- 學位論文
線上診斷測驗及補救教學系統研發－以國小數學領域分數概念為例
The Development of an Online Diagnostic Test and Remedial Instruction System－Using The Concept of Fraction in Elementary School Math as an example
摘要
本研究嘗試以國小四、五年級數學領域之七個能力指標為例，探討結合知識結構的貝氏網路是否能有效的診斷出學童的錯誤類型。並發展一套以九年一貫課程數學領域能力指標為基礎的線上診斷測驗及補救教學系統，讓學生透過線上診斷測驗立即得知自己的測驗結果，並根據診斷報告進行線上補救教學，期能同時達到評量、診斷、補救教學的功效。 研究結果發現： 一、貝氏網路應用於診斷分數概念相關能力指標具有良好的效果，可達到不錯的辨識率；加入知識結構之貝氏網路比貝氏網路雛型具有較佳的辨識率。 二、電腦化適性診斷測驗預測推估出來的分數比完整作答分數高，但又有其一定的預測率，不但可以節省試題也可以節省施測時間，還可以立即的診斷出學生的錯誤類型及子技能。 三、經過電腦化補救教學之後，學生成績均有顯著的進步，顯示電腦化補救教學的確有顯著的功效。
並列摘要
This research used 7 indicators of mathematical field of grade 4 and 5 in elementary school as an example to study if Bayesian networks combining knowledge structure can effectively diagnose the students’ mistaken types. It also developed a set of on-line diagnostic test based on mathematical indicator of Grade 1-9 Curriculum and remedial instruction system to allow the students to immediately find their test results through on-line diagnostic test and have on-line remedial instruction according to diagnostic report. The research expected to reach the effects of evaluation, diagnosis and remedial instruction. The research findings are below: 1. Bayesian networks reveal good results when diagnosing fraction-related indicators and they can lead to satisfying identification rate; Bayesian networks adding knowledge structure have better identification rate than the model of Bayesian networks. 2. The predicted scores of computerized adaptive diagnostic test are higher than those of complete answers. However, the former reveals certain predication rate which can save not only the tests, but also the test time. The test can also immediately diagnose the students’ mistaken types and sub-skills. 3. After computerize adaptive remedial instruction the students’ performance improves significantly which shows the significant effect of computerize adaptive remedial instruction.