7. Learning Analytics – a definition
“learning analytics is the measurement, collection, analysis and reporting of data about
learners and their contexts, for purposes of understanding and optimizing learning and the
environments in which it occurs”
(Siemens, 2012)
11. Types of learning analytics?
Management
Reading lists
Who’s using the
service
Trends in
departments
KPIs
Learner
Focussed on
individual
Help them make
choices
Help them study
effectively
Curriculum
Improved learning
activities
Identify areas that
work
Quality rather than
quantity
Wellbeing
Pastoral
Mental health
12. VLE data
+
Student record system
+
Attendance data
+
Library data
Buildings data
+
Learning space data
+
Location data
Teaching quality data
+
Assessment data
+
Curriculum design data
Content data
+
Learning pathways
data
Better retention
and attainment
A more efficient
campus
Improved teaching
& curricula
Personalised and
adaptive learning
Now
Learning
analytics
Institutional
analytics
Educational
analytics
Cognitive
Analytics and AI
Future
Jisc Learning Analytics Service
Retention and
attainment
Efficient campus
Improving teaching
& curricula
13. Universities have
lots of data
– but in silos
By department
By service
By student cohort
By location
16. Current activity
• Commercials:
• VLE
• LMS
• eBook suppliers
• Jisc:
• Learning Analytics Service
• Project work – e.g. LA Cymru
• Working with suppliers
• Data Hub
18. Current activity
• Commercials:
• VLE
• LMS
• eBook suppliers
• British Library
• Jisc:
• Learning Analytics Service
• Project work – e.g. LA Cymru
• Working with suppliers
• Data Hub
19. Data
Collection
Data
Storage
and Analysis
Presentation
and Action
Jisc Learning Analytics open architecture: core
Alert and Intervention
system
Other Staff
Dashboards
Student Consent
Student App:
Study Goal
Jisc Learning
Analytics Predictor
Learning
Data Hub
Student Records VLE Library
Staff dashboards in
Data Explorer
Self Declared Data Attendance, Presence, Equipment use etc….
Data Aggregator
UDD Transformation Toolkit Plugins and/or Universal xAPI Translator
19
Jisc Learning Analytics Service
22. LA from an ILL
perspective
Need to understand your
institutional perspective
Libraries are not always
part of the discussion
Types of ILL analytics
23. LA from an ILL perspective
Data for management
• Informed decisions on
document management
• Impact and value
• Improve the user experience
Data for learning
• Usage patterns
• Engagement
• Citation use
24. Opportunities
Re-think current
data
What other data
could you get
Engage with
suppliers
Digital landscape
Be part of your
institutional
discussion
You’re best placed
to know what
could be achieved
26. Where to start!
LEGAL ETHICAL DATA QUALITY INTERPRETATION INSTITUTIONAL
BARRIERS
RESPONSIBILITIES STUDENT VIEW
27. Legal & Ethical
GDPR
Privacy
Data ownership
Transparency
Consent
Anonymity
‘I’m not a number’
Change student behaviour
Student motivation
Built in bias
28. USW
“learning analytics can be the basis for better quality
conversations with students about their expectations and
aspirations.”
29. University of Gloucestershire
• We will use Learning Analytics to help all students reach their full
academic potential.
• We will be transparent about data collection, sharing, consent and
responsibilities.
• We will abide by ethical principles and align with our university strategy,
policies and values.
• Learning Analytics will not be used to inform significant action at an
individual level without human intervention.
30. University of Greenwich
• We will use Learning Analytics to help all students reach their full academic
potential.
• We will be transparent about data collection, sharing, consent and
responsibilities.
• We will abide by ethical principles and align with our university strategy,
policies and values.
• Learning Analytics will be supported by focused staff and student development
activities.
• Learning Analytics will not be used to inform significant action at an individual
level without human intervention.
• We will actively work to recognise and address any potential negative impacts
from Learning Analytics.
32. Data
interpretation
• Correlation ≠ Causation
• Quality of algorithms
• What is it telling me?
• Visualisation
• Decision making
• Predictions
33. Barriers & Responsibilities
Institutional barriers
• Lack of conversations
• Lack of headspace
• Not a priority
Responsibilities
• What are the institutional
and personal
responsibilities if the data
shows ‘something’