DSpace community: 網路學習科技研究所碩士在職專班

MagicSchool AI數位對話工具對小學生數學素養題學習成效研究;MagicSchool AI數位對話工具對小學生數學素養題學習成效研究

Tue, 20 Oct 2026 08:58:59 GMT

title: MagicSchool AI數位對話工具對小學生數學素養題學習成效研究;MagicSchool AI數位對話工具對小學生數學素養題學習成效研究 abstract: 本研究旨在探討MagicSchool AI數位對話工具應用於國小學生數學素養題學習活動後，學生數學學習成效，學習成效與年級、性別是否有差異之初探性研究。本研究於暑期課後照顧班中進行，以國小四、五年級學生共13名為研究對象，其中1名學生因於實驗期間請假未完成完整三週的實驗活動，及另一名學生未正確使用MagicSchool AI數位對話工具進行數學素養題練習，故將兩名學生於學習成效統計分析中予以排除，最終納入11名學生進行前測、後測與延宕後測之學習成效量化分析。本研究採單組前測、後測與延宕後測之前實驗研究設計，介入活動為期三週，共進行五節數學素養題練習課程。研究工具包括MagicSchool AI數位對話工具、數學素養題題庫與測驗卷。使用數學素養題題目與答案為題庫，透過提示詞設定，於 MagicSchool AI平台設置一個數學AI小老師，使其與學生互動，過程中以提問、提示、步驟拆解、不直接給予答案的方式提供鷹架支持協助學生理解與學習。數學素養題庫與測驗題取自國家教育研究院素養導向試題，內容涵蓋生活情境判讀、數量關係理解與多步驟推理。數學素養題測驗卷評分方式採用人工評分與AI評分，並通過ICC評分一致性驗證，最終分數取兩者平均值進行後續分析。資料分析方面，本研究以年級與性別做為群組，使用Friedman 檢定與 Conover 事後檢定的量化分析方式分析學生於前測、後測與延宕後測之學習成效差異。另外挑選四年級、五年級學習成效進步與持平共4位學生，四年級、五年級學習保留效果不佳共2位學生，針對測驗卷與練習題的數學概念進行關聯分析，以理解學生的學習歷程，其中 1 位五年級學生同時納入兩種分析，所以共5位學生進行學習歷程分析。研究結果顯示，學生於數學AI小老師介入活動後，全體學生組、四年級組與男性組，後測與前測分數的差異達到統計上的顯著，顯示介入活動期間觀察到立即學習表現的提升伴隨現象。五年級組與女性組前後測分數差異則呈現大效果量但未達統計顯著，可能受限於樣本數過小。後測與延宕後測分數變化未達顯著差異，顯示學習成效具有一定的保留效力。;This exploratory study examined the effects of using the MagicSchool AI digital conversational tool to support elementary school students in learning mathematical literacy problems. It also explored whether students’ learning outcomes differed by grade level and gender. The study was conducted in a summer after-school program with 13 fourth- and fifth-grade students. Two students were excluded from the learning effectiveness analysis: one did not complete the full three-week intervention due to absence， and the other did not use the MagicSchool AI tool properly during the practice activities. As a result， 11 students were included in the final quantitative analysis of pretest， posttest， and delayed posttest results. A one-group pretest–posttest–delayed posttest pre-experimental design was adopted. The intervention lasted for three weeks and included five sessions of mathematical literacy practice. The research instruments included the MagicSchool AI digital conversational tool， a mathematical literacy problem bank， and test papers. Based on selected mathematical literacy problems and their solutions， a “Math AI Tutor” was created on the MagicSchool AI platform through prompt design. The tutor interacted with students by asking guiding questions， giving hints， breaking complex problems into smaller steps， and avoiding direct answers. In this way， it provided scaffolded support to help students understand and solve mathematical literacy problems. The problem bank and test items were selected from competency-oriented assessment items developed by the National Academy for Educational Research， covering real-life context interpretation， quantitative reasoning， and multi-step problem solving. The mathematical literacy tests were scored using both human scoring and AI scoring. The consistency between the two scoring methods was examined using the intraclass correlation coefficient， ICC. The final test scores were calculated by averaging the human and AI scores for subsequent analysis. For data analysis， students were grouped by grade level and gender. The Friedman test and Conover post hoc test were used to examine differences in learning outcomes across the pretest， posttest， and delayed posttest. In addition， students were selected for further learning process analysis based on their learning performance and retention outcomes. Specifically， four fourth- and fifth-grade students whose performance either improved or remained stable， and two fourth- and fifth-grade students whose retention was relatively weak， were selected for analysis. Since one fifth-grade student was included in both categories， a total of five students were ultimately included in the learning process analysis. Their test responses and practice records were analyzed to identify connections among mathematical concepts and to better understand their learning processes. The results showed that， after the intervention with the Math AI Tutor， the overall group， the fourth-grade group， and the male group showed statistically significant improvement from pretest to posttest. This suggests that students demonstrated immediate gains in mathematical learning during the intervention. For the fifth-grade group and the female group， the pretest–posttest differences showed large effect sizes but did not reach statistical significance， possibly due to the small sample size. No significant differences were found between the posttest and delayed posttest scores， indicating that the learning gains were retained to a certain extent.

