Evaluating Adaptive Hypermedia Authoring while Teaching Adaptive Systems

1
Evaluating Adaptive Hypermedia Authoring while
Teaching Adaptive Systems

• Alexandra Cristea
• a.i.cristea_at_tue.nl
• http//wwwis.win.tue.nl/alex/

2
LAOS
3
Goal point of view evaluation
4
USI point of view evaluation
5
Procedure

• Background knowl. of adaptive syst. UM, AH
  focus
• Exercises CM building on paper
• Theoretical framework (LAOS, LAG)
• Exercises writing LAOS rules on paper
• Course evaluation questionnaire anonymous,
  individual
• Installing, experimenting creating MOT
  presentation (DM, GM) on paper (AM, UM, PM) in
  groups of 2-4
• Project evaluation questionnaire anonymous,
  individual
• MOT system evaluation questionnaire anonymous,
  individual and free evaluation groups
• Student grading

6
Student spread

• Backgrounds
• art, psychology, literature, economics, physics,
  computer science, engineering, mathematics
• Nationalities
• Dutch, Belgium, Greek, Indian, USA, China,
  Belarus, Israel, Indonesia, Chili
• Genders
• 9 females, rest males
• Previous degrees
• BA, MA, ME, M Sc., Lic., B Sc.

7
Theme

• any within Adaptive Systems
• selected
• CM for adaptive systems
• Complex adaptive systems
• ITS
• Introduction to AI

8
(No Transcript)
9
(No Transcript)
10
Student grades for project presentation, MOT
analysis and MOT implementation
11
Course evaluation
12
Project evaluation
13
(No Transcript)
14
Difference domain lesson

• students claimed they understood (Mean
  3.46 Standard Deviation 1.20)
• and they find it very useful (Mean
  3.83 Standard Deviation 0.389)

15
Reuse of personal, others material

• considered useful
• comparison useful to see others CM/lessons
  with useful to reuse ones own 60,6
  correlation related

16
automatic translations DM-GM

• used
• important
• although AEH authoring complex, many layers
  simplifications and automatic transformations are
  possible and can help the beginner author

17
Use of different attributes

• mean 2.19 and standard deviation 1.33 actual
  responses from
• 0 no other attributes used to
• 4 almost only other attributes used

18
Collaboration Requirements in MOT

• already possible
• tools for interconnectivity between material of
  different authors
• necessary
• flag or notify about currently-being-edited
  courses and lessons, so that other authors
  shouldnt link to perishable material.
• advanced management groups of authors
• Services for notification, communication (about
  concepts to which there are links but the
  contents disappeared, etc.)

19
Semantics in MOT

• MOT is based on LAOS and on semantic web
  directives
• necessary
• more explicit ontologies,
• synonyms - to identify semantic overlaps

20
User Model in MOT

• dynamic model of the user's history
• user model variables should be also user writable
  (flag)
• retrieved by prompting the user
• Specified where? AM? UM?

21
Adaptation Issues in MOT

• ADAPT EAH patterns of adaptive behavior
• students feedback on adaptation rules
• a better definition for the next-concept
  concept
• translating automatically link types into rules
• avoiding loops
• other language constructs for all
• showing exercises hiding theory

22
Conclusions

• 1st real-class setting experimental results for
  MOT
• MOT AEH authoring system
• MOT 2/5 of LAOS framework
• Hints for possible improvements of MOT
• Results confirmed some hypotheses on LAOS
  framework for (adaptive) authoring of adaptive
  hypermedia for education