Answers are grounded in this paper and cite their sources.
Background: Multiple-choice questions (MCQs) are widely used in educational evaluation; nonetheless, their effectiveness depends widely on object quality and psychometric properties. Traditional item analysis methods are typically applied after exam administration, reducing the ability to detect problematic items during the test development phase. Objective: This research suggests a hybrid framework that combines AI-based pre-assessment with traditional post-test psychometric analysis to validate Arabic MCQs before and after exam administration. Methods: The suggested framework uses ChatGPT-4 to conduct a pre-assessment of MCQ items by estimating item difficulty, discrimination potential, and distractor effectiveness based on linguistic and semantic properties. Traditional psychometric analysis was then performed using actual learner response data collected from 195 individuals to compute item difficulty, discrimination indices, reliability estimates, and distractor effectiveness. Results: A moderate positive correlation was observed between AI-based predictions and traditional psychometric results (r = 0.42, p<0.05). The AI model demonstrates effectiveness in identifying possible weaknesses in question form and distractor quality. Yet, its performance was limited in estimating discrimination indicators that depend directly on actual learner response behavior. Conclusions: The findings suggest that AI-assisted pre-assessment can support the early identification of problematic MCQ items before exam administration. Integrating AI-based linguistic evaluation with traditional psychometric analysis may enhance the quality of Arabic educational assessment.
No takes yet. Share an insight, caveat, or question.
Omar Dahham Sarhan (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: