{"slug":"aidriven-interactive-hierarchical-concep-052566","apex":{"id":"n1","children":[{"children":[{"text":"The proposed system leverages artificial intelligence to generate initial concept maps, refined through human-in-the-loop input for pedagogical accuracy and relevance.","label":"Proposed AI Concept Map System","parentId":"n2","type":"CONC","id":"n3","children":[{"type":"DETL","text":"A custom-designed interface enables learners to explore concepts at varying levels of depth, promoting active engagement and quick navigation.","label":"Interactive System Features","parentId":"n3","children":[],"id":"n4"}]}],"id":"n2","type":"CONC","parentId":"n1","text":"Traditional concept maps lack interactivity and scalability, necessitating enhancements with AI capabilities and interactive features in digital learning environments.","label":"AI-powered Concept Maps Need"},{"id":"n5","children":[{"id":"n6","children":[],"parentId":"n5","label":"Early Visualization Studies","text":"Early work by Naps et al. emphasized visual engagement, particularly in computer science education, contributes significantly to student understanding and motivation.","type":"DETL"},{"label":"Navigable Concept Map Systems","text":"The CoMPASS project and ActiveMath platform introduced navigable and adaptive visual structures to improve structural understanding and navigation efficiency.","parentId":"n5","type":"DETL","id":"n7","children":[]},{"type":"JUST","parentId":"n5","label":"Interactive Features Standard","text":"Hollingsworth and Narayanan argue that interactive features like concept maps should be standard components of digital textbooks.","children":[],"id":"n8"},{"parentId":"n5","text":"Barria-Pineda et al. developed visualization tools supporting self-regulated learning via concept-level mapping.","label":"Self-Regulated Learning Support","type":"DETL","id":"n9","children":[]},{"children":[],"id":"n10","type":"DETL","parentId":"n5","text":"In ontology-oriented learning systems, concept maps serve as structured, navigable knowledge representations, exemplified by TM4L.","label":"Ontology-Oriented Learning Systems"},{"parentId":"n5","label":"Concept Maps Improve Learning","text":"Many studies have shown that concept maps improve learning outcomes, particularly for complex material.","type":"FIND","id":"n11","children":[{"type":"STAT","text":"A meta-analysis by Schroeder et al. reviewed 142 studies and found concept maps significantly more effective than reading texts (g = .39) or reviewing outlines (g = .28).","label":"Meta-analysis Effectiveness","parentId":"n11","children":[],"id":"n12"},{"label":"Anatomy Course Study","text":"Bolatli and Bolatli reported higher post-test scores and lower cognitive load in anatomy students using predefined concept maps.","parentId":"n11","type":"STAT","id":"n13","children":[]},{"type":"DETL","text":"Elgendi and Shaffer demonstrated interactive glossary maps increased student engagement and repeated glossary use in a computer science e-textbook.","label":"Interactive Glossary Engagement","parentId":"n11","children":[],"id":"n14"},{"children":[],"id":"n15","type":"DETL","label":"Booc.io System Features","text":"Schwab et al. introduced booc.io, a system with drill-down hierarchical concept maps supporting adaptive navigation and targeted feedback.","parentId":"n11"},{"parentId":"n11","text":"Ma and Chen proposed an LLM framework for automated concept map construction from e-books, including segmentation, key concept extraction, and relationship identification.","label":"LLM Concept Map Construction","type":"DETL","id":"n16","children":[{"children":[],"id":"n17","type":"STAT","text":"Their evaluation of GPT-4o demonstrated strong performance, effectively extracting key concepts and accurately identifying hierarchical and cross-topic connections.","label":"GPT-4o Performance","parentId":"n16"},{"id":"n18","children":[],"parentId":"n16","label":"LLM Map Structure Insight","text":"LLMs could generate concept maps that differ from textbook structure, reflecting a more logical and content-based organization.","type":"INSG"}]},{"id":"n19","children":[],"text":"Kluga et al. integrated causal concept maps into an intelligent anatomy textbook for personalized navigation, quiz adaptation, and content feedback.","label":"Causal Concept Maps","parentId":"n11","type":"DETL"},{"id":"n20","children":[],"parentId":"n11","label":"Legal Concept Hierarchy System","text":"Wehnert et al. presented a dynamic visualization system for exploring concept