WoSS

1
WoSSN
National Institute of Standards and Technology
(NIST) Gaithersburg, Maryland February
22-25, 2005
Building Intelligent Learning Management Systems
to implement the Teacher-Student dialogue

• Keith Maycock and John G.Keating
• Department of Computer Science
• National University of Ireland Maynooth.

2
Acknowledgement
This project is jointly funded by IRCSET and IBM
3
Agenda

• Motivation
• Intelligent systems and Learning
• Bringing e-learning into an on-demand framework
• Effects of adding help on the activity tree
• Locating a learning experience in a learning
  experience repository
• Conclusion
• Questions

4
Agenda

• Motivation
• Intelligent systems and Learning
• Bringing e-learning into an on-demand framework
• Effects of adding help on the activity tree
• Locating a learning experience in a learning
  experience repository
• Conclusion
• Questions

5
Motivation
LMS
Student
Profile of student
Profile of student
LMS
LMS
6
Motivation

• Individually tutored students against classroom
  environment.
• In a typical classroom environment every student,
  on average, asks about 0.1 questions every hour.
• The speed with which different students can
  progress through instruction varies by factors of
  three to seven.
• With individual tutoring, students may ask or
  answer on average 120 questions per hour.
• The achievement of individually tutored students
  may exceed that of classroom students by as much
  as two standard deviations an improvement which
  is equivalent to raising the performance of 50th
  percentile students to that of 98th percentile
  students.
• Expected influx into higher education.
• Currently there are roughly 70 million people in
  higher education, this number is expected to more
  than double before 2025.

7
Motivation

• Industry and learning
• Technology is increasing at a rapid rate and
  businesses are having to spend a substantial
  amount of money to keep their staff up to date
  with the state of the art.

• It is for all the above reasons that e-learning
  must traverse into an on-demand framework
  tailored to the individual needs of each user to
  reduce time-spent learning and increase
  productivity.

8
Agenda

• Motivation
• Intelligent systems and Learning
• Bringing e-learning into an on-demand framework
• Effects of adding help on the activity tree
• Locating a learning experience in a learning
  experience repository
• Conclusion
• Questions

9
What are Intelligent systems?

• Artificial intelligence aims to implement
  machines that simulate intelligent human
  behavior.
• This intelligent human behavior is often
  misunderstood, as there are multiple definitions
  such as, verbal, spatial and emotional
  intelligence.
• In the context of our project, we consider
  intelligence as the ability to learn from past
  experiences and subsequent profiling.
• A direct correlation can be mapped over to our
  definition of machine intelligence, as our
  intelligent learning management system will learn
  from past experiences when evaluating problems
  with different users.

10
Understanding Learning

• This project is focused on the vocal aspect of
  learning with respect to the teacher student
• relationship.
• The importance of language can be seen clearly
  throughout the evolution of hominids.
• With the emergence of language the hominid
  evolution accelerated.
• It is believed that with the introduction of
  language, this gave hominids the ability to
  create an internal visual perception of a complex
  reality thus enabling hominids to think through
  problems
• The introduction of language also enabled
  hominids to project into a future state of
  reality when dealing with problems.
• How does this relate to e-learning.
• We believe that if learning objects suited to a
  particular user are returned, it would increase
  the ability of each user to learn more
  effectively as the user is constantly reading and
  thus creating an internal representation of each
  learning object encountered

11
Agenda

• Motivation
• Intelligent systems and Learning
• Bringing e-learning into an on-demand framework
• Effects of adding help on the activity tree
• Locating a learning experience in a learning
  experience repository
• Conclusion
• Questions

12
Bringing e-learning into an on-demand framework

• The ADL initiative was established in November
  1997. Their mission is to bring the highest
  quality of instructional material, tailored to
  the needs of each individual anytime anywhere.
• The ADL produced the Sharable Content Object
  Reference Model (SCORM) as the backbone for
  producing reusable-learning objects.
• Each SCORM compliant learning object has the
  following fields, with various meta data
  components.
• ltmanifestgt
• ltorganisationsgt
• ltresourcesgt
• lt(sub)manifestsgt

• The SCORM is defined within three books.
• The content aggregation (CAM) book defines the
  learning content using XML tags.

13
Bringing e-learning into an on-demand framework

• The SCORM Run Time Environment (RTE) describes
  the LMS requirements for interacting with
  learning objects.
• The Sequencing and Navigation (SN) defines the
  various methods of delivering courses to clients

14
Bringing e-learning into an on-demand framework

• The following represents the basic schematic of
  how the learning management system interacts
  with the learning object.

Launches
Learning Object
LMS
Data Model
API
15
Bringing e-learning into an on-demand framework

• Building learning objects is the first step in
  developing intelligent learning management
  systems and bringing e-learning into an on-demand
  framework.

