Phase 1 Learning Analytics Intro Slides

Overview

Jisc Learning Analytics

Learning Analytics

Background

Jisc Learning Analytics Services

User views of products

Timeline and next steps

Student App (additional slides)

How data is included (additional slides)

Learning Analytics - Initial Meetings 2015 2

Outline of session

About Jisc…


It operates shared digital infrastructure and services, negotiates sector-wide deals with IT vendors and commercial publishers, and provides trusted advice and practical assistance for universities and colleges.

Jisc is the UK higher and further education sectors’ not-for-profit organisation for digital service and solutions.

What does Jisc do?

Does 4 things…

Providing and developing a network infrastructure and

related services that meet the needs of the UK research and

education communities

Supporting the procurement of digital content for UK education and research

Our network of national and regional teams provide local

engagement, advice and support to help you get the

most out of our service offer

Our R&D work, paid for entirely by our major funders, identifies

emerging technologies and develops them around your

particular needs

Co-design challenges

Research at risk (R@R)

Prospect to alumnus (P2A) Learning analytics

Digital learning & capabilitiesImplementing FELTAG

Business intelligence

Hosting platform Hosting platform

http://www.jisc.ac.uk/rd/projects/prospect-to-alumnus


http://www.jisc.ac.uk/rd/projects/effective-learning-analytics


http://www.jisc.ac.uk/rd/projects/building-digital-capability


http://www.jisc.ac