結合生成式AI的教師備課平台之開發與初步評估;Development and Preliminary Evaluation of a Teacher Lesson Planning Platform with Generative AI

Tue, 20 Oct 2026 08:58:40 GMT

title: 結合生成式AI的教師備課平台之開發與初步評估;Development and Preliminary Evaluation of a Teacher Lesson Planning Platform with Generative AI abstract: 從《十二年國民基本教育課程綱要》實施以來，教學現場強調素養導向與差異化教學。但在實務上，書商所提供的標準化教師手冊多屬於通案性質，往往無法直接對應不同班級的在地化需求。為了將這些公版教材轉化為合適的教學內容，教師常需仰賴社群共備來解構教材並激發靈感。然而，前期的資料蒐集與文書整理耗費了大量時間，反而壓縮了教師之間實質的對話與討論空間，無形中增加了備課壓力。為減輕教師在備課初期的文書負擔，本研究以探討教師備課需求為出發點，進而導入 AI 輔助，探究如何將生成式人工智慧（Generative AI）轉化為實用的「備課小幫手」。考量到直接使用傳統 AI 容易產生內容不正確，或給出偏離教學現場的建議，本研究導入了檢索增強生成（Retrieval-Augmented Generation， RAG）技術。透過這項技術，教師可以先上傳自己的教材來建立專屬知識庫；系統能依據這些確切的文本內容，協助進行資料收斂，幫助教師在短時間內完成初步的教材整理與提供備課的內容建議。基於上述背景，本研究開發並初步評估了一套結合生成式 AI 與 RAG 技術的教師備課平台。在系統定位上，本研究提供教學發想與教材整合的建議。為避免取代教師專業，系統在設計上不提供「直接產出完整教案」的功能，以確保教學設計的最終決策權回歸教師本身。在成效評估方面，本研究以科技接受模式為理論框架，邀請 39 位具備教案撰寫經驗的現職國中小教師進行問卷調查，藉此了解他們對該平台的知覺有用性、知覺易用性及使用意願。研究結果顯示，參與測試的教師大多對此平台給予正面評價。量化與質性回饋指出，這套教師備課平台有助於減少整理公版教材所需的時間，並能在活動設計上提供多元的參考方向，多數教師也表達了願意持續使用的意圖。綜合而言，本研究除了回應教學現場對備課資源整合的需求，也初步支持以「輔助收斂」取代「自動生成」的系統設計，在教育實務中具有良好的應用價值，可供未來推動智慧教學輔助工具作為參考。;Since the implementation of Taiwan’s 12-Year Basic Education Curriculum， the educational field has emphasized literacy-oriented and differentiated instruction. In practice， however， the standardized teacher manuals provided by publishers are mostly generalized and often fail to directly meet the localized needs of different classrooms. To transform these standardized materials into suitable instructional content， teachers frequently rely on collaborative lesson planning to deconstruct materials and inspire ideas. However， the initial data collection and document organization consume a significant amount of time， which in turn compresses the space for actual dialogue and discussion among teachers， inadvertently increasing the pressure of lesson preparation. To alleviate teachers′ document burden in the early stages of lesson preparation， this study starts from exploring teachers′ lesson planning needs， introduces AI assistance， and investigates how to transform Generative Artificial Intelligence (GenAI) into a practical "lesson planning assistant." Considering that directly using traditional AI easily produces incorrect content or suggestions that deviate from the teaching context， this study introduces Retrieval-Augmented Generation (RAG) technology. Through this technology， teachers can first upload their own materials to build a dedicated knowledge base; the system can then assist in data consolidation based on these exact texts， helping teachers complete preliminary material organization and providing content suggestions for lesson preparation in a short time. Based on the above background， this study developed and preliminarily evaluated a teacher lesson planning platform that integrates GenAI and RAG technology. Regarding system positioning， this study provides suggestions for instructional inspiration and material integration. To avoid replacing teachers′ professionalism， the system is designed not to provide the function of "directly generating complete lesson plans，" ensuring that the final decision-making authority for instructional design returns to the teachers themselves. In terms of effectiveness evaluation， this study used the Technology Acceptance Model (TAM) as the theoretical framework and invited 39 in-service K-12 teachers with lesson planning experience to participate in a questionnaire survey， aiming to understand their perceived usefulness， perceived ease of use， and intention to use the platform. The research results showed that most participating teachers gave positive evaluations of this platform. Quantitative and qualitative feedback indicated that this teacher lesson planning platform help to reduce the time required to organize standardized materials and provide diverse reference directions for activity design. Most teachers also expressed their intention to continue using it. In summary， in addition to responding to the needs of the educational field for integrating lesson planning resources， this study also preliminarily supports that a system design replacing "automatic generation" with "assisted consolidation" has good application value in educational practice and can serve as a reference for promoting intelligent instructional support tools in the future.

