Presentation is loading. Please wait.

Presentation is loading. Please wait.

/ faculty of mathematics and informatics TU/e eindhoven university of technology 1 Towards Generic Adaptive Systems: Analysis of a Case Study Licia Calvi.

Similar presentations


Presentation on theme: "/ faculty of mathematics and informatics TU/e eindhoven university of technology 1 Towards Generic Adaptive Systems: Analysis of a Case Study Licia Calvi."— Presentation transcript:

1 / faculty of mathematics and informatics TU/e eindhoven university of technology 1 Towards Generic Adaptive Systems: Analysis of a Case Study Licia Calvi & Alexandra Cristea Databases & Hypermedia Group, Department of Informatics AH’02: May 29-31, 2002, Malaga

2 / faculty of mathematics and informatics TU/e eindhoven university of technology 2 Keywords Generic AS XML AHA!

3 / faculty of mathematics and informatics TU/e eindhoven university of technology 3 Index Motivation & background AHA! & beyond Concept-mapping paradigm New Adaptation Rules: How to Augment the Adaptation Engine Implementing New Rules in the current AHA! Problems & need of checking mechanisms Future directions Conclusion

4 / faculty of mathematics and informatics TU/e eindhoven university of technology 4 Index Motivation & background AHA! & beyond Concept-mapping paradigm New Adaptation Rules: How to Augment the Adaptation Engine Implementing New Rules in the current AHA! Problems & need of checking mechanisms Future directions Conclusion

5 / faculty of mathematics and informatics TU/e eindhoven university of technology 5 Ideas & Motivation AH author can separate w. difficulty: – links vs. concepts; –adaptive navigation vs. a. presentation & –carefully design a synchronous system a better way to look at AH authoring pb: –combination of CM paradigm for course narrative & –several new adaptation rules

6 / faculty of mathematics and informatics TU/e eindhoven university of technology 6 Method analyze AHA! –for general observations on AHS & –improvement suggestions for AHA! suggest a concept-based AHS structure extend rule-based overlay method for user-adaptation  another step towards flexible generic-purpose AH

7 / faculty of mathematics and informatics TU/e eindhoven university of technology 7 Index Motivation & background AHA! & beyond Concept-mapping paradigm New Adaptation Rules: How to Augment the Adaptation Engine Implementing New Rules in the current AHA! Problems & need of checking mechanisms Future directions Conclusion

8 / faculty of mathematics and informatics TU/e eindhoven university of technology 8 A few words on AHA! well-known system AH pioneer (1 st version: 1996/97) & domain benchmark power & popularity due to simplicity

9 / faculty of mathematics and informatics TU/e eindhoven university of technology 9 AHA! adaptation methods 1.  page = concept, showed/not acc. to conds (on vars) in XML file (“requirement list”) 2.vars changing rules  simple (“generate list”) 3.cond. fragm. in pgs: AHA tag language (XML based) adaptive navigation support  1-2: adaptive navigation support (pg level) adaptive presentation  3: adaptive presentation

10 / faculty of mathematics and informatics TU/e eindhoven university of technology 10 Problems Lack of: –Reusability –Expressivity

11 / faculty of mathematics and informatics TU/e eindhoven university of technology 11 Index Motivation & background AHA! & beyond Concept-mapping paradigm New Adaptation Rules: How to Augment the Adaptation Engine Implementing New Rules in the current AHA! Problems & need of checking mechanisms Future directions Conclusion

12 / faculty of mathematics and informatics TU/e eindhoven university of technology 12 Concept mapping independent semanticsintuitive classif.: divide source material into concepts:  piece has independent semantics (~ semantic Web) –low level: atomic concepts –concepts collections: composite concepts –together: concept hierarchy = primitive building blocks of hypermedia

13 / faculty of mathematics and informatics TU/e eindhoven university of technology 13 Linking building blocks w. diff. sequences  diff. presentations (high granularity level: concept level)  adaptive navigation support  adaptive presentation: at lower, concepts fractions level –E.g. text intro. can be used w. other introductory fragments in introductory chapter, (to drop at later browsing) etc. –Pb.: no independent meaning. common solution: –divide concepts into sub-concepts; but: –pb: semantics loss; collaborative authoring; cannot be semantically annotated & not significant for search mechanisms.

14 / faculty of mathematics and informatics TU/e eindhoven university of technology 14 Attributes more appropriate : –concept name, alternative contents, fragments, etc. course content mapped on concept hierarchy & describing concepts w. attributes set, adaptation = concept-level & attribute adaptation. Advantage: can be performed & viewed from high level –no need of separate consideration of cond. fragments in texts (difficult to re-use by other authors)  content - & adaptative engine rules authoring is separated  easier automatic checks  adaptation = combining concept attributes into pages (info pieces that can be show at a time)

15 / faculty of mathematics and informatics TU/e eindhoven university of technology 15 Navigation dependent on presentation format –e.g.: a handheld device w. short pg displays “next” button more often within same lesson model: compatible w. RDF standard: –resources  concepts, –properties  attributes & –literals  attribute values

16 / faculty of mathematics and informatics TU/e eindhoven university of technology 16 Adaptive navigation & presentation

