Can ChatGPT Support Prospective Teachers in Physics Task Development?

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
Read More Add to Saved list
  • Author(s): Stefan Küchemann (ORCID Stefan Küchemann (ORCID 0000-0003-2729-1592); Steffen Steinert (ORCID Steffen Steinert (ORCID 0000-0001-6364-934X); Natalia Revenga; Matthias Schweinberger (ORCID Matthias Schweinberger (ORCID 0009-0001-3006-7818); Yavuz Dinc; Karina E. Avila (ORCID Karina E. Avila (ORCID 0000-0002-2087-3592); Jochen Kuhn (ORCID Jochen Kuhn (ORCID 0000-0002-6985-3218)
  • Language:
    English
  • Source:
    Physical Review Physics Education Research. 2023 19(2).
  • Publication Date:
    2023
  • Document Type:
    Journal Articles
    Reports - Research
  • Additional Information
    • Availability:
      American Physical Society. One Physics Ellipse 4th Floor, College Park, MD 20740-3844. Tel: 301-209-3200; Fax: 301-209-0865; e-mail: [email protected]; Web site: https://journals.aps.org/prper/
    • Peer Reviewed:
      Y
    • Source:
      14
    • Education Level:
      Grade 10
      High Schools
      Secondary Education
      Higher Education
      Postsecondary Education
    • Subject Terms:
      Artificial Intelligence; Natural Language Processing; Man Machine Systems; Physics; Science Education; Science Teachers; Teaching Methods; Grade 10; High School Students; Mechanics (Physics); Technology Uses in Education; Science Instruction; Student Attitudes; Foreign Countries; Science Curriculum; Preservice Teachers; Undergraduate Students; Graduate Students
    • Subject Terms:
      Germany
    • Accession Number:
      10.1103/PhysRevPhysEducRes.19.020128
    • ISSN:
      2469-9896
    • Abstract:
      The recent advancement of large language models presents numerous opportunities for teaching and learning. Despite widespread public debate regarding the use of large language models, empirical research on their opportunities and risks in education remains limited. In this work, we demonstrate the qualities and shortcomings of using ChatGPT 3.5 for physics task development by prospective teachers. In a randomized controlled trial, 26 prospective physics teacher students were divided into two groups: the first group used ChatGPT 3.5 to develop text-based physics tasks for four different concepts in the field of kinematics for 10th-grade high school students, while the second group used a classical textbook to create tasks for the same concepts and target group. The results indicate no difference in task correctness, but students using the textbook achieved a higher clarity and more frequently embedded their questions in a meaningful context. Both groups adapted the level of task difficulty easily to the target group but struggled strongly with sufficient task specificity, i.e., relevant information to solve the tasks was missing. Students using ChatGPT for problem posing rated high system usability but experienced difficulties with output quality. These results provide insights into the opportunities and pitfalls of using large language models in education.
    • Abstract:
      As Provided
    • Publication Date:
      2024
    • Accession Number:
      EJ1409494