由於電腦及網路的普及，中小學評量試題電子化的程度也越來越高；如何有效的幫助教師進行試題管理與試題分類，是近年來相當重要的研究課題。電子試題題庫的大量建置與應用下，能幫助教師快速地產生與編譯出一份電子試卷；而試題題庫中通常會提供如難度、鑑別度、布魯姆認知分類指標等等的試題資訊，作為教師選擇試題時的依據。
然而要能正確且適當的標示出電子試題的這些重要的試題資訊，往往需要花費龐大的人力與時間。為此，本研究發展出可自動判別出布魯姆認知分類指標的分類機制；應用事先分類完成的大量試題並搭配簡單貝氏分類演算法來訓練並產生一試題布魯姆認知分類模型，再依據此一試題分類模型來判斷所匯入之新試題的布魯姆認知分類指標。實驗設計將針對尚未分類的215題國小三年級上學期自然科試題進行自動分類，並得到80.9%的準確率，可證明此機制能有效的判斷出國小自然科試題的布魯姆認知分類指標，可提供與應用在未來大量電子試題自動分類上的參考。

The extensive usage of computers and networks also pushes teachers in the elementary and junior high schools to use electronic assessment systems for their examinations. These assessment systems usually contain large volumes of test items in their item banks. How to effectively help teachers to manage and classify the test items is an important research issue in recent years.
To help teachers to compile an assessment, test items in the banks will typically carry information like difficulty, discrimination, and bloom cognitive taxonomy for teachers to choose from. However, to correctly and properly tag these important information on the items often require a huge amount of effort and time. This thesis develops an mechanism to automatically determine the of test items. A large amount of test items tagged with the bloom cognitive taxonomy information are used by the Naive Bayes classification algorithm for training in order to build an item classification model, which is then used to judge the correct bloom cognitive taxonomy of test items newly added into the item bank. An experiment is designed to classify, using the trained model, 215 test items of science courses in elementary schools. The results show that the accuracy of classification is almost 80.9%, which confirms that this mechanism can effectively judge bloom cognitive taxonomy of a test item and can provide for e-learning systems as an automatic classification tool to save human efforts.

Anderson, L., Krathwohl, D., & Bloom, B. (2001). A Taxonomy for Learning,
Teaching, and Assessing: A Revision of Bloom's Taxonomy of educational
Objectives: Longman.
Bloom, B. (1956). Taxonomy of Educational Objectives: The Classification ofEducational Goals Handbook I: Cognitive domain. New York, NY:Longman,Green.: McKay.
Domingos, P. & Pazzani, M. (1997). On the Optimality of the Simple Bayesian Classifier under Zero One Loss, Machine Learning, Vol. 29, 103-130.
Li, Y. H. & Jain, A. K. (1998), Classification of text documents, Computer Journal, Vol. 41, 537-546.
Ma, Wei-Yun & Keh-Jiann Chen (2003). "Introduction to CKIP Chinese Word Segmentation System for the First International Chinese Word Segmentation Bakeoff", Proceedings of ACL, Second SIGHAN Workshop on Chinese Language Processing, pp168-171.
柯映竹(2003)。變數間正負相關對簡易貝氏分類器學習正確率之影響。國立成功大學工業管理研究所碩士論文，未出版。台南市：國立成功大學。
陳豐祥（2009）。新修訂布魯姆認知領域目標的理論內涵及其在歷史教學上的應用，歷史教育，15，1-53
張佩琪(2010)。整合教師評量知識之智慧型出題輔助系統。國立成功大學工程科學研究所碩士論文，未出版。台南市：國立成功大學。
葉連祺、林淑萍(2003)。布魯姆認知領域教育目標分類修訂版之探討，教育研究月刊，105，94-106。
鄭蕙如、林世華（2004）。Bloom 認知領域教育目標分類修訂版理論與實務之探 討--以九年一貫課程數學領域分段能力指標為例，臺東大學教育學報，15(2)，247-274。