17 / faculty of mathematics and informatics TU/e eindhoven university of technology 17 What is already in AHA? main difference: –Concepts: at pg granulation –pgs constructs (conditional fragments)  concept attrs & cannot be independently used w. other concepts or c. attributes. under development version consider multiple attributes & a DB structure, that allows flexibility

18 / faculty of mathematics and informatics TU/e eindhoven university of technology 18 Index Motivation & background AHA! & beyond Concept-mapping paradigm New Adaptation Rules: How to Augment the Adaptation Engine Implementing New Rules in the current AHA! Problems & need of checking mechanisms Future directions Conclusion

19 / faculty of mathematics and informatics TU/e eindhoven university of technology 19 Typical adaptivity Most AS = rule-based, i.e.: Adaptation : conditional rules: IF THEN

20 / faculty of mathematics and informatics TU/e eindhoven university of technology 20 New adaptation rules proposed

21 / faculty of mathematics and informatics TU/e eindhoven university of technology 21 A level rule IF ENOUGH( ) THEN ENOUGH = fct. of no. & quality of prerequisites; true if, e.g., a given no. of prerequisites from a set is fulfilled –Ex: PREREQUISITES = time_spent; ACTION = “go to next level” –Rule becomes: IF ENOUGH (time_spent on crt. level) THEN “go to next level” –Where ENOUGH is defined, e.g., as follows: ENOUGH (time) = 30 time units; time (advanced topic) = 10 (time units per topic); ENOUGH (medium topic) = 5 (time units per topic); ENOUGH (beginner topic) = 2 (time units per topic);

22 / faculty of mathematics and informatics TU/e eindhoven university of technology 22 A temporal rule: action repeated as long as 1-more cond.s hold: WHILE DO –E.g: warning - user search direction is wrong  service denial over a threshold / drill ex.

23 / faculty of mathematics and informatics TU/e eindhoven university of technology 23 A repetition rule: a certain (simple / composed) action repeated for a no. of times predefined by author: FOR DO E.g.: time action has to last before reader can move on.

24 / faculty of mathematics and informatics TU/e eindhoven university of technology 24 An interruption command: forced user to do smthg. else: BREAK = exacerbation of traditional AHS behavior: user “punished” for not sticking to learning pathways

25 / faculty of mathematics and informatics TU/e eindhoven university of technology 25 A generalization command: new concept reached is compared w. more general ones it refers to. As a result, the reader is pointed to related concept(s): GENERALIZE (COND, COND 1, …, COND n )

26 / faculty of mathematics and informatics TU/e eindhoven university of technology 26 A specialization command: if concept is general, system deductively points reader to more specific instantiations: SPECIALIZE (COND, COND 1, …, COND n ) –E.g, if student reads about “Model Reader” in a course on postmodern literature, she can be pointed to an extract from Calvino’s novel ‘Se una notte’, where this notion is exemplified.

27 / faculty of mathematics and informatics TU/e eindhoven university of technology 27 Other commands comparison (concept analogy search) & difference both instances of generalization; duration – a rule related to repetition –lyrical use of repetitions in hyperfiction has given rise to a particular design pattern

28 / faculty of mathematics and informatics TU/e eindhoven university of technology 28 Index Motivation & background AHA! & beyond Concept-mapping paradigm New Adaptation Rules: How to Augment the Adaptation Engine Implementing New Rules in the current AHA! Problems & need of checking mechanisms Future directions Conclusion

29 / faculty of mathematics and informatics TU/e eindhoven university of technology 29 Here definition of enough Here a conditional fragment Here optional alternative fragment Here a conditional fragment Another example is: Here predefined events sequence Here an alternative event (action) 1. the level rule:2. the temporal rule:

30 / faculty of mathematics and informatics TU/e eindhoven university of technology 30 3. the repetition rule:4. interruption command: Here a conditional fragment E.g, explan. is given if question no  5. Next follows diff.strategy – e.g., suggestion to consult diff. material, etc. Here a conditional fragment 5.generalization command: 6. specialization command: Here details of generalization (levels, etc.) Example: Here details of generalization (levels, etc.) E.g. jump 1-* levels in concept hierarchy. Extra processing can be done in body part, e.g. commenting on next level & reason why. Here details of specialization (levels, etc.) Example: Here details of specialization (levels, etc.) Similar to 5, but direction of processing in concept hierarchy is top-down instead of bottom-up.

31 / faculty of mathematics and informatics TU/e eindhoven university of technology 31 Index Motivation & background AHA! & beyond Concept-mapping paradigm New Adaptation Rules: How to Augment the Adaptation Engine Implementing New Rules in the current AHA! Problems & need of checking mechanisms Future directions Conclusion

32 / faculty of mathematics and informatics TU/e eindhoven university of technology 32 Pros & cons Balance: system complexity vs. authoring efficiency –Extending AS w. extra adaptation rules is beneficial if rules can express situations that were not possible (difficult) to express w. given set of tools/ rules. –Makes sense if it doesn’t increase dramatically the types of tests an AH author has to do to verify his/her output.

