Summary of Analyzing Chat Protocols Of Novice Programmers Solving Introductory Programming Tasks with Chatgpt, by Andreas Scholl et al.
Analyzing Chat Protocols of Novice Programmers Solving Introductory Programming Tasks with ChatGPT
by Andreas Scholl, Daniel Schiffner, Natalie Kiesler
First submitted to arxiv on: 29 May 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This research paper investigates how introductory programming students interact with Large Language Models (LLMs) like ChatGPT-3.5, specifically focusing on their conversations and use patterns. In a German university’s introductory course, 213 students were tasked with solving programming exercises with ChatGPT’s assistance. The resulting data consists of 2335 chat protocols, which were analyzed regarding prompts, frequencies, progress, content, and other usage patterns. The study reveals diverse interactions, both supportive and concerning, providing insights to inform and align teaching practices for future introductory programming courses. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research paper looks at how students in a programming course use special language tools like ChatGPT-3.5. In this study, 213 students did exercises with the help of ChatGPT as part of their classwork. They shared their conversations (2335 prompts) so that researchers could analyze what they were doing and why. The results show that students have different ways of interacting with these tools, both helpful and worrying. This information can help teachers prepare for future programming classes. |
