Logo des Repositoriums
 

Analyzing Chat Protocols of Novice Programmers Solving Introductory Programming Tasks with ChatGPT

Kurzanzeige
dc.contributor.authorScholl, Andreas
dc.contributor.authorSchiffner, Daniel
dc.contributor.authorKiesler, Natalie
dc.contributor.editorSchulz, Sandra
dc.contributor.editorKiesler, Natalie
dc.date.accessioned2024-09-03T16:26:20Z
dc.date.available2024-09-03T16:26:20Z
dc.date.issued2024
dc.description.abstractLarge Language Models (LLMs) have taken the world by storm, and students are assumed to use related tools at a great scale. In this research paper we aim to gain an understanding of how introductory programming students chat with LLMs and related tools, e.g., ChatGPT-3.5. To address this goal, computing students at a large German university were motivated to solve programming exercises with the assistance of ChatGPT as part of their weekly introductory course exercises. Then students (n=213) submitted their chat protocols (with 2335 prompts in sum) as data basis for this analysis. The data was analyzed w.r.t. the prompts, frequencies, the chats’ progress, contents, and other use pattern, which revealed a great variety of interactions, both potentially supportive and concerning. Learning about students’ interactions with ChatGPT will help inform and align teaching practices and instructions for future introductory programming courses in higher education.en
dc.identifier.doi10.18420/delfi2024_05
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/44534
dc.language.isoen
dc.pubPlaceBonn
dc.publisherGesellschaft für Informatik e.V.
dc.relation.ispartofProceedings of DELFI 2024
dc.relation.ispartofseriesDELFI
dc.subjectChatGPT-3.5
dc.subjectlarge language models
dc.subjectstudents
dc.subjectinteraction pattern
dc.subjectapplication
dc.subjectchat protocols
dc.subjectintroductory programming
dc.subjecthigher education
dc.titleAnalyzing Chat Protocols of Novice Programmers Solving Introductory Programming Tasks with ChatGPTen
dc.typeText/Conference paper
mci.conference.date09.-11. September 2024
mci.conference.locationFulda
mci.conference.sessiontitleBest Paper Kandidaten Langbeiträge
mci.document.qualitydigidoc
mci.reference.pages63-79

Dateien

Originalbündel
1 - 1 von 1
Vorschaubild nicht verfügbar
Name:
Andreas-Scholl.pdf
Größe:
537.11 KB
Format:
Adobe Portable Document Format
Herunterladen

Sammlungen

P356 - DELFI 2024 - Die 22. Fachtagung Bildungstechnologien