DSpace collection: 博碩士論文

探討使用GPT結合真實情境與GraphRAG的個人化下一句預測;Investigating Personalized Next-Sentence Prediction Using GPT with Authentic Context and GraphRAG

title: 探討使用GPT結合真實情境與GraphRAG的個人化下一句預測;Investigating Personalized Next-Sentence Prediction Using GPT with Authentic Context and GraphRAG abstract: 下一句預測（NSP）已成為大型語言模型在支援英語為外語（EFL）寫作上的重要應用方向。然而，現有的 NSP 常缺乏個人化與事實可靠性。為了改善這些限制，本研究提出一套系統：結合個人化與情境化提示（PCP）的個人化 NSP 寫作助理。該系統包含三個模組：情境模組（CM），用以擷取如圖片輸入等真實情境；資訊擷取模組（IEM），利用 GraphRAG 檢索相關資訊；以及寫作風格模組（WSM），用以捕捉學生的寫作風格。這三個模組的輸出將整合成 PCP，用來引導預測句的生成。系統以 OpenAI o3 為主要模型。本研究之評估包含以相似度與正確性指標進行的自動化測試，以及針對七位印尼 EFL 高中生進行的正式實驗，採用前實驗研究設計，分析其預測功能的使用行為並評估預測句的表現。結果顯示，本研究所提出的系統能有效提升預測句的表現。三個模組皆對系統性能有顯著貢獻，其中 WSM 對預測句整體表現的影響最大，證實符合學生寫作風格是實現個人化的關鍵。IEM 在學生寫作深度不足時，提供必要的內容細節，且縮小高低成就學生之間預測句性能差距的最重要因素。正式實驗中，G-Eval 分數亦證實系統生成的預測句表現優異，學生反映系統提供的預測句有助於構思並加快文章寫作速度。此外，越積極提供情境圖片的學生對預測句的接受度越高。本研究證明，結合個人化、真實情境與 GraphRAG 及 OpenAI o3，為改進 NSP 寫作助理提供了一種可行的方法。研究結果為開發更具適應性與可持續性的 EFL 寫作助理，提供了實證依據與設計見解。;Next-sentence prediction (NSP) for EFL writing support often lacks personalization and factual reliability. To address these limitations, this study proposed a personalized NSP with Personalized and Contextual Prompt (NSP-PCP) for writing assistant, which proposed three modules such as the Contextual Module (CM), which extracts authentic context such as image inputs; the Information Extraction Module (IEM), which retrieve relevant information using GraphRAG; and the Writing Style Module (WSM), which captures individual writing styles. These modules are integrated into a PCP that guides the generation of predicted sentences. The system is powered by OpenAI o3 as the primary model. The evaluation comprised an automatic test employing similarity and correctness metrics, as well as a formal experiment conducted with seven Indonesian EFL high school students using a pre-experimental design, in which they engaged in writing tasks with our proposed system. The results indicate that the proposed system improved the performance of predicted sentences. All three modules made significant contributions. WSM had the largest impact on overall performance, confirming that matching a student′s writing style is a big portion to personalization. IEM provided essential content details when students′ writing lacked depth, which was the most influential factor in reducing the performance gap between higher and lower achieving students. In the formal experiment, G-Eval scores confirmed the higher performance of predicted sentences, and students reported that the predictions supported idea development and drafting efficiency. Moreover, students who more actively provided contextual images showed higher acceptance of the predicted sentences. Therefore, this study demonstrates that combining personalization, authentic context, and GraphRAG with OpenAI o3 model provides a practical approach to improving NSP mechanism for writing assistance. The findings offer empirical evidence and design insights for developing more adaptive and sustainable writing support systems of EFL writing in the future.

支持知識翻新取向科學探究學與教之線上學習平台開發與初步評估;Development and Preliminary Evaluation of an Online Learning Platform Supporting a Knowledge Building Approach to Scientific Inquiry Learning and Teaching.