• Extending the manifest to include a personal
  element with various attributes, such as, name,
  age, address, ability, learning preference and
  associated metadata would enable the LMS to
  initiate conversation with the client on a
  personal level.
• ltmanifestgt
• ltorganisationsgt
• ltresourcesgt
• lt(sub)manifestsgt
• ltPersonalgt

16
Bringing e-learning into an on-demand framework

• The ltPersonalgt field would initially be empty in
  every learning object. Once the learning
  experience has commenced the users personal
  profile would be dynamically filled from locally
  stored information.

• Technology is changing rapidly and
  correspondingly, adaptive on-demand technology
  training is now an essential part of day-to-day
  business. It should be possible for users to log
  into any LMS and get instant access to learning
  objects.
• Adding the ltPersonalgt element into the manifest
  allows each user the freedom to log onto any LMS
  and initiate a learning experience.
• Giving the users this freedom is essentially
  bringing e-learning into an on-demand framework.
  Allowing users instant access to tailor made
  learning objects.

17
Agenda

• Motivation
• Intelligent systems and Learning
• Bringing e-learning into an on-demand framework
• Effects of adding help on the activity tree
• Locating a learning experience in a learning
  experience repository
• Conclusion
• Questions

18
Effects of adding help on the Activity tree

• An Activity Tree is a general term that
  represents an instance of hierarchical learning
  activities and the corresponding sequencing
  information for the interoperable application of
  specified sequencing behaviors.
• The Activity Tree is not a static structure and
  is free to change dynamically with the needs of
  the learning object vender.

• The structural change to a learning objects
  activity tree is seen below, when a learner
  prompts the LMS for help.

19
Effects of adding help on the Activity tree
Course
Module1
Module2
Lesson 1
Lesson 2
Learner has problem With lesson 2 and prompts the
LMS for help.
Once the learning experience has concluded, the
transformation from lesson two to the new sub
manifst is saved in a learning experience
repository.
LMS returnes a learning object suited to the
learners needs and creates a (sub)manifest at the
point of help.
20
Agenda

• Motivation
• Intelligent systems and Learning
• Bringing e-learning into an on-demand framework
• Effects of adding help on the activity tree
• Locating a learning experience in a learning
  experience repository
• Conclusion
• Questions

21
Locating a learning experience in a Learning
Experience Repository

• Before the learning object can be stored in a
  learning experience repository, the learning
  object should be sent to an ADL certification
  center to maintain high standards and ensure that
  changes made to the learning objects Activity
  Diagram conforms to the SCORM standard.
• The ADL certification center should append an
  element to indicate that the current learning
  object was changed
• The ADL certification center should also give the
  learning object a unique-learning Experience
  Repository Number (LERN) that represents the
  location of the learning object in the learning
  experience repository.

22
Locating a learning experience in a Learning
Experience Repository

• The changes made to the basic schematic of how
  an LMS interacts with a learning object are shown
  below.

Launches
Learning Object
Changes
LMS
SCORM Cert.
Data Model
Learning
experience repository.
Api
23
Procedure for LMS interacting with learning
objects
LMS
Launches learning object
Problem with learning experience
No problem with learning experience
Checks if learning object has LERN
Learning experience repository
LMS
Has LERN
No LERN
Same problem
New problem
24
Procedure for LMS interacting with learning
objects
Same problem
New problem
LMS
LMS
LMS offers previous solution to the problem
searches
Returns a new learning object at the point of
confusion within the activity tree
25
Procedure for LMS interacting with learning
objects

• After the learning experience has concluded and
  a change has occurred within the learning objects
  activity tree.

ADL certification center
Learning experience repository
Learning object with changes incorporated
26
Agenda

• Motivation
• Intelligent systems and Learning.
• Bringing e-learning into an on-demand framework.
• Effects of adding help on the activity tree.
• Locating a learning experience in a learning
  experience repository.
• Conclusion.
• Questions.

27
Conclusion

• We believe that extending the manifest and
  building learning experience repositories is the
  next step in achieving an automated one-to-one
  tutoring experience and binging e-learning into
  an on demand framework.
• The LMS would have the same ability as an
  intelligent, experienced visually impaired
  teacher, being able to make suggestions based on
  a vast amount of meta-data available for both the
  learning object and the client and also based on
  past experiences with similar clients.
• Future models could include a visual aid for the
  LMS in the form of a camera, which would enable
  the LMS to monitor the clients body language.
• Neural Networks, for example, could be trained to
  recognise when a client is stressed, confused,
  frustrated or simply not relaxed, and
  automatically suggest help for the current
  learning experience.

28
Questions and Answers