Augmenting Digital Textbooks with Reusable Smart Learning Content: Solutions and Challenges
- 1. Augmenting Digital Textbooks with Reusable Smart Learning Content: Solutions and Challenges Jordan Barria-Pineda, Arun Balajiee Lekshmi Narayanan, Peter Brusilovsky iTextbooks’22 Workshop @ AIED’22
- 2. Current approaches for Intelligent Textbooks AUTHOR Textbook content
- 3. Current approaches for Intelligent Textbooks AUTHOR Textbook content Learning content
- 4. Current approaches for Intelligent Textbooks AUTHOR Textbook content Learning content
- 5. Current approaches for Intelligent Textbooks AUTHOR Textbook content Learning content
- 6. Current approaches for Intelligent Textbooks AUTHOR Textbook content Learning content
- 7. Example: Runestone interactive books
- 8. Our vision
- 9. Our vision
- 10. Our vision
- 11. Our vision Crowdsourcing, Interoperability (e.g, LTI)
- 12. Online Reading System: Reading Mirror
- 13. Case 1: Educational video recommendations Concept extraction and initial relevancy filter Collection of video candidates Textual representation of the videos Reading-Video similarity calculation Recommenda- tions presentation in the UI
- 14. Case 1: Educational video recommendations Concept extraction and initial relevancy filter Collection of video candidates Textual representation of the videos Reading-Video similarity calculation Recommenda- tions presentation in the UI Thaker, K.M., Brusilovsky, P., He, D. (2018) Concept enhanced content representation for linking educational resources.
- 15. Case 1: Educational video recommendations Concept extraction and initial relevancy filter Collection of video candidates Textual representation of the videos Reading-Video similarity calculation Recommenda- tions presentation in the UI https://youtube-dl.org/
- 16. Case 1: Educational video recommendations Concept extraction and initial relevancy filter Collection of video candidates Textual representation of the videos Reading-Video similarity calculation Recommenda- tions presentation in the UI Simple textual matching of transcripts’ keyphrases and the concepts extracted from the textbook in the first step.
- 17. Case 1: Educational video recommendations Concept extraction and initial relevancy filter Collection of video candidates Textual representation of the videos Reading-Video similarity calculation Recommenda- tions presentation in the UI tf-idf
- 18. Concept extraction and initial relevancy filter Collection of video candidates Textual representation of the videos Reading-Video similarity calculation Recommenda- tions presentation in the UI Case 1: Educational video recommendations
- 19. Concept extraction and initial relevancy filter Collection of video candidates Textual representation of the videos Reading-Video similarity calculation Recommenda- tions presentation in the UI Case 1: Educational video recommendations
- 20. Case 2: Smart learning content recommendations
- 21. Case 2: Smart learning content recommendations
- 22. Case 2: Smart learning content recommendations
- 23. Case 2: Smart learning content recommendations
- 24. Case 2: Smart learning content recommendations
- 25. Case 2: Smart learning content recommendations
- 26. Case 2: Smart learning content recommendations
- 27. Other related educ. recommendations 1. Recommendations to external resources (Rahdari et al. 2020)
- 28. 1. Recommendations to external resources (Rahdari et al. 2020) 2. Recommendations to other textbooks (Thaker et al. 2020) Other related educ. recommendations
- 29. 1. Recommendations to external resources (Rahdari et al. 2020) 2. Recommendations to other textbooks (Thaker et al. 2020) 3. Recommendations of learning content for instructional design (Albó et al. 2019; Chau et al. 2017; 2018) Other related educ. recommendations
- 30. 1. Recommendations to external resources (Rahdari et al. 2020) 2. Recommendations to other textbooks (Thaker et al. 2020) 3. Recommendations of learning content for instructional design (Albó et al. 2019; Chau et al. 2017; 2018) 4. Recommendations to video courses Other related educ. recommendations