hierarchies extracted from legal textbooks, supporting various navigation modes.","type":"DETL"}]}],"parentId":"n1","label":"Visualization Role in Learning","text":"Numerous studies have highlighted the pivotal role of visualization in enhancing the comprehension and retention of educational content.","type":"CONC"},{"children":[{"type":"INSG","text":"The interface introduces a layered, LLM-augmented design supporting on-demand concept generation, infinite drill-down navigation, and in-context information display.","label":"Interface Layered LLM Design","parentId":"n21","children":[],"id":"n22"},{"id":"n23","children":[],"parentId":"n21","table":{"cols":["Aspect","Ma and Chen System","Proposed System"],"rows":[{"label":"LLM Use","cells":["Automates extraction of concepts and relationships","Employs LLMs to generate concept maps"]},{"label":"Real Educational Context","cells":["Does not address use in real educational contexts","Addresses use with validation based on real student feedback"]},{"label":"Interactive UI/UX Design","cells":["Lacks production-ready interactive UI/UX design","Focuses on production-ready interactive UI/UX design"]},{"label":"Cognitive Overload","cells":["Overlooks cognitive overload from large, flat maps","Addresses via hierarchical drill-down navigation and embedded pedagogical content"]},{"label":"Content Alignment","cells":["Uses full course materials","Plans to incorporate RAG in future iterations"]}]},"text":"Our system, similar to Ma and Chen, uses LLMs for concept map generation but addresses interactive UI/UX design and cognitive overload.","label":"Current System vs Ma and Chen","type":"CMPR"},{"children":[],"id":"n24","type":"EXMP","label":"System Applied Courses","text":"The system was applied in Object-Oriented Programming and Data Structures, and UI Design and AI-Assisted Frontend Development university courses.","parentId":"n21"},{"id":"n25","children":[{"id":"n26","children":[],"parentId":"n25","label":"Main Map Functionality","text":"Each concept node could be expanded to explore subtopics, allowing students to see the “big picture” and access detailed content.","type":"DETL"}],"label":"Main Course Map Overview","text":"The Main Map of the Course functioned as a central, interactive overview of the entire curriculum, visually organizing key topics and their relationships.","parentId":"n21","type":"SUBC"},{"id":"n27","children":[{"children":[],"id":"n28","type":"INSG","label":"Information Panel Benefit","text":"This feature allowed learners to engage with the content without leaving the map interface, maintaining flow and minimizing distractions.","parentId":"n27"}],"parentId":"n21","text":"The Information Panel provided contextual details for each concept selected within the map, displaying concise explanations, examples, or supporting materials.","label":"Information Panel Details","type":"SUBC"},{"parentId":"n21","label":"Child Concept Map Expansion","text":"A Child Concept Map is a secondary, more focused map that expands upon a specific node from the main concept map.","type":"SUBC","id":"n29","children":[{"text":"Child maps support hierarchical learning by allowing users to progressively explore concepts at increasing levels of depth without overwhelming them.","label":"Child Map Purpose","parentId":"n29","type":"JUST","id":"n30","children":[]}]},{"id":"n31","children":[{"id":"n32","children":[],"parentId":"n31","text":"When a student reaches a terminal node and seeks further explanation, the system can generate an extended concept map based on the topic's semantic description.","label":"Dynamic Sub-map Generation","type":"DETL"},{"parentId":"n31","text":"This feature transforms the concept map into an adaptive learning environment capable of supporting personalized, self-directed exploration across limitless depth within a subject domain.","label":"Adaptive Learning Environment","type":"INSG","id":"n33","children":[]}],"parentId":"n21","label":"Infinite Drill-Down AI Exploration","text":"The Infinite Drill-Down AI-Based Domain Exploration feature enables learners to move beyond predefined content by dynamically generating new sub-maps using AI.","type":"SUBC"}],"id":"n21","type":"CONC","parentId":"n1","text":"This project explores the implementation and evaluation of an interactive, hierarchical concept map platform designed to enhance digital learning experiences.","label":"Interactive Hierarchical Concept Map Platform"},{"label":"AI-Driven Map Generation Process","text":"The system generates