Hello there!

This repo contains the code and datasets utilized for my CS109 Project: Analyzing Keyword Indicators of LLM-Generated Content in Online Niche Communities.

A brief overview of the repo: The py files are all of the code utilized in this repo. They produced each of the json and csv files, which are primarily stored in the repo for reference and manipulation for anyone who does not want to, or can not, run the LLM generation and scraping functions. The file main.py brings everything together and runs essentially every other function.

More information about the files, and the project at large, can be found at: https://github.com/MatthewMattei/109-project/blob/main/MatthewMatteiCS109WriteUp.pdf