INFSCI 2955 Adaptive Web Systems Session 2-1: Adaptive Navigation Support

1. INFSCI 2955Adaptive Web SystemsSession 2-1: Adaptive Navigation Support Peter Brusilovsky School of Information Sciences University of Pittsburgh, USA http://www.sis.pitt.edu/~peterb/2955-092/

2. Outline • Adaptive hypermedia • Where? • Why? • What? • How? • Adaptive navigation support • Approaches • Mechanisms

3. Adaptive hypermedia: Why? • Different people are different • Individuals are different at different times • "Lost in Hyperspace” • Large variety of users • Variable characteristics of the users • Large hyperspace

4. Where it can be useful? • Web-based Education • ITS, tutorials, Web courses • On-line information systems • classic IS, information kiosks, encyclopedias • E-commerce • Museums • virtual museums and handheld guides • Information retrieval systems • classic IR, filtering, recommendation, services

5. Where it can be useful? • Web-based education • ELM-ART, AHA!, KBS-Hyperbook, MANIC • On-line information systems • PEBA-II, AHA!, AVANTI, SWAN, ELFI, ADAPTS • E-commerce • Tellim, SETA, Adaptive Catalogs • Virtual and real museums • ILEX, HYPERAUDIO, HIPS, Power, Marble Museum • Information retrieval, filtering, recommendation • SmartGuide, Syskill & Webert, IfWeb, SiteIF, FAB, AIS

6. Adapting to what? • Knowledge: about the system and the subject • Goal: local and global • Interests • Background: profession, language, prospect, capabilities • Navigation history

7. What can be adapted? • Hypermedia = Pages + Links • Adaptive presentation • content adaptation • Adaptive navigation support • link adaptation

9. Adaptive navigation support: goals • Guidance: Where I can go? • Local guidance (“next best”) • Global guidance (“ultimate goal”) • Orientation: Where am I? • Local orientation support (local area) • Global orientation support (whole hyperspace)

10. Adaptive navigation support • Direct guidance • Restricting access • Removing, disabling, hiding • Sorting • Annotation • Generation • Similarity-based, interest-based • Map adaptation techniques

11. Example: Adaptive annotation Annotations for topic states in Manuel Excell: not seen (white lens) ; partially seen (grey lens) ; and completed (black lens)

12. 1. Concept role 2. Current concept state Example: Adaptive annotation 4 3 2 v 1 3. Current section state 4. Linked sections state

13. Adaptive navigation support: major goals and relevant technologies

14. What can be adapted: links • Contextual links (“real hypertext”) • Local non-contextual links • Index pages • Table of contents • Links on local map • Links on global map

15. Link types and technologies

16. Some Popular ANS Mechanisms • Relevance-based navigation support • Expresses link relevance to user interests • Mechanism is similar to adaptive search, but interface is different • Prerequisite-based navigation support • Progress-based navigation support • A mechanism is different from interface • Same mechanism, different presentation

17. Relevance-based navigation support • Sorting • HYPERFLEX, 1993 • Annotation (icons) • Siskill & Webert 1996 • Annotation (font) • ScentTrails 2003 • Annotation (icons) + Sorting • YourNews, 2007

18. Evaluation of sorting • HYPERFLEX: IR System • adaptation to user search goal • adaptation to “personal cognitive map” • Number of visited nodes decreased (significant) • Correctness increased (not significant) • Goal adaptation is more effective • No significant difference for time/topic

19. Syskill & Webert vs. ScentTrails

20. Content-Based Link Annotation in YourNews

21. Prerequisite Mechanism: ISIS-Tutor • An adaptive tutorial for CDS/ISIS/M users • Domain knowledge: concepts and constructs • Concept-Based Hyperspace : • Description of concepts and constructs • Examples and problems indexed with concepts (could be used in an exploratory environment) • Link annotation with colors and marks • Removing links to “not relevant” pages

22. Concepts, examples, and problems Example 1 Concepts Examples Concept 4 Example 2 Example M Concept 1 Concept N Problems Concept 2 Problem 1 Concept 5 Problem 2 Problem K Concept 3

23. Indexing and navigation Example 1 Concepts Examples Concept 4 Example 2 Example M Concept 1 Concept N Problems Concept 2 Problem 1 Concept 5 Problem 2 Problem K Concept 3

24. Student modeling and adaptation • States for concepts: • not ready (may be hidden) • ready (red) • known (green) • learned (green and ‘+’) • State for problems/examples: • not ready (may be hidden) • ready (red) • solved (green and ‘+’)

25. Sample index page (annotation)

26. Sample index page (hiding)

27. ISIS-Tutor: Evaluation • 26 first year CS students of MSU • 3 groups: • control (no adaptation) • adaptive annotation • adaptive annotation + hiding • Goal: 10 concepts (of 64), 10 problems, all examples

28. Experiment design

29. Results: performance Adaptive annotation makes navigation more efficient

30. The value of adaptivity: steps

31. The value of adaptivity: repetitions

32. Results: recall No effect on recall

33. To hide or not to hide? Additional value of hiding is unclear. Users prefer “freedom”

34. InterBook: Prerequisite-based navigation in ET • “Knowledge behind pages” • Structured electronic textbook (a tree of “sections”) • Sections indexed by domain concepts • Outcome concepts • Background concepts • Concepts are externalized as glossary entries • Shows educational status of concepts and pages

35. Sections and concepts Textbook Chapter 1 Chapter 2 Section 1.2 Section 1.1 Section 1.2.1 Section 1,2,2

36. Sections and concepts Textbook Domain model Concept 4 Chapter 1 Concept 1 Concept n Chapter 2 Concept 2 Section 1.2 Section 1.1 Concept m Concept 3 Section 1.2.1 Section 1,2,2

37. Indexing and navigation Textbook Domain model Concept 4 Chapter 1 Concept 1 Concept n Chapter 2 Concept 2 Section 1.2 Section 1.1 Concept m Concept 3 Section 1.2.1 Section 1.2.2 Prerequisite and Outcome Links Book Structure

39. Glossary view

40. Navigation in InterBook • Regular navigation • Linear (Continue/Back) • Tree navigation (Ancestors/Brothers) • Table of contents • Concept-based navigation • Glossary (concept -> section) • Concept bar (section -> concept) • Hypertext links (section -> concept)

41. Adaptive navigation support • Adaptive annotations • Links to sections • Links to concepts • Pages • Adaptive sorting • Background help • Direct guidance (course sequencing) • Teach Me

42. User modeling • Overlay student model for domain concepts • Knowledge states for each concept • unknown (never seen) • known (visited some page) • learned (passed a test) • Information for sections • visited/not visited • time spent • Information for tests: last answers

43. Adaptive annotation • Educational status for concept unknown known learned • Educational status for sections not ready to be learned ready to be learned suggested

44. 1. State of concepts (unknown, known, ..., learned) 2. State of current section (ready, not ready, nothing new) 3. States of sections behind the links (as above + visited) Adaptive annotation in InterBook 3 2 v 1

45. Bookshelves and books

46. Book view

47. Backward learning: “help” and “teach this”

48. InterBook: Evaluation • Goal: to find a value of adaptive annotation • Electronic textbook about ClarisWorks • 25 undergraduate teacher education students • 2 groups: with/without adaptive annotation • Format: exploring + testing knowledge • Full action protocol

49. Results • No overall difference in performance • Sequential navigation dominates ...but ... • Adaptive annotation encourage non-sequential navigation • The effect of “following green” • The adaptation mechanism works well

50. Preferred ways of navigation