以小學教師資格考探索人工智慧工具於師資養成輔助的潛力-試題 認知層次分析

Exploring the Potential of Artificial Intelligence Tools in Teacher Preparation Based on the Elementary School Teacher Qualification Examination: Analyzing the Cognitive Level of Examination Questions

為解決複雜的教學問題，需培養教師具備高階認知層次的能力，而日新月異的人工智慧有望成為師資養成的助力。教師資格考試為師資生修習師培課程能力認證的門檻，分析試題中的認知層次分布及人工智慧工具（例：ChatGPT）的答題表現，以探索其於教學輔助能力的表現有其必要性。本研究選取2019年到2022年小學教師資格考試中的教育專業科目，即「教育理念與實務」、「學習者發展與適性輔導」和「課程教學與評量」三相關考科的試題，共560題，運用修訂後的Bloom認知分類六層次，並再區分為高、低層次對不同考科試題及題型進行分析。此外，研究者探查ChatGPT於相關考科的總得分，並以盒鬚圖比較ChatGPT在不同科目和題型中高、低認知層次試題得分比的分布情形。結果顯示，教師資格考試的教育專業科目中，三考科的低認知層次試題占分比都高於高認知層次試題。符應素養導向評量要求的綜合題，高認知層次占分比比較高，達81.67 % ，但選擇題的高認知層次占分比僅達6.55 % ，有提升高認知層次比例的必要。此外，ChatGPT在教育專業科目平均總分為72.73分，成功通過教師資格考試平均60分的門檻，但對於高認知層次試題的表現歧異度大。這表明ChatGPT具有成為師資養成輔助工具的潛力，但教育工作者仍需特別注意高層次認知情境的評鑑與批判。

 

Training teachers to develop higher cognitive levels to address complex teaching challenges is necessary. Artificial intelligence (e.g., ChatGPT) holds the potential to assist in teacher education. Teacher qualification examination serves as a threshold for certifying pre-service teachers’ abilities in pursuing teacher education curricula. Analyzing the distribution of cognitive levels in examination questions and assessing the performance of artificial intelligence tools in answering these questions is necessary to explore their potential in aiding teaching assistance. This study selected 560 education professional examination questions from the elementary school teacher qualification examination between 2019 and 2022. We used the revised Bloom’s cognitive taxonomy to analyze and categorize questions into high and low cognitive levels. We investigated the ChatGPT scores in the relevant subject areas and compared the differences in score distribution between high and low cognitive levels across different subjects and question types using box plots. The results indicate that the percentage of low-order questions in all three subjects was higher than that of high-order questions in the teacher qualification examination of education professional subjects. The proportion of high-order comprehensive questions has increased to 81.67% to meet the competence-oriented assessment requirements. The percentage for multiple-choice questions remains relatively low at only 6.55%. This indicates a need to increase the proportion of high-order questions. Furthermore, ChatGPT achieved an average total score of 72.73 points in the education professional subjects, surpassing the threshold of an average score of 60 points for the teacher qualification examination. However, there was significant variability in its performance on high-order questions. This suggests that ChatGPT can potentially become an assistive tool for teacher education. However, educators must consider developing critical thinking skills in high-order cognitive contexts when using such tools.