title: 支持知識翻新取向科學探究學與教之線上學習平台開發與初步評估;Development and Preliminary Evaluation of an Online Learning Platform Supporting a Knowledge Building Approach to Scientific Inquiry Learning and Teaching. abstract: 近年來數位學習平台已廣泛應用於國小自然科學教學，然而經分析發現，現有環境多設計為以習得既有知識為目標的作業管理系統，其功能侷限於行政流程與程序執行，難以支持以產生與精進想法為核心的知識翻新歷程。此限制導致在欲落實知識翻新教學的課堂中，探究活動往往流於形式操作而缺乏思辨，且小組間易形成資訊孤島。基於此，本系統深化「以想法為中心」之設計理念，在教師端整合「結構化備課包」以降低教學引導負擔；在學生端則透過「想法牆」、「問題牆」與「跨組討論牆」等核心機制，引導學生將思考轉化為可視化的概念人造物，並打破小組界線以落實集體認知責任。本研究採系統初步評估設計，針對國小高年級學生進行實測。結果顯示，學生對平台之科技接受度趨於正向，並肯定系統在促進想法表達、同儕互動及跨組交流方面之成效。本研究證實 Idea Flow 能有效支援合作探究歷程中之深度思考與社群互動，可為未來相關平台設計提供具體參考。 ;In recent years, digital learning platforms have been widely adopted in elementary science education. However, most existing environments are designed as "management-oriented systems" focused on acquiring established knowledge, with functions limited to procedural execution. Such platforms struggle to support the Knowledge Building process centered on "generating and refining ideas," leading to superficial inquiry and information silos between groups. To address these challenges, this study developed "Idea Flow," a platform deepening the "idea-centered" design philosophy. For teachers, it integrates "structured lesson preparation kits" to reduce the burden of instructional guidance. For students, it provides core mechanisms such as "Idea Walls," "Problem Walls," and "Cross-group Discussion Walls" to help them transform thoughts into visual "conceptual artifacts" and foster collective cognitive responsibility. This study adopted a preliminary evaluation design. The results indicate that students showed positive technology acceptance and affirmed the platform′s effectiveness in promoting idea expression and community interaction.

資訊科技結合桌遊融入國小五年級教學活動之資訊素養和運算思維能力的分析;An Analysis of Information Literacy and Computational Thinking Skills in Fifth-Grade Elementary Students Through the Integration of Information Technology and Board Games into Instruction

title: 資訊科技結合桌遊融入國小五年級教學活動之資訊素養和運算思維能力的分析;An Analysis of Information Literacy and Computational Thinking Skills in Fifth-Grade Elementary Students Through the Integration of Information Technology and Board Games into Instruction abstract: 本研究的主要目的在於探討如何將資訊科技與桌遊結合，融入國小五年級彈性學習課程的設計與實施過程中，並深入分析此種創新教學模式對學生資訊素養、運算思維及學習成效的影響。研究問題包括：一、運用機器人遊戲進行〈TechTopia—科技烏托邦〉時，對國小高年級學生的運算思維能力有何影響？二、國小高年級學生在進行〈TechTopia—科技烏托邦〉中的程式設計歷程為何？三、〈TechTopia—科技烏托邦〉融入資訊科技對國小五年級不同性別學生的資訊素養有何差異？四、國小高年級學生對〈TechTopia—科技烏托邦〉遊戲式學習的課程回饋為何？本研究採用混合方法進行，包含質性與量性資料的收集與分析。首先，進行文獻回顧，整理有關遊戲式學習、資訊素養、運算思維等理論，並基於此基礎設計一個結合桌遊和資訊科技的彈性學習課程。接著，研究者於某國小五年級進行教學，收集學生的學習成果、問卷資料以及過程錄影。資料分析部分，採用統計方法進行學習成效測驗，並對遊戲歷程進行質性分析，以深入瞭解彈性課程如何更貼近學習目標。研究結果顯示，學生在運算思維整體表現及各構面上皆有提升，尤以多步推理、抽象化分析與演算法規劃相關題型進步最為明顯。質性資料亦顯示，學生在多回合遊戲歷程中逐漸能以較具結構性的方式進行問題拆解與程式修正，展現由操作層次轉向策略層次的演算法思維發展。此外，資訊素養自評問卷結果顯示整體表現正向，男生在資料管理與工具應用上自評較高，而男女在溝通表達與使用態度上差異不明顯。〈TechTopia—科技烏托邦〉情境化任務亦促使學生實際運用資訊蒐集、判斷與決策能力，有效促進資訊素養之養成。;This study explores the integration of information technology and board games into a flexible curriculum for fifth-grade elementary students and examines its effects on their computational thinking, information literacy, and learning satisfaction. The research investigates how using the robot-based game TechTopia influences upper elementary students’ computational thinking skills, how students engage in programming during gameplay, how the incorporation of information technology in TechTopia affects the information literacy of students of different genders, and how students perceive and respond to this game-based learning approach. A mixed-methods design was employed, combining quantitative data from achievement tests and questionnaires with qualitative data from classroom observations and video recordings. The curriculum was implemented in a fifth-grade class, and analyses focused on students’ learning outcomes, engagement, and experiences throughout the instructional process. Students showed overall improvement in computational thinking, particularly in multi-step reasoning, abstraction, and algorithmic planning. Qualitative findings indicated a shift from operational to strategic algorithmic thinking. Information literacy self-assessments revealed overall positive performance, with boys rating themselves higher in data management and tool use, while gender differences in communication and attitudes were minimal. Contextualized tasks in TechTopia effectively fostered students’ information literacy through active information collection, evaluation, and decision-making.

