The Learning Ecosystem – A Content Agnostic Adaptive Learning and Analytics System
Presentation from 'InFocus: Learner analytics and big data', a CDE technology symposium held at Senate House on 10 December 2013. Conducted by George Mitchell (Chief Operations Officer, CCKF Ltd, Dublin).
Audio of the session and more details can be found at www.cde.london.ac.uk.
2. Goals
Provide a personalized learning experience
o
o
o
o
o
Deliver learning at an appropriate time
Deliver appropriate learning material
Learn about the learner
Manage and adapt to change: abilities, metrics, behavior
etc.
Identify weaknesses and try to remedy
Help a learner to realize their potential
Simulate or emulate a good teacher
Remain subject and content independent
www.realizeitlearning.com
3. The Academic Model
Key Concepts
Ability metrics
Target knowledge
Learning paths
Determine
knowledge
Intelligent engine
– adapting to learner
Profiling
Content
www.realizeitlearning.com
4. Key Concepts
Target knowledge
Target
knowledge
Knowledge space
Logical connections between elements
Pre-requisite and other relationships
Domain
Element
5
Element
6
Topic
Element
3
Topic
Element
1
Area
Area
Element
1
Area
Element
2
Area
Element
3
Element
4
Area
Element
4
Element
5
Element
2
Element
7
www.realizeitlearning.com
5. Key Concepts
Target knowledge
Target
knowledge
By its very nature a competency based model
Granular elements of knowledge
Ability to track progress and attainment against
knowledge elements
Ability to track specific competencies
Ability to navigate through the elements by
demonstrating competency
www.realizeitlearning.com
6. Key Concepts
Target knowledge
Academic Independence
Maintaining academic rigor
Control of curriculum and content
Fully engaging faculty in online delivery
Real time evidence
for course evolution
Target
knowledge
7. Key Concepts
Intelligent engine
Intelligent engine
Requirements
Deliver learning suited to an individual
Adapt to responses from the individual
Evolve behavior as the system grows
Learning paths
Ability metrics
Determine
knowledge
Intelligent engine
Profiling
– adapting to learner
www.realizeitlearning.com
8. Key Concepts
Intelligent engine
Intelligent engine
Ability metrics
Measure and Predict Ability
Granular approach
Likelihood function
Gathers evidence to adjust functions
Automatically evolves and balances network
www.realizeitlearning.com
9. Key Concepts
Intelligent engine
Intelligent engine
Learning paths
Learning Paths
Paths managed dynamically
Adapt to learner experience
Element
6
Element
1
Element
5
Element
3
Element
4
Element
2
Element
7
Element
8
Element
1
Element
6
Element
3
Element
7
Element
2
Element
8
Element
5
Element
4
Element
7
Element
1
Element
2
Element
8
Element
6
Element
3
Element
4
Element
5
www.realizeitlearning.com
10. Key Concepts
Intelligent engine
Intelligent engine
Determine knowledge
Respect what the student knows
Gap analysis to identify what learner
needs to know
Knowledge Space
Knowledge required
Determine
knowledge
Determine knowledge
www.realizeitlearning.com
11. Key Concepts
Intelligent engine
Intelligent engine
Profiling
Profiling
Deliver the learning material that is most
appropriate to the learner
Different types of material vary in effectiveness for different
learners
Knowledge
element
Learner Profile
Find content
Probability of
success = 0.5
Content 1
Content 2
Content 3
Evaluate
content
Probability of
success = 0.7
Render and
delivery content
to learner
Exclude as not
suitable
www.realizeitlearning.com
12. Key Concepts
Intelligent engine
Intelligent engine
Delivering Learning Excellence
Measuring and predicting ability
Respecting what the learner already knows
Continuously adapting to the individual
Evolving its own behavior
Establishing competencies
with evidence
13. Key Concepts
Content
Content
Goals for content
Adapt to the learner
Don’t ask the same questions all the time
Vary for learner
Provide evidence for propagation network
Integrate with behavioral engine
Integrate with knowledge elements
www.realizeitlearning.com
14. Breaking Boundaries – Case Study
Truly content Agnostic
English
o Literature
o English Composition
History
o US History
Business & Accounting
o Marketing Management
o Spreadsheets
o Managing accounting
o Macroeconomics
Criminal Justice
o Introduction to American Court System
Computer Science
o Computer Networks
o Security
Science, Psychology, Engineering, Ethics
o Biology
o Systems Engineering
o Introduction to Psychology
o Student Success
Mathematics
o Introduction to Mathematics
o College Algebra
o Statistics: Data-driven Decision Making
A client’s deployment statistics for 1 year
o
o
o
o
o
50,000+ students
75,000+ course enrollments
18,000,000 unique questions generated by the Realizeit system
317,000 practices and revision interactions
60+ courses
26. Roadmap for Transformation
A journey towards a new paradigm of teaching and learning
Competency
Based Learning
Evolved
Content
Student
Engagement
Content
Metrics
Business
Intelligence
Course
Analytics
Learning
Trends
Insights from
Data
Evolved
Curricula
Faculty
Engagement
www.realizeitlearning.com
Editor's Notes
ReportingAll sections of Intro to Bus. Session results for each objective in the learning map which synch to the course objectives
ReportingAll sections of Intro to Bus. Session results for each objective in the learning map which synch to the course objectives