33 / faculty of mathematics and informatics TU/e eindhoven university of technology 33 Future directions automatic check tools visual checking mechanisms, dynamical representation of processes involved; –E.g., effect of new rule on rest can be shown on static (smaller) link graph, as a propagation of a colored fluid through graph, etc.

34 / faculty of mathematics and informatics TU/e eindhoven university of technology 34 Index Motivation & background AHA! & beyond Concept-mapping paradigm New Adaptation Rules: How to Augment the Adaptation Engine Implementing New Rules in the current AHA! Problems & need of checking mechanisms Future directions Conclusion

35 / faculty of mathematics and informatics TU/e eindhoven university of technology 35 Conclusion suggested a better approach for AH authoring: –combination of CM paradigm to construct course narrative & several new adaptation rules. –highlighted new rules to integrate into AH authoring shell / toolkit. showed integration of 2 formalisms in AHA! ex. version (for more adaptivity)  We claim that this approach is another step towards flexible generic-purpose adaptive hypermedia.

36 / faculty of mathematics and informatics TU/e eindhoven university of technology 36 Thank you for listening!

37 / faculty of mathematics and informatics TU/e eindhoven university of technology 37 Recent AHA! extensions 1.editor to connect requirements to pages; 2.editor for generate rules; 3.forms to make changes to UM: most important: form allowing AH user to modify knowledge attributes assoc. to page-concepts.

38 / faculty of mathematics and informatics TU/e eindhoven university of technology 38 System complexity vs. authoring efficiency

39 / faculty of mathematics and informatics TU/e eindhoven university of technology 39 Index Motivation & background AHA! & beyond Concept-mapping paradigm New Adaptation Rules: How to Augment the Adaptation Engine Implementing New Rules in the current AHA! Problems & need of checking mechanisms Future directions Conclusion

40 / faculty of mathematics and informatics TU/e eindhoven university of technology 40 Problems & need of check mechanisms by increasing system complexity, authoring efficiency grows for a while, and then drops. –AHA! is somewhere at beginning of slope –Adding more features & flexibilities can increase authoring efficiency for a while, but how to stop before down-curve? E.g., when authors deal w. complex graphs w. many concepts & attr.s, it’s easy to leave something out by mistake.

41 / faculty of mathematics and informatics TU/e eindhoven university of technology 41 AHAM tries to deal w. such pb. as: –termination ( avoiding of loops) & –confluence (equivalence of rule execution order) T: activation graphs (active DBs static analysis): –possible states graph: det. by concepts, links, attr.s, values (init. val.s & ranges – search tree constrains optimization) & rule sets –If graph has no loops, system will always terminate. C: commutation check (rule pairs order equivalence) AHA! : only monotonic attributes (per concept) increase  termination; but: difficult in next version w. multiple attr.s AHA! doesn’t deal w. confluence.

42 / faculty of mathematics and informatics TU/e eindhoven university of technology 42 Other problems concepts (or concept fragments) never reached; rules (or other adaptation mechanisms) w. attributes w. out of range (or domain) values.

43 / faculty of mathematics and informatics TU/e eindhoven university of technology 43 New rules good news: don’t require extra checking mechanisms –  loops in regular rules will also  in level -, temporal -, repetition rules. –Non-equivalent non-commutable rules to be executed at a given time pose same problems on extended set. –Extended commands of generalization & specialization can be treated the same as regular links. –Interruption command can help in breaking infinite loops, ~ Java catch-throw mechanism of exception handling.

44 / faculty of mathematics and informatics TU/e eindhoven university of technology 44 New rules bad news: time - & space -consuming. better way: simplifications & complexity decreasing assumptions. –E.g., belief revision technique to check inconsistencies in knowledge attr.s to concepts & consequent knowledge acquisition pb.

45 / faculty of mathematics and informatics TU/e eindhoven university of technology 45 Belief revision introduction of a case-based heuristics that: 1.recalls previous concept w. same features & assoc. attributes; 2.adapts course struct., via rule-based formalism, to current learning scenario; 3.resolves inconsistencies so that changes of state are epistemologically conservative (resulting narrative is not subverted).

46 / faculty of mathematics and informatics TU/e eindhoven university of technology 46 Future directions W. standardiz. of AS building bricks (LOM, Learner model– IEEE, LTSC for education, RDF, etc.) it’s feasible to collaborate & share adaptive techniques, technologies & also system parts, AH presentations, etc. Adaptive & adaptable systems –are necessary in education, where learners come w. different cultural & knowledge backgrounds, learning styles, genders, ages, (context: life-long learning). –are definitely necessary in commerce (Amazon.com). –can have surprising applications: adaptive literature & art.

47 / faculty of mathematics and informatics TU/e eindhoven university of technology 47 Conclusion: distructive criticized widespread practice to distinguish adaptation in hypermedia between adaptive navigation support & adaptive presentation because: AH authors have to artificially separate links from concepts but still coordinate them to provide a conceptually valid adaptation that contributes to a significant knowledge acquisition.


Download ppt "/ faculty of mathematics and informatics TU/e eindhoven university of technology 1 Towards Generic Adaptive Systems: Analysis of a Case Study Licia Calvi."

Similar presentations


Ads by Google