Abstract
Purpose
The study explored how ChatGPT could transform examination writing in higher education. The research question was: How can the AI tool ChatGPT help transform examination writing in higher education? The study interviewed the chatbot (ChatGPT) by way of "prompt engineering" to test if it has the potential to achieve the following: (1) Generate varied questions on a subject matter of the same level of difficulty, (2) Generate varied questions on a subject matter with case scenarios, (3) Generate varied questions on a subject matter that requires critical thinking, (4) Generate varied questions on a subject matter that takes into consideration the diverse needs and backgrounds of students and (5) Streamline assessment process. These objective tests were to explore the diverse ways the chatbot could assist in the examination process. Despite the academic concerns surrounding students' use of ChatGPT, the study's findings seek to stimulate discussion on the potentially significant benefits ChatGPT offers to the educational sector if it is effectively implemented.
Approach/Design/Method
Through "prompt engineering", the study interviewed ChatGPT to test it on the five (5) objectives. Subject area lecturers and exam moderators reviewed questions as well as marking schemes generated by the chatbot to ensure accuracy and appropriateness.
Findings
ChatGPT was able to generate varied questions of the same difficulty level on the same given content and generated questions with case scenarios. The questions generated also required critical thinking; ChatGPT produced questions considering students' diverse needs and backgrounds. Finally, it could streamline the assessment process as well. However, ChatGPT required specific human guidance to shape the questions. Also, the examiner or the educator needed to double-check the accuracy of the questions generated. Additionally, it was discovered that the version of ChatGPT used was limited in subject areas that required graphics and figures.
Research Limitations/Implications
The study found that ChatGPT is effective with text-like tasks but is limited in areas that require graphics and figures (for the version used), which may be needed in some fields of study. It also meant that responses only had to be in text for the Chatbot to award scores based on the assessment criteria. Notwithstanding the limitations, ChatGPT can become an excellent tool for assisting educators in assessing students, thereby transforming examination writing in higher education.
The originality of the study
Research on ChatGPT is an emerging one. The study is novel, as this area is still being explored. This paper will serve as one of the early research works that provide educators and policymakers with knowledge of leveraging ChatGPT to transform examination writing.