interactive concept maps by querying LLMs, such as GPT-4o-mini, based on provided course metadata and prompt-tuning commands.","parentId":"n1","type":"CONC","id":"n34","children":[{"type":"DETL","label":"Concept Map Development Steps","text":"The end-to-end concept map development process includes eight distinct steps, from course creation and initial generation to refinement and nested map creation.","parentId":"n34","children":[{"parentId":"n35","label":"Step 1: Course creation","text":"The instructor defines a new course by providing a course title, a free-form course description, and optional prompt-tuning instructions.","type":"DETL","id":"n36","children":[]},{"children":[],"id":"n37","type":"DETL","parentId":"n35","text":"The system queries the LLM to produce a draft map of key concepts and their relationships.","label":"Step 2: Initial map generation"},{"parentId":"n35","label":"Step 3: Full map regeneration","text":"If the initial map is unsatisfactory, instructors can clear it and regenerate a new one from scratch.","type":"DETL","id":"n38","children":[]},{"type":"DETL","parentId":"n35","label":"Step 4: Map refinement","text":"Users can ask a secondary LLM (e.g., ChatGPT) to rephrase or restructure parts of the map for better clarity or alignment.","children":[],"id":"n39"},{"type":"DETL","label":"Step 5: Concept information generation","text":"Clicking a concept opens an interactive panel that fetches descriptive content via the LLM.","parentId":"n35","children":[],"id":"n40"},{"type":"DETL","parentId":"n35","text":"Instructors can discard and regenerate concept information if needed.","label":"Step 6: Concept information regeneration","children":[],"id":"n41"},{"text":"Generated descriptions can be edited or enhanced using a separate LLM interface (e.g., ChatGPT).","label":"Step 7: Concept information refinement","parentId":"n35","type":"DETL","id":"n42","children":[]},{"type":"DETL","text":"Instructors can expand individual concepts by generating subordinate maps, enabling drill-down exploration.","label":"Step 8: Nested concept map generation","parentId":"n35","children":[],"id":"n43"}],"id":"n35"},{"id":"n44","children":[],"text":"The refinement process requires manual review of each map level and concept description to validate pedagogical relevance and accuracy.","label":"Quality and Coherence Assurance","parentId":"n34","type":"INSG"},{"children":[],"id":"n45","type":"JUST","parentId":"n34","label":"Refinement Process Time","text":"For highly customized courses, the refinement process can be time-consuming; however, AI-assisted generation significantly reduces the baseline effort."}]},{"label":"Limitations of Generic LLM Maps","text":"Several limitations emerge from relying solely on large language models (LLMs) without incorporating course-specific materials.","parentId":"n1","type":"CONC","id":"n46","children":[{"text":"Initial concept maps are generated based only on a course title and concise metadata, risking shallow or misaligned content in specialized domains.","label":"Metadata-Based Generation Risks","parentId":"n46","type":"SUBC","id":"n47","children":[{"children":[],"id":"n48","type":"DETL","text":"Future work will explore integrating retrieval-augmented generation (RAG) techniques to enable concept map generation based directly on actual course content.","label":"Future Work RAG","parentId":"n47"}]},{"text":"Although infinite drill-down capability is innovative, it also poses challenges like disorientation and topic drift.","label":"Infinite Drill-Down Challenges","parentId":"n46","type":"SUBC","id":"n49","children":[{"type":"DETL","parentId":"n49","text":"As users delve deeper into nested submaps, they may lose awareness of their location within the overall concept structure.","label":"Disorientation Risk","children":[],"id":"n50"},{"label":"Topic Drift Risk","text":"In the absence of clear semantic boundaries, LLMs may generate tangential or unrelated subtopics, resulting in conceptual divergence.","parentId":"n49","type":"DETL","id":"n51","children":[]},{"children":[],"id":"n52","type":"DETL","label":"Future UX Strategies","text":"Future work will explore introducing depth limits and developing UX strategies for clearer visual cues to help users maintain orientation.","parentId":"n49"}]},{"parentId":"n46","label":"Submap Consistency Issues","text":"Because submaps are generated independently, a concept node on a higher-level map may not reproduce its child nodes when opened in a dedicated