國小四年級自然科 AI 輔助深讀之初步研究;A Preliminary Study of AI-Assisted Deep Reading in Elementary Science for Fourth-Grade Students.

Tue, 20 Oct 2026 08:58:23 GMT

title: 國小四年級自然科 AI 輔助深讀之初步研究;A Preliminary Study of AI-Assisted Deep Reading in Elementary Science for Fourth-Grade Students. abstract: 國小中年級自然科學習逐漸由生活經驗的觀察，轉向較具學科性的概念理解。學生在學習過程中，不只需要讀懂文本，也需要整理資訊、釐清概念，並以自己的話表達想法。然而，在教學現場中，部分學生閱讀多篇自然科文本時，容易出現能理解部分內容卻不易整理、知道一些內容卻無法完整表達，或不知道如何提問與作答的情形。基於此，本研究以國小四年級自然科 AI 輔助深讀活動為情境，探討學生在多文本閱讀與生成式 AI 輔助歷程中的學習經驗。本研究採質性描述研究取向，以國小四年級三個班級共93名學生為研究對象，於112學年度第二學期實施自然科多文本深讀活動，並導入 ChatGPT 作為學習輔助工具。學生透過明日星球平台進行自然科多文本閱讀、個人讀寫與小組討論，並在教師引導下使用 ChatGPT 進行概念釐清、資訊查詢、重點整理與提問延伸。研究以76份有效開放式問卷為主要分析資料，並參照明日星球平台作答紀錄與189筆可辨識的 ChatGPT 互動事件。資料分析經由資料整理、反覆閱讀、初步編碼、類別整併與主題歸納，整理學生的 AI 使用方式、學習感受、學習困難與支持需求。研究發現，學生多在閱讀或作答時遇到不理解的內容、不知道如何回答，或需要即時協助時使用 ChatGPT。從學生自述來看，其使用方式主要包括詢問自然科概念、查詢答案或相關資訊、整理重點與參考作答；實際互動事件則以概念釐清與答案查詢為主，兩者合計占75.7%，延伸追問、應用推論與資訊整理所占比例相對較低。多數學生自述 ChatGPT 能提供概念說明與作答參考，使其在理解或作答遇到困難時較容易獲得協助；部分學生也因 AI 回應中的補充說明或延伸內容，而對自然科主題產生好奇。不過，學生在自然科深讀歷程中仍面臨閱讀理解、資訊整理、概念掌握、問題形成與作答表達等困難，也不一定能判斷 AI 回應是否適切或正確。整體而言，生成式 AI 可作為自然科深讀歷程中的即時輔助資源，但其價值不在於取代閱讀、思考或教師引導，而在於能否被納入適切的學習歷程。自然科 AI 輔助深讀的關鍵，在於多文本閱讀、教師引導、同儕互動、閱讀支架與 AI 輔助之間的整合。教師若能提供提問示範、文本查證與資訊整理支架，較能協助學生檢視並整理 AI 回應，進而轉化為自己的理解與表達。;As elementary school students progress into the middle grades， science learning gradually shifts from observations based on everyday experiences toward the understanding of more subject-specific concepts. Students need not only to comprehend science texts but also to organize information， clarify concepts， and express ideas in their own words. In classroom practice， however， some students may understand only part of the content but have difficulty organizing information across multiple science texts， expressing what they know clearly， or formulating questions and written responses. Against this background， this study explored fourth-grade students’ learning experiences in AI-assisted deep reading activities in elementary science， focusing on multiple-text reading and the use of generative AI as a learning support tool. This study adopted a qualitative descriptive approach and involved 93 fourth-grade students from three classes in an elementary school. The activities were implemented during the second semester of the 2023–2024 academic year in Taiwan. Students used the Planet of Tomorrow platform to read science texts， complete individual reading and writing tasks， and participate in group discussions. Under teacher guidance， they also used ChatGPT to clarify concepts， search for information， organize key points， and extend their questions. The primary data consisted of 76 valid responses to an open-ended questionnaire， supplemented by platform response records and 189 identifiable ChatGPT interaction events. The data were analyzed through data organization， repeated reading， initial coding， category consolidation， and thematic synthesis. The findings showed that students commonly used ChatGPT when they encountered content they did not understand， were unsure how to answer a question， or needed immediate assistance. According to their self-reports， students used ChatGPT to ask about science concepts， search for answers or related information， organize key points， and obtain guidance when constructing responses. The interaction records showed that concept clarification and answer seeking accounted for 75.7% of the identifiable interactions， whereas extended questioning， application and inference， and information organization occurred less frequently. Most students reported that ChatGPT provided conceptual explanations and guidance for constructing responses， particularly when they experienced difficulty understanding texts or answering questions. Some students also expressed greater curiosity about science topics after receiving additional explanations or related information from AI. Nevertheless， students continued to experience difficulties in reading comprehension， information organization， concept understanding， question formulation， and written expression. They did not always know how to formulate clear questions or determine whether AI-generated responses were appropriate or accurate. Overall， generative AI may serve as a source of immediate support during deep reading in elementary science. Its value， however， does not lie in replacing reading， thinking， or teacher guidance， but in how appropriately it is integrated into the learning process. The effective use of generative AI in deep reading depends on the integration of multiple-text reading， teacher guidance， peer interaction， reading scaffolds， and AI support. When teachers model question formulation and provide scaffolds for text-based verification and information organization， students may be better able to evaluate， organize， and integrate AI-generated information into their own understanding and written responses.