Mathematical Word Problem Generation using Generative AI with Contextualization, Personalization, and Socialization: A Comprehensive Framework for Application and Evaluation

title: Mathematical Word Problem Generation using Generative AI with Contextualization, Personalization, and Socialization: A Comprehensive Framework for Application and Evaluation abstract: 真實情境數學應用題（AMWPs）作為重要的教學資源，不僅能評估學生對多元數學概念的掌握程度，更能培養數學推理與解題能力。然而，建構真實情境數學應用題（AMWP）實屬艱鉅任務，因其需兼顧數學正確性、情境相關性與教育價值三者平衡。要生成既可解又具意義的真實情境數學應用題，需謹慎整合真實世界情境、精確數值數據、適當認知需求，並與學習目標相契合。此外，確保題型與難度層級的多樣性更為生成過程增添複雜性。在此背景下，自動生成數學應用題能有效應對這些挑戰，實現高效產出多元、情境相關且數學運算正確的題目。現有自動化數學問題生成研究主要採用三種核心技術：模板式生成、問題改寫及神經網路驅動的文本生成。其中模板式方法常涉及勞力密集的流程，因其需人工設計模板，且部分情況下依賴特定語言工具或資源，導致跨情境的擴展性與適應性受限。問題改寫法透過改寫或修改現有題目，卻受限於語義漂移問題——措辭變動可能無意間改變數學含義或解法。此法亦因高度依賴既有題庫而缺乏創新性，且可能引發情境錯配或歧義。此外，基於神經網路的問題生成雖具更高靈活性，卻衍生其他挑戰：例如產生事實矛盾、生成不可解題型，以及缺乏教學控制力以符合課程標準或目標技能。神經模型可能產生文化偏見或無關情境，且其輸出品質因訓練數據依賴性而差異懸殊。相較於現有數學應用題生成研究，我們提出一種嶄新方法，運用生成式人工智慧自動生成具備情境化、個人化與社會化特性的數學應用題。情境化策略旨在將數學概念置於真實世界、實際情境或個人相關情境中，使數學應用題更具意義，這些情境能反映學習者的日常經驗與環境。情境化AMWP將數學連結至日常體驗、實務情境或相關事件，使其對學習者更具相關性、真實性與吸引力。個人化機制則藉由調整難度以匹配個別學習者能力，提升AMWP的有效性。藉由依學生技能水平量身打造問題，確保每位學習者獲得適當挑戰，從而促進參與度、激發動機並達成最佳學習成效。最後，社會化機制則進一步融入社交互動提示與團體導向任務，將AMWP從個人練習工具轉化為協作學習工具，支持共同解題並發展合作、協商、觀點分享等社會認知能力。我們的主要貢獻包括： 1) 透過系統性文獻回顧（SLR）對數學應用題自動生成研究進行全面綜述。本綜述整合了當前數學應用題生成的進展，涵蓋尖端技術與評估方法，為研究者與教育工作者提供完整參考，為未來研究在選擇生成方法與評估方式時提供指引。此外，本研究提出整合情境化、個人化與社會化原則的數學應用題生成與評估綜合框架。該框架不僅能引導自動生成數學精確且符合情境的應用題，更提供結構化評估標準，用以衡量應用題品質、教學契合度，以及在個別學習與協作學習情境中的成效。 2) 提出並實施自動化AMWP生成系統。該系統運用生成式人工智慧，提出一種創新的三難度等級AMWP生成方法，並將其整合至自動化系統中。透過自動化指標、人工評鑑與啟發式評估等多重技術，驗證生成之應用題與系統品質，證實生成式人工智慧結合真實情境資訊於AMWP 生成技術之可行性。 3) 透過在真實教育環境中的實施與驗證，對 AQG 系統的有效性進行實證分析。我們在真實學習情境中，透過準實驗研究評估該系統的成效。結果顯示該系統能促進數學問題解決能力，並提升學生的數學學習表現，證實其在課堂環境中的實用價值。 4) 提出名為SocioMathLLM的社會化多模態大型語言模型框架。該框架整合創新提示工程策略，融合多模態真實情境資訊（文字與圖像）、多元群體背景資料及社會化準則（如群體規模、任務性質、社會目標、互動頻率、交流數量與社會依存性等），以生成旨在培養群體社會化能力的真實情境數學應用題。SocioMathLLM 特別強調其在協作式數學學習中的應用潛力，可培養群體協作、合作、協商及想法分享等社會化能力。;Mathematical Word Problems (MWPs) serve as an important instructional resource that not only assesses students’ proficiency in diverse mathematical concepts but also supports mathematical reasoning and problem-solving skills. Generating authentic MWP (AMWPs) is a challenging task due to the need to balance mathematical correctness, contextual relevance, and educational value. Generating AMWPs that are both solvable and meaningful requires careful integration of real-world scenarios, accurate numerical data, appropriate cognitive demand, and alignment with learning objectives. Additionally, ensuring diversity in problem types and difficulty levels adds further complexity to the generation process. Here, the automatic generation of MWPs can help address these challenges by efficiently producing diverse, contextually relevant, and mathematically accurate problems. Existing studies on automatic MWP generation have primarily employed three main techniques: template-based generation, question rewriting, and neural network–based text generation. Among these, template-based methods often involve labor-intensive and time-consuming processes, as they require manually crafted templates and, in some cases, rely on language-specific tools or resources that limit scalability and adaptability across contexts. Question rewriting, which involves paraphrasing or modifying existing problems, is limited by semantic drift, where changes in wording may unintentionally alter the mathematical meaning or solution. This approach also produces limited novelty, as it depends heavily on pre-existing problems, and may introduce context mismatches or ambiguity. Furthermore, neural network–based problem generation offers greater flexibility but introduces other challenges, such as factual inconsistencies, unsolvable problems, and a lack of pedagogical control to align with curriculum standards or targeted skills. Additionally, neural models may produce