Reliability of ChatGPT in automated essay scoring for dental undergraduate examinations
This study shows the potential of ChatGPT for essay marking. However, an appropriate rubric design is essential for optimal reliability. With further validation, the ChatGPT has the potential to aid students in self-assessment or large-scale marking automated processes.
Authors
- Intekhab Islam (ORCID: https://orcid.org/0000-0002-7754-0609)
- Bernadette Quah (ORCID: https://orcid.org/0000-0002-5754-5517)
- Timothy Jie Han Sng (ORCID: https://orcid.org/0000-0003-4069-5153)
- Chee Weng Yong (ORCID: https://orcid.org/0000-0001-9905-1585)
- Lei Zheng
Institutions
- National University of Singapore (SG)
- National University Health System (SG)
Publication Details
- Journal
- BMC Medical Education
- Published
- 2024-09-03
- DOI
- https://doi.org/10.1186/s12909-024-05881-6
- Citations
- 45
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 5.41