Downloaded 18 times
Uploaded byPeter Brusilovsky
IUI2017 SmartLearn keynote: Intelligent Interfaces for Open Social Student Modeling
The document discusses intelligent interfaces for open social student modeling, highlighting technologies like adaptive navigation support and open social student models that aim to enhance user performance, motivation, and retention in education. It emphasizes the use of topic-based adaptations, social navigation, and progress visualization to engage students and improve learning outcomes. Various methodologies and tools, such as mastery grids and quizpack, are examined to illustrate their effectiveness in fostering individualized and social learning experiences.
More Related Content
Similar to IUI2017 SmartLearn keynote: Intelligent Interfaces for Open Social Student Modeling
IUI2017 SmartLearn keynote: Intelligent Interfaces for Open Social Student Modeling
- 1. Intelligent Interfaces for OpenSocial Student Modeling Peter Brusilovsky Sharon Hsiao,Tomek Loboda, Julio Guerra, Jordan Barria-Pineda PAWS Lab, University of Pittsburgh
- 2. Overview • Goals – Whywe are doing it? • Open Student Models – From ANS to OSM • Open Social Student Models – QuizMap, Progressor, Progressor+ • Mastery Grids – Topic-level OSLM in Mastery Grids – Concept-level OSLM in Mastery Grids
- 3. From Goals toTechnologies • Technologies –Adaptive Navigation Support –Open Student Models –Open Social Student Modeling • Why to use it –Increase user performance –Increase motivation and retention
- 4. Targets Engaged • AdaptiveNavigation Support • Topic-based Adaptation • Open Student Modeling • Social Navigation and Comparison • Open Social Student Modeling • Social Educational Progress Visualization • Multiple Content Types • Open Source • Concept-Based Adaptation
- 5. Adaptive Link Annotation:InterBook 1. Concept role 2. Current concept state 3. Current section state 4. Linked sections state 4 3 2 1 √
- 6. Questions of the current quiz,served by QuizPACK List of annotated links to all quizzes available for a student in the current course Refresh and help icons QuizGuide = Topic-Based ANS
- 7. Topic-Based Adaptation Concept A Concept B Concept C Eachtopic is associated with a number of educational activities to learn about this topic Each activity classified under 1 topic
- 8. QuizGuide: Adaptive Annotations •Target-arrow abstraction: – Number of arrows – level of knowledge for the specific topic (from 0 to 3). Individual, event-based adaptation. – Color Intensity – learning goal (current, prerequisite for current, not-relevant, not-ready). Group, time- based adaptation. Topic–quiz organization:
- 9.
- 10. QuizGuide: Motivation Average activity 0 50 100 150 200 250 300 20022003 2004 Average num. of sessions 0 5 10 15 20 2002 2003 2004 Average course coverage 0% 10% 20% 30% 40% 50% 60% 2002 2003 2004 Within the same class QuizGuide session were much longer than QuizPACK sessions: 24 vs. 14 question attempts at average. Average Knowledge Gain for the class rose from 5.1 to 6.5
- 11. • Topic-Based interfaceorganization is familiar, matches the course organization, and provides a compromise between too-much and too-little • Two-way adaptive navigation support guides to the right topic • Open student model provides clear overview of the progress Topic-Based ANS: Success Recipes
- 12. Targets Engaged Adaptive NavigationSupport Topic-based Adaptation Open Student Modeling • Social Navigation and Comparison • Open Social Student Modeling • Social Educational Progress Visualization • Multiple Content Types • Open Source • Concept-Based Adaptation
- 13. Social Navigation • Concept-basedand topic-based navigation support work well to increase success and motivation • Knowledge-based approaches require some knowledge engineering – concept/topic models, prerequisites, time schedule • In our past work we learned that social navigation – “wisdom” extracted from the work of a community of learners – might replace knowledge-based guidance • Social wisdom vs. knowledge engineering
- 14. Knowledge Sea –Social Navigation Farzan, R. and Brusilovsky, P. (2005) Social navigation support through annotation-based group modeling. 10th International User Modeling Conference Lecture Notes in Artificial Intelligence, vol. 3538. Berlin: Springer Ve
- 15. Open Social StudentModeling • Motivation – Combine benefits of Open Student Models with social navigation and social comparisons • Key steps – Assume simple topic-based design – Show topic- and content- level knowledge progress of a student in contrast to the progress of the class – The design should guide students to most appropriate topics and content • Main challenge – How to design the interface to show student and class progress over topics? – We went through several attempts…
- 16.
- 17.
- 18.
- 19. • Topic organizationshould follow the natural progress or topics in the course • Clear comparison between “me” and “group” • Ability to compare with individual peers, not only the group • Privacy management OSLM: Success Recipes
- 20. The Value ofOSLM 205.73 113.05 80.81 125.5 0 50 100 150 200 250 Attempts Progressor QuizJET+IV QuizJET+Portal JavaGuide 68.39% 71.35% 42.63% 58.31% 0.00% 20.00% 40.00% 60.00% 80.00% Success Rate Progressor QuizJET+IV QuizJET+Portal JavaGuide
- 21. The Mechanism ofSocial Guidance stronger students left the traces for weaker ones to follow 21Time Topics
- 22.
