ChatGPT’s Performance in Spreadsheets Modeling Assessments based on Revised Bloom’s Taxonomy

Abstract

ChatGPT has taken the education scene by storm and caused uneasiness among educators. Mixed reactions were observed with some institutions banning it, while others embracing it with caution. This paper evaluates the performance of ChatGPT on solving spreadsheets modeling assessment questions with multiple test items categorized according to the revised Bloom’s taxonomy, to discover the accuracy of the answers provided at each cognitive learning level. The insights obtained may be useful for educators to design future assessment questions which focus more on testing critical thinking skills to assess the students accordingly to achieve the intended learning outcomes, and we propose recommended actions on how to do so. Our proposed methodology can be applied to other course modules to achieve their respective insights for future assessment designs and actions.