submap.","type":"SUBC","id":"n53","children":[{"id":"n54","children":[],"label":"Algorithmic Consistency Support","text":"Scalable resolution for submap consistency will require algorithmic support and improved tooling across the concept hierarchy.","parentId":"n53","type":"DETL"}]}]},{"text":"The system features a lightweight, modular architecture that combines AI-driven content generation with interactive frontend visualization.","label":"AI Concept Map System Architecture","parentId":"n1","type":"CONC","id":"n55","children":[{"id":"n56","children":[],"parentId":"n55","label":"Python Backend","text":"The Python backend handles HTTP requests, interacts with the OpenAI GPT-4o-mini API, and stores course content in a file-based structure.","type":"DETL"},{"parentId":"n55","label":"Vis.js Frontend","text":"The frontend uses Vis.js to render dynamic, clickable concept maps, enabling content display and drill-down navigation.","type":"DETL","id":"n57","children":[]},{"id":"n58","children":[{"parentId":"n58","label":"LLM Prompt Instructions","text":"The prompt instructs the LLM to generate at least 15 nodes, define a single root concept, and create a tree-like hierarchical structure without cycles or dangling nodes.","type":"DETL","id":"n59","children":[]},{"children":[],"id":"n60","type":"DETL","parentId":"n58","text":"The prompt also requires formatting output as Vis.js code, labeling all edges with clear semantic relationships, ensuring domain-specific accuracy, and including a concrete output example.","label":"Detailed Prompt Requirements"},{"children":[],"id":"n61","type":"DETL","text":"The LLM response is cached as a plain text file, serving subsequent requests directly from the local file system to avoid redundant OpenAI API calls.","label":"Map Caching","parentId":"n58"}],"text":"Concept maps are generated by dynamically constructing and sending prompts to an LLM, such as GPT-4o-mini, driven by frontend input and course metadata.","label":"Prompt-Engineered Map Generation","parentId":"n55","type":"SUBC"},{"parentId":"n55","text":"The system generates individual concept pages as HTML fragments through targeted prompt engineering when a user selects a concept node.","label":"Prompt-Engineered Concept Pages","type":"SUBC","id":"n62","children":[{"id":"n63","children":[],"text":"The prompt instructs the model to generate valid HTML fragments using semantic tags, format code snippets with pre/code, and mathematical content with LaTeX/MathJax.","label":"HTML Generation Requirements","parentId":"n62","type":"DETL"}]},{"type":"SUBC","label":"Content Management Panel","text":"The Content Management Panel is a core instructor-facing tool enabling efficient oversight of all AI-generated concept map content.","parentId":"n55","children":[{"parentId":"n64","label":"Instructor Management Capabilities","text":"Instructors can create/manage courses, regenerate/refine maps, and customize individual concept pages using third-party LLMs for better alignment.","type":"DETL","id":"n65","children":[]}],"id":"n64"}]},{"label":"Evaluation: Student Feedback","text":"This section presents the design and results of a student survey evaluating the perceived effectiveness of AI-powered concept map interfaces.","parentId":"n1","type":"CONC","id":"n66","children":[{"text":"Hierarchical concept maps were developed for two courses at American University Kyiv, and a survey was administered to students.","label":"Survey Design Overview","parentId":"n66","type":"SUBC","id":"n67","children":[{"parentId":"n67","text":"Concept maps were developed for Object-Oriented Programming and Data Structures for first-year Bachelor of Software Engineering/AI and Data Science students.","label":"Course 1: OOP & Data Structures","type":"EXMP","id":"n68","children":[{"parentId":"n68","label":"Course 1 Content Count","text":"42 concept maps and 117 individual concept pages were generated and integrated into Course 1.","type":"STAT","id":"n69","children":[]},{"id":"n70","children":[],"parentId":"n68","text":"24 students participated in the survey for Course 1.","label":"Course 1 Survey Participants","type":"STAT"}]},{"parentId":"n67","text":"Concept maps were developed for UI Design and AI-Assisted Frontend Development for first-year Bachelor of Software Engineering and AI program students.","label":"Course 2: UI Design & AI Frontend","type":"EXMP","id":"n71","children":[{"parentId":"n71","label":"Course 2 Content Count","text":"27 concept maps and 128 concept pages were generated and refined for Course 