culturally biased or irrelevant contexts, and their outputs can vary widely in quality due to dependence on training data. In contrast to existing works on MWPs generation, we propose a different approach that leverages generative AI to automatically generate AMWPs with contextualization, personalization, and socialization. Contextualization enhances the meaningfulness of AMWPs by situating mathematical concepts within authentic, real-world, or personally relevant contexts that reflect learners’ everyday experiences and environments. Contextualized AMWPs link mathematics to everyday experiences, practical situations, or relatable events, to make them relevant, authentic, and engaging for learners. Personalization contributes to making AMWPs more effective by adjusting the difficulty level to match individual learners’ abilities. By tailoring problems to students’ skill levels, it ensures that each learner is appropriately challenged, promoting engagement, motivation, and optimal learning outcomes. Finally, the socialization mechanism transforms AMWPs from tools for individual practice into instruments for collaborative learning by incorporating social interaction prompts and group-oriented tasks, supporting collaborative problem-solving and the development of social-cognitive competencies such as collaboration, cooperation, negotiation, and idea-sharing. Our main contributions include: 1) Presenting a comprehensive review of MWP automatic generation research by Systematic Literature Review (SLR). It synthesizes current advancements in MWP generation, including state-of-the-art techniques and evaluation methods. This offers a comprehensive reference for researchers and educators, guiding the selection of generation approaches and evaluation methods in future work. In addition, this study proposes a comprehensive framework for generating and evaluating MWPs, which integrates contextualization, personalization, and socialization principles. The framework not only guides the automatic generation of mathematically accurate and contextually relevant problems but also provides structured evaluation criteria to assess problem quality, pedagogical alignment, and effectiveness in both individual and collaborative learning settings. 2) Proposing and implementing an automated AMWP generation system. It presents a novel method for generating AMWPs with three difficulty levels using generative AI, which was implemented in an automated system. Multiple evaluation techniques, including automatic metrics, human evaluation, and heuristic evaluation, were applied to validate the quality of both the generated MWPs and the system, demonstrating the feasibility of combining generative AI with authentic contextual information in AMWP generation. 3) Presenting empirical validation of the AQG system’s effectiveness through implementation and validation in real educational settings. We evaluated the effectiveness of the proposed system through a quasi-experimental study in authentic learning contexts. The results demonstrated that the system facilitates mathematical problem-solving and improves students’ mathematics learning performance, confirming its practical utility in classroom environments. 4) Proposing a socialized multimodal LLM framework called SocioMathLLM. It integrates an innovative prompt engineering strategy to incorporate multimodal authentic contextual information (text and image), diverse group background information, and socialization criteria (e.g., group size, task nature, social goal, social frequency, interaction quantity, and social interdependency, etc.) to generate AMWPs aimed at fostering group socialization. SocioMathLLM highlights its potential for application in collaborative mathematics learning and fostering socialization competencies such as group collaboration, cooperation, negotiation, and ideas-sharing.