chatGPT for generating questions and assessments based on accreditations
This addresses the problem of creating standardized assessments for academic programs under multiple accreditations, such as in Saudi Arabia, though it is incremental in applying AI to a specific educational domain.
The research tackled generating accreditation-compliant student assessments using generative AI, introducing a method to map verbs for question creation and validating it with faculty questionnaires, achieving 85% approval for generating complete exam questions and 98% for editing existing ones.
This research aims to take advantage of artificial intelligence techniques in producing students assessment that is compatible with the different academic accreditations of the same program. The possibility of using generative artificial intelligence technology was studied to produce an academic accreditation compliant test the National Center for Academic Accreditation of Kingdom of Saudi Arabia and Accreditation Board for Engineering and Technology. A novel method was introduced to map the verbs used to create the questions introduced in the tests. The method allows a possibility of using the generative artificial intelligence technology to produce and check the validity of questions that measure educational outcomes. A questionnaire was distributed to ensure that the use of generative artificial intelligence to create exam questions is acceptable by the faculty members, as well as to ask about the acceptance of assistance in validating questions submitted by faculty members and amending them in accordance with academic accreditations. The questionnaire was distributed to faculty members of different majors in the Kingdom of Saudi Arabias universities. one hundred twenty responses obtained with eight five percentile approval percentage for generate complete exam questions by generative artificial intelligence . Whereas ninety eight percentage was the approval percentage for editing and improving already existed questions.