- 31. 1. Recommendations to external resources (Rahdari et al. 2020) 2. Recommendations to other textbooks (Thaker et al. 2020) 3. Recommendations of learning content for instructional design (Albó et al. 2019; Chau et al. 2017; 2018) 4. Recommendations to video courses 5. In this work, also, recommendations to interactive book exercises! Other related educ. recommendations 1. B Rahdari, P Brusilovsky, K Thaker, J Barria-Pineda. Using knowledge graph for explainable recommendation of external content in electronic textbooks iTextbooks@ AIED, 2020 2. Khushboo Thaker, Lei Zhang, Daqing He and Peter Brusilovsky "Recommending Remedial Readings Using Student's Knowledge state" (EDM 2020) 3. Albó, L., Barria-Pineda, J., Brusilovsky, P., Hernández-Leo, D. (2019). Concept-Level Design Analytics for Blended Courses. https://doi.org/10.1007/978-3-030-29736-7_40
- 32. Challenges 1. Scaling the system by the type of smart content allocation, potentially making it automatic instead of static allocation as noted in prior work (Alpizar-Chacon et al. 2021)
- 33. Challenges 1. Scaling the system by the type of smart content allocation, potentially making it automatic instead of static or semi- automatic allocation as noted (Alpizar-Chacon et al. 2021) 2. Allocation that adapts to the teacher’s understanding of the course in a finer grained way – previous efforts have been done by following coarse-grained units formed from different sections (Chau et al. 2017; 2018) or concepts (Rahdari et al. 2020). 1. Alpizar-Chacon, Isaac; Barria-Pineda, Jordan; Akhuseyinoglu, Kamil; Sosnovsky, Sergey; Brusilovsky, Peter. Integrating textbooks with smart interactive content for learning programming. iTextbooks @ AIED 2021 2. Chau, H., Barria-Pineda, J., Brusilovsky, P. (2018). Learning Content Recommender System for Instructors of Programming Courses. AIED 2018. 3. Hung Chau, Jordan Barria-Pineda, and Peter Brusilovsky. 2017. Content Wizard: Concept-Based Recommender System for Instructors of Programming Courses. (UMAP 2017).
- 34. Challenges 1. Scaling the system by the type of smart content allocation, potentially making it automatic instead of static or semi- automatic allocation as noted in prior work (Alpizar-Chacon et al. 2021) 2. Allocation that adapts to the teacher’s understanding of the course in a fine-grained way is allocated as coarse-grained units formed from different sections (Chau et al. 2017; 2018) and as demonstrated by wiki recommendations (Rahdari et al. 2020) in e-textbooks. 3. Adapt to the learner state
- 35. Discussion and Future work 1. Dynamic SLC at different levels of granularity
- 36. Discussion and Future work 1. Dynamic SLC at different levels of granularity 2. Reader’s control over the smart content curation
- 37. Discussion and Future work 1. Dynamic SLC at different levels of granularity 2. Reader’s control over the smart content curation 3. Passive recommendations as another option
- 38. Discussion and Future work 1. Dynamic SLC at different levels of granularity 2. Reader’s control over the smart content curation 3. Passive recommendations as another option 4. Learner-sourced recommendations
- 39. Discussion and Future work 1. Dynamic SLC at different levels of granularity 2. Reader’s control over the smart content curation 3. Passive recommendations as another option 4. Learner-sourced recommendations 5. Overcoming challenges identified with their possible solutions
- 40. Discussion and Future work 1. Dynamic SLC at different levels of granularity 2. Reader’s control over the smart content curation 3. Passive recommendations as another option 4. Learner-sourced recommendations 5. Overcoming challenges identified with their possible solutions 6. Evaluation of the approaches through a “live” classroom study (pending analysis)
- 41. Conclusions 1. Integrating multiple SLCs into an eTextbook – making it a “intelligent” textbook with recommendations for the reader. 2. Present a system that is flexible with the possibility of interchangeable learning platform (eTextbook system) 3. Identify the challenges and discuss solutions
- 42. Q & A Thanks for your attention! Augmenting Digital Textbooks with Reusable Smart Learning Content: Solutions and Challenges Jordan Barria-Pineda, Arun Balajiee Lekshmi Narayanan, Peter Brusilovsky iTextbooks’22 Workshop @ AIED’22