kth.sePublikationer
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Kattis vs ChatGPT: Assessment and Evaluation of Programming Tasks in the Age of Artificial Intelligence
KTH, Skolan för elektroteknik och datavetenskap (EECS), Människocentrerad teknologi, Medieteknik och interaktionsdesign, MID.ORCID-id: 0009-0005-3260-6036
KTH, Skolan för elektroteknik och datavetenskap (EECS), Människocentrerad teknologi, Medieteknik och interaktionsdesign, MID.ORCID-id: 0009-0005-9000-2951
Utrecht University Hekla, Netherlands.
KTH, Skolan för elektroteknik och datavetenskap (EECS), Människocentrerad teknologi, Medieteknik och interaktionsdesign, MID.ORCID-id: 0000-0002-8543-3774
2024 (Engelska)Ingår i: LAK 2024 Conference Proceedings - 14th International Conference on Learning Analytics and Knowledge, Association for Computing Machinery (ACM) , 2024, s. 821-827Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

AI-powered education technologies can support students and teachers in computer science education. However, with the recent developments in generative AI, and especially the increasingly emerging popularity of ChatGPT, the effectiveness of using large language models for solving programming tasks has been underexplored. The present study examines ChatGPT's ability to generate code solutions at different difficulty levels for introductory programming courses. We conducted an experiment where ChatGPT was tested on 127 randomly selected programming problems provided by Kattis, an automatic software grading tool for computer science programs, often used in higher education. The results showed that ChatGPT independently could solve 19 out of 127 programming tasks generated and assessed by Kattis. Further, ChatGPT was found to be able to generate accurate code solutions for simple problems but encountered difficulties with more complex programming tasks. The results contribute to the ongoing debate on the utility of AI-powered tools in programming education.

Ort, förlag, år, upplaga, sidor
Association for Computing Machinery (ACM) , 2024. s. 821-827
Nyckelord [en]
Academic Integrity, Automated Grading, ChatGPT, Programming Education
Nationell ämneskategori
Utbildningsvetenskap
Identifikatorer
URN: urn:nbn:se:kth:diva-344554DOI: 10.1145/3636555.3636882Scopus ID: 2-s2.0-85187550433OAI: oai:DiVA.org:kth-344554DiVA, id: diva2:1845942
Konferens
14th International Conference on Learning Analytics and Knowledge, LAK 2024, Kyoto, Japan, Mar 18 2024 - Mar 22 2024
Anmärkning

QC 20240321

 Part of ISBN 9798400716188

Tillgänglig från: 2024-03-20 Skapad: 2024-03-20 Senast uppdaterad: 2024-03-21Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltextScopus

Person

Dunder, NoraViberg, Olga

Sök vidare i DiVA

Av författaren/redaktören
Dunder, NoraLundborg, SagaViberg, Olga
Av organisationen
Medieteknik och interaktionsdesign, MID
Utbildningsvetenskap

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetricpoäng

doi
urn-nbn
Totalt: 46 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf