is generated by AI or Humans. The implementation is divided into four parts: a) English language analysis b) Text summarization model c) Compute similarity between the generated summaries d) Text classification model
The getData file downloads the datasets.
All summarized data, dataset upon removal of difficult words and exploratory data analysis can be found here: https://drive.google.com/drive/folders/15KriEbCAnXOhhyp0A8LkNM7_rmKbjilM?usp=sharing