歷史主題閱讀：以多文本閱讀與概念圖活動提升歷史觀點取替能力;Historical theme reading: Improving historical perspective taking through multi-text reading and concept map activities

Tue, 20 Oct 2026 08:57:43 GMT

title: 歷史主題閱讀：以多文本閱讀與概念圖活動提升歷史觀點取替能力;Historical theme reading: Improving historical perspective taking through multi-text reading and concept map activities abstract: 本研究旨在探討運用多文本閱讀與概念圖活動提升台灣六年級學生歷史觀點取替能力的成效。研究主題聚焦於「皇民化運動」與「二次世界大戰」兩大歷史議題，選取台灣北部三個班級共73名學生為研究對象。其中兩班（49人）進行「皇民化運動」主題學習，探討台灣人與日本人在皇民化政策下的不同立場與回應；第三個班（24人）則進行「二次世界大戰」主題學習，理解軸心國與同盟國在二戰時的立場選擇與多元觀點。研究進行前測與後測比對、K-W-L學習模式(知-想-學)個人讀寫，並以多文本閱讀、小組討論及概念圖繪製活動作為主要教學策略。研究旨在引導學生整合各種歷史資訊，培養批判性思考與多元視角的歷史觀點。綜合前後測數據與個人讀寫內容結果顯示，在「皇民化運動」主題中，學生以現代觀點直接評價歷史事件的傾向顯著降低，並逐漸能從歷史人物角色及歷史脈絡理解事件；在「第二次世界大戰」主題中，學生歷史脈絡理解能力呈現提升趨勢，但以現代觀點直接評價歷史事件的傾向亦有所增加，顯示戰爭議題較容易引發學生以現代價值觀進行歷史判斷。整體而言，多文本閱讀結合概念圖活動有助於學生整理多文本資訊、建構歷史理解，惟不同歷史主題因議題性質不同，對學生歷史思維發展所產生的影響亦有所差異。;This study aims to investigate the effectiveness of using multiple text reading and concept mapping activities to enhance the historical perspective taking of sixth-grade students in Taiwan. The research focuses on two major historical topics: the Japanization Movement (Kōminka Movement) and the Second World War. A total of 73 students from three classes in northern Taiwan participated in the study. Two classes (49 students) engaged in the topic of the Japanization Movement， exploring the differing positions and responses of Taiwanese and Japanese people under Japanization policies; the third class (24 students) studied the Second World War， examining the multiple perspectives and choices of the Axis Powers and the Allied Powers during wartime. The study employed pretest and posttest comparisons， as well as individual K-W-L (Know–Want to Know–Learned) reading and writing activities. The main instructional strategies included multiple-text reading， group discussions， and concept mapping activities. The goal was to guide students in integrating diverse historical information and developing critical thinking and multiperspective reasoning within the context of historical inquiry. The combined results of the pretest–posttest comparisons and the individual reading and writing responses indicated that， in the Kōminka Movement unit， students became less likely to evaluate historical events directly from a present-day perspective and gradually developed a better understanding of historical events through the perspectives of historical actors and their historical contexts. In the Second World War unit， students demonstrated improvement in their understanding of historical contexts; however， they also showed a greater tendency to judge historical events from present-day values， suggesting that war-related topics are more likely to evoke present-oriented moral judgments. Overall， the findings indicate that integrating multiple-text reading with concept mapping activities helps students organize information from multiple texts and construct historical understanding. However， different historical topics may influence the development of students′ historical thinking in different ways because of their distinct historical characteristics.