chatgptscrapeR: A Tool for Retrieving Student-AI Interactions

Abstract

The rapid adoption of ChatGPT and other large language models (LLMs) in education has created new opportunities for human-AI collaboration research, e.g., studying interactions, automating support or implementing novel ways of assessment. However, existing methods for retrieving ChatGPT conversation data -either through OpenAI’s API or manual transcription-are limited by technical, financial, and scalability constraints. This paper introduces chatGPTscrapeR, an open-source R package and Shiny web application that automates the extraction of ChatGPT conversation data from URLs. Thus, it enables researchers and educators to efficiently retrieve, organize, and subsequently analyze interaction logs, and their metadata. The retrieved data are ready to be assessed if they are part of an assignment or analyzed using different methods. In all such cases, automating the retrieval of human-AI interactions is instrumental for an efficient analysis of such interactions and for creating modern AI-enabled learning systems. © 2025 IEEE.