Group Members: Khai Davis, Phalgun Kasu, Gabrielle Kuruvilla, Justin Lai
The project focuses on training and evaluating text classification models to identify human-written and AI-generated text. In an era dominated by AI language models like ChatGPT and BARD, distinguishing between human and machine-generated content has become increasingly important for various applications, including content moderation, plagiarism detection, and ensuring the integrity of online information. The project aims to address this challenge by leveraging machine learning techniques to develop robust and accurate classification models. By experimenting with a diverse range of models, including Logistic Regression, SVM, RNN, LSTM, and GPT, the project aims to explore the strengths and limitations of different approaches in classifying text across multiple genres, such as essays, poetry, and Wikipedia article introductions. Through comprehensive evaluation and analysis, the project aims to provide insights into the performance, scalability, and computational efficiency of these models, ultimately contributing to advancements in the field of natural language processing and text classification.