2.","type":"STAT","id":"n72","children":[]},{"id":"n73","children":[],"text":"11 students participated in the survey for Course 2.","label":"Course 2 Survey Participants","parentId":"n71","type":"STAT"}]},{"label":"Total Survey Responses","text":"A total of 35 surveys were received from both courses.","parentId":"n67","type":"STAT","id":"n74","children":[]},{"id":"n75","children":[],"text":"The survey was proposed at the final part of the course as a means of recalling course content and evaluating the concept map’s effectiveness for structured review.","label":"Survey Administration","parentId":"n67","type":"DETL"},{"id":"n76","children":[],"text":"Questions assessed overall satisfaction, engagement, effectiveness for review/learning, and usefulness of drill-down navigation.","label":"Key Survey Questions","parentId":"n67","type":"DETL"}]},{"id":"n77","children":[{"type":"STAT","parentId":"n77","text":"Students reported an average satisfaction score of 8.91 out of 10 with their learning experience using the concept map app.","label":"Overall Satisfaction Score","children":[],"id":"n78"},{"id":"n79","children":[],"text":"Students rated the app’s usefulness for learning new content at an average of 8.31 out of 10.","label":"Learning Effectiveness Score","parentId":"n77","type":"STAT"},{"label":"Engagement & Enjoyment","text":"A large majority (91.4%) of students agreed that the app made learning more engaging or enjoyable.","parentId":"n77","type":"STAT","id":"n80","children":[]},{"id":"n81","children":[],"parentId":"n77","label":"Drill-Down Usefulness","text":"100% of students confirmed that the ability to click on concept names and navigate through nested maps was helpful.","type":"STAT"},{"children":[{"id":"n83","children":[],"parentId":"n82","label":"Both Equally Effective","text":"60% of students found both interactive concept maps and traditional materials equally effective for review and recall.","type":"STAT"},{"type":"STAT","label":"Preferred Interactive Maps","text":"34.3% of students preferred interactive concept maps for reviewing course material.","parentId":"n82","children":[],"id":"n84"},{"text":"Only 5.7% of students preferred text-based materials alone for reviewing course material.","label":"Preferred Text-Based Materials","parentId":"n82","type":"STAT","id":"n85","children":[]}],"id":"n82","type":"DETL","text":"Students expressed varying preferences for reviewing course material using interactive concept maps versus traditional materials.","label":"Preferred Review Methods","parentId":"n77"},{"id":"n86","children":[{"id":"n87","children":[],"parentId":"n86","text":"11 students mentioned appreciating the ability to click, navigate, and explore deeper levels of topics.","label":"Clickability and Depth Navigation","type":"DETL"},{"type":"DETL","label":"Visual Structure and Relationships","text":"9 students highlighted the clarity and usefulness of the visual concept map structure and topic relationships.","parentId":"n86","children":[],"id":"n88"}],"text":"Open-ended responses revealed clickability/depth navigation and visual structure/relationships between topics as major advantages.","label":"Most Useful Features","parentId":"n77","type":"DETL"},{"type":"DETL","text":"Students suggested improvements related to UI, current interactions, and additional functionalities.","label":"Suggested Improvements","parentId":"n77","children":[{"parentId":"n89","text":"7 students felt the app was already perfect or good enough, stating “everything is perfect” or “all is good”.","label":"App Perfect or Good","type":"STAT","id":"n90","children":[]},{"type":"STAT","text":"8 students recommended UI improvements, including design changes for a more pleasant visual side and a dark theme.","label":"UI Improvement Suggestions","parentId":"n89","children":[],"id":"n91"},{"type":"STAT","label":"Interaction Improvement Suggestions","text":"6 students recommended improvements in current interactions, citing issues with dragging, zooming, and scrolling the graph.","parentId":"n89","children":[],"id":"n92"},{"label":"Additional Functionality Ideas","text":"Various individual ideas were suggested, such as online collaboration, shared comments, quizzes, and the ability to ask questions.","parentId":"n89","type":"DETL","id":"n93","children":[]}],"id":"n89"},{"parentId":"n77","text":"High ratings across both courses suggest AI-generated maps are relevant for learning, and the hierarchical drill-down structure offers an effective human-computer interaction