- 23. Targets Engaged Adaptive NavigationSupport Topic-based Adaptation Open Student Modeling Social Navigation and Comparison Open Social Student Modeling Social Educational Progress Visualization • Multiple Content Types • Open Source • Concept-Based Adaptation
- 24. Progressor+ OSLM fortwo types of content • macro- and micro- comparisons (group or peers) 24
- 25. Students Spent MoreTime in Progressor+ Quiz =: 5 hours Example : 5 hours 20 mins25 60.04 150.19 224.7 296.9 69.52 121.23 110.66 321.1 0 50 100 150 200 250 300 350 400 QuizJET JavaGuide Progressor Progressor+ Total time spent (minutes) Quiz Example
- 26. Students Achieved HigherSuccess Rate 26 42.63% 58.31% 68.39% 71.20% 0.00% 20.00% 40.00% 60.00% 80.00% QuizJET JavaGuide Progressor Progressor+ Success Rate p<.01
- 27.
- 28. Mastery Grids: ContentAccess 28
- 29. Mastery Grids: Groupand Peer OSLM 29
- 30. MG flexibility • Parametersto set the visualization: – show hide toolbar or any of its elements – set the (sub) groups: top N, other sub groups – preset values (for example load individual view by default) – enable/disable recommendation • Parameters can be specified by group or by user
- 31. Mastery Grids EngageMore 31 0 10 20 30 40 50 60 Problems Solved 0 5 10 15 20 25 30 35 40 45 50 Examples Viewed And social comparison (OSSM) features strengthen the effect
- 32. OSSM Engages Persistently 32 10 15 20 25 30 PART1 PART 2 Activity by Session OSM OSSM Step-wise regression: being in the OSSM group means an increase of about 30 activities, as compared to being in the OSM group.
- 33. OSSM Group BecomesMore Effective • Instructional Effectiveness (Paas & Van Merriënboer, 1993) Relates performance in problems and time spent 33 -0.4 -0.2 0 0.2 PART 1 PART 2 Effectiveness Score OSSM OSM
- 34. Targets Engaged Adaptive NavigationSupport Topic-based Adaptation Open Student Modeling Social Navigation and Comparison Open Social Student Modeling Social Educational Progress Visualization Multiple Content Types Open Source • Concept-Based Adaptation
- 35. Concept-Based Student Modeling Example2 Example M Example 1 Problem 1 Problem 2 Problem K Concept 1 Concept 2 Concept 3 Concept 4 Concept 5 Concept N Examples Problems Concepts
- 36. These cells (firstrow) shows your progress in the topics of the course This bar chart shows your progress in the concepts of the course Each topic has several concepts associated to it. Mouseover a topic to highlight its concepts This bar chart (upside-down) shows the average progress of the rest of the class on the concepts Middle row shows the difference between your progress and the progress of the group Third row shows the progress of the group in blue Concept level OSLM
- 37. An overlayed paneopens indicating which topic you are inspecting (in this case the topic "Comparisons") The concepts within the selected topic are highlighted
- 38. Mousing over this activity Conceptsin the selected activity are highlighted This gauge estimates the how much you can learn in the selected activity. You will probably learn more in activities that have more new concepts See more in IUI 2017 Demo! "Concept-Level Knowledge Visualization for Supporting Self- Regulated Learning"
- 39. Targets Engaged Adaptive NavigationSupport Topic-based Adaptation Open Student Modeling Social Navigation and Comparison Open Social Student Modeling Social Educational Progress Visualization Multiple Content Types Open Source Concept-Based Adaptation
- 40. Acknowledgements • Joint workwith – Sergey Sosnovsky – Sharon Hsiao – Julio Guerra – Jordan Barria-Pineda • NSF Grants – EHR 0310576 – IIS 0426021 – CAREER 0447083 • ADL “PAL” grant to build Mastery Grids
- 41. Read About It! •Brusilovsky, P., Sosnovsky, S., and Yudelson, M. (2009) Addictive links: The motivational value of adaptive link annotation. New Review of Hypermedia and Multimedia 15 (1), 97-118. • Brusilovsky, P., Hsiao, I.-H., and Folajimi, Y. (2011) QuizMap: Open Social Student Modeling and Adaptive Navigation Support with TreeMaps. Proceedings of 6th European Conference on Technology Enhanced Learning (ECTEL 2011), pp. 71-82 • Hsiao, I.-H., Bakalov, F., Brusilovsky, P., and König-Ries, B. (2013) Progressor: social navigation support through open social student modeling. New Review of Hypermedia and Multimedia • Brusilovsky, P., Somyurek, S., Guerra, J., Hosseini, R., Zadorozhny, V., and Durlach, P. (2016) Open Social Student Modeling for Personalized Learning. IEEE Transactions on Emerging Topics in Computing 4 (3), 450-461. • Jordan, B.-P., Guerra, J., Huang, Y., and Brusilovsky, P. (2017) Concept-Level Knowledge Visualization for Supporting Self-Regulated Learning. In: Proceedings of Companion of the 22nd International Conference on Intelligent User Interfaces (IUI '17), Limassol, Cyprus, ACM, pp. 141-144 also available at https://doi.org/10.1145/3030024.3038262.