3. “learning analytics is the measurement,
collection, analysis and reporting of data
about learners and their contexts, for
purposes of understanding and
optimising learning and the
environments in which it occurs”
SoLAR – Society for Learning Analytics Research
Learning Analytics Service
4. Effective Learning Analytics Challenge
Learning Analytics Service
Rationale
»Organisations wanted help to get started and have access to standard
tools and technologies to monitor and intervene
Priorities identified
»Code of Practice on legal and ethical issues
»Develop a core learning analytics service with app for students
»Provide a network to share knowledge and experience
Timescale
»2015-17 Development
»2017-18 Beta Service
»Aug 2018 Full Service
5. Agenda
Learning Analytics Service
Predictive models
identify students at risk
Timely intervention by teaching or support
staff
Increased retention
Better understanding
of the effectiveness
of interventions
Rich data on student
activity and attainment
Data shared with
student prompting
them to change
own behaviour
Better student
outcomes
Data can be
explored to
understand patterns
of behaviour
Better understanding
of the behaviours
linked to differential
outcomes
6. Paul Bailey, Senior Codesign Manager, Research and Development
Jisc learning analytics service
https://docs.analytics.alpha.jisc.ac.uk/docs/learning-analytics/Home
7. Jisc’s Learning Analytics Project
Three core strands:
Learning
Analytics Service
Toolkit,
Consultancy,
Framework
Community,
Network, Events
Jisc Learning Analytics
Learning Analytics Service
8. Community: Project Blog,
mailing list and network events
Blog: http://analytics.jiscinvolve.org
Docs: http://docs.analytics.alpha.jisc.ac.uk/
Mailing: analytics@jiscmail.ac.uk
Learning Analytics Service
9. On-boarding Process
Stage 1: Orientation – get more info
Stage 2: Discovery – DIY and/or paid for consultancy
Stage 3: Culture and Organisation Setup – sign up for
Jisc service and/or supplier products
Stage 4: Data Integration - push data to learning data
hub
Stage 5: Implementation Planning
Learning Analytics Service
https://analytics.jiscinvolve.org/wp/on-boarding/
10. Discovery readiness
Topic ID Question Commentary Response Score
Leadersh
ip
1 The institutional senior management
team is committed to using data to
make decisions
Please provide a commentary on you
response to each question where
appropriate
0 - Hardly or not at
all
1 - To some extent
2 - To a great
extent
Leadersh
ip
2 Our vice-chancellor / principal has
encouraged the institution to
investigate the potential of learning
analytics
0 - Hardly or not at
all
1 - To some extent
2 - To a great
extent
Leadersh
ip
3 There is a named institutional
champion / lead for learning analytics
0 - No
2 - Yes
Vision 4 We have identified the key
performance indicators that we wish to
improve with the use of data
0 - Hardly or not at
all
1 - To some extent
2 - To a great
extent
Learning Analytics Service
A supported review of institutional readiness
11. Lessons Learned
1. Governance – senior management buy-in, wide engagement, dedicated project
manager
2. Agreed goal – managing expectations
3. Clear strategic aims – see case studies
4. The main benefits/challenges
» It is more than the “product”
» Data cleaning and business processes (assessment data, student status, etc)
» Improving student support process – managing interventions
» Good communication to staff and students
Learning Analytics Service
Implementation of learning analytics
12. Toolkit: Code of Practice
Learning Analytics Service
Code of Practice
http://www.jisc.ac.uk/guides/code-of-practice-for-learning-
analytics
Literature Review
http://repository.jisc.ac.uk/5661/1/Learning_Analytics_A-
_Literature_Review.pdf
Template Learning Analytics Policy
https://analytics.jiscinvolve.org/wp/2016/11/29/developing-
an-institutional-learning-analytics-policy/
Guidance on consent for learning analytics
https://analytics.jiscinvolve.org/wp/2017/02/16/consent-for-
learning-analytics-some-practical-guidance-for-institutions/
13. Legal and ethical: consent and GDPR
Learning Analytics Service
Advice is
Make sure your collection notice covers the use of data
to support the student learning and wellbeing
Not ask for consent for the use of non-sensitive data for
analytics (our current understanding is that this can be
considered as of legitimate interest or public interest)
Ask for consent for use of sensitive data (which, under
the GDPR, is called “special category data”)
Ask for consent to take interventions directly with
students on the basis of the analytics
https://analytics.jiscinvolve.org/wp/
14. Take-up of Jisc service
30 institutions signed-up
8 institutions institution wide roll-out Sept
14 HEIs in data integration/pilot stage
8 Colleges in service development
Learning Analytics Service
15. Data
Collection
Data
Storage
and Analysis
Presentation
and Action
Jisc Learning Analytics open architecture: core
Alert and Intervention
system
Other Staff
Dashboards
Consent Service
(tbc)
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
16. Products and dashboards
Data Explorer: Learning Analytics dashboards for staff, focussing on showing learning analytics
data to staff based on their role.
Study Goal: An app for students - allowing them to view their learning analytics data, and set
measurable actions to support their success.
Learning Analytics Predictor: A predictive model designed to do one thing well - predict
success at course level. Output can be viewed in Data Explorer or any other system that can
integrated in the Learning Data Hub.
Traffic Lights Calculator: A straightforward rules based engine, allowing RAG status to be
calculated for online activity, attendance and achievement, at module level. Output fromTLC
can viewed in data explorer or any other system that can integrated in the learning data hub.
Learning Data Hub: the core of Jisc's learning analytics service, holds data about students,
works in conjunction with an institutions data warehouse, rather than replace it, to share data
between applications in a standard way, a collection point for semi-structured learning data
such as student activity.
Learning Analytics Service
17. Data Explorer
Data Explorer Release 2.0 - Aug 18
View data in learning records warehouse
Site Overview – overview of all data
My Students and My Modules
Notes (interventions) on students
RAG Status and predictive models
User Guide and videos
https://docs.analytics.alpha.jisc.ac.uk/docs/d
ata-explorer/Home
Jisc Learning Analytics 2017
19. Study Goal
Study Goal aims
Social learning app with gamification
Setting targets and logging self-declared activity
(fitbit model)
View activity and attainment data
Attendance check-in
Guides and videos
https://docs.analytics.alpha.jisc.ac.uk/docs/study-
goal/Home
Jisc Learning Analytics 2017
21. Learning Analytics Service
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
Retention and
attainment
A more efficient
campus
Improved teaching
& curricula
Personalised and
adaptive learning
Efficient campus
Improving teaching
& curricula
Now
Learning
analytics
Institutional
analytics
Educational
analytics
Cognitive
Analytics and AI
Future
22. Health and well-being
• Can we use activity data to support health and well-being?
• Timely interventions identify students earlier
• Patterns of behaviour
• Improved student support processes
• Developing coping strategies
• Additional data
• Student sentiment analysis
• Long term data study
• Sensitive data
• Build AI models to predict at risk students, also beyond
graduation
Learning Analytics Service
23. Student Success
• Behavioural patterns that lead to success (attendance, engagement, attainment, submission
date/time of assignments)
• Predictive models that look at success i.e. first or 2:1 – that will model the behaviours
• Grouping of behaviours that lead to success (e.g. accessing a wider range of resources, time on
task, linking intended with actual behaviours)
Learning Analytics Service
25. Employability
• Analyse data to find indicators that
lead to employability
Baseline data on employability
Activity data e.g.
• Careers entry profiles
• Careers engagement activity
• Employability skills in modules
• Work experience
Learning Analytics Service
HEPI Employability: Degrees of
Value