pattern.","label":"Evaluation Conclusion","type":"INSG","id":"n94","children":[]}],"label":"Survey Results Summary","text":"The analysis shows high student satisfaction and perceived effectiveness, quantitatively confirming that the interactive and visual structure of concept maps was well-received.","parentId":"n66","type":"SUBC"}]},{"children":[{"id":"n96","children":[],"label":"System as Intelligent Textbook","text":"The system positions itself as a practical implementation of the intelligent textbook paradigm, augmenting content delivery and navigational structure for student-centered learning.","parentId":"n95","type":"INSG"},{"children":[],"id":"n97","type":"DETL","parentId":"n95","label":"Evaluation Results Summary","text":"Evaluation results, based on 69 AI-generated concept maps and 245 unique concept descriptions across two undergraduate computer science courses, confirm the system's educational value."},{"label":"Key Findings Reinforcement","text":"Feedback from 35 student surveys underscored the potential of integrating AI-generated maps into intelligent textbooks and online courses to enhance comprehension, engagement, and structured review.","parentId":"n95","type":"INSG","id":"n98","children":[]},{"children":[{"id":"n100","children":[],"text":"One key direction is the integration of retrieval-augmented generation (RAG) techniques to allow the LLM to incorporate course-specific materials into the generation process.","label":"RAG Integration for Content","parentId":"n99","type":"DETL"},{"children":[],"id":"n101","type":"DETL","parentId":"n99","text":"To improve usability and mitigate disorientation, future enhancements will include research on depth-limiting mechanisms and UX improvements for visual context and navigational cues.","label":"Usability Enhancements"},{"parentId":"n99","text":"Algorithmic methods and instructor-facing tools will be developed to support structural validation and map coherence across different levels of hierarchy.","label":"Submap Consistency Resolution","type":"DETL","id":"n102","children":[]},{"children":[],"id":"n103","type":"DETL","label":"Refinement Process Integration","text":"The refinement process will be more tightly integrated into the instructor-facing UI for seamless editing and regeneration of maps and concept pages within the same workflow.","parentId":"n99"},{"parentId":"n99","label":"Admin Dashboard Extension","text":"The admin dashboard will be extended to provide broader control and monitoring of content quality.","type":"DETL","id":"n104","children":[]},{"id":"n105","children":[],"text":"Additional research will explore the system’s effectiveness in other domains such as mathematics, management, and postgraduate software engineering education.","label":"Other Domain Exploration","parentId":"n99","type":"DETL"},{"type":"DETL","text":"The implementation of agentic AI workflows, where multiple autonomous agents coordinate multi-step concept map construction and refinement, will be explored.","label":"Agentic AI Workflows","parentId":"n99","children":[],"id":"n106"}],"id":"n99","type":"SUBC","label":"Future Work Directions","text":"Future work will address current limitations identified in the system’s architecture and usage, focusing on several key directions.","parentId":"n95"}],"id":"n95","type":"CONC","parentId":"n1","text":"This study presented the design and implementation of an AI-driven system for generating interactive hierarchical concept maps for digital learning environments and intelligent textbooks.","label":"Conclusion and Future Work"},{"children":[],"id":"n107","type":"DETL","parentId":"n1","text":"The author thanks American University Kyiv instructors Roman Tymoshuk, Andrii Tsabanov, and Ivan Danilov for reviewing and integrating the concept maps into the learning process.","label":"Acknowledgements"},{"label":"Generative AI Declaration","text":"The author used ChatGPT-4 and Grammarly to check grammar, spelling, improve writing style, paraphrase, and reword, taking full responsibility for the content.","parentId":"n1","type":"DETL","id":"n108","children":[]}],"label":"AI-driven Interactive Hierarchical Concept Maps","text":"This paper explores the design and implementation of AI-driven interactive concept maps as components of intelligent textbooks and digital learning environments.","type":"APEX"},"contentType":"Explainer","sourceType":"text","sourceUrl":null,"sharedAt":{"_seconds":1780211475,"_nanoseconds":461000000},"title":"AI-driven Interactive Hierarchical Concept Maps"}