A powerful set of educational tools has emerged over the last decade with the rise in the adoption of online adaptive learning content. An increasingly popular tool in this space is the “intelligent textbook” as a platform to support and distribute content for e-learning, given its re- semblance with real-life physical books. Existing efforts in this direction include the development of digital textbooks where both textual con- tent and interactive learning activities (i.e., examples, problems, etc.) are carefully handcrafted by the authors so that they are perfectly placed to follow the knowledge acquisition-practice flow. However, this approach is very time-consuming, and it requires the work of high-expertise authors. In this work, we suggest and discuss a scalable solution: we take existing digital textbooks and augment them by using repositories of existing on- line learning material associated with the subject matter. We present our current work in this direction and discuss challenges and opportunities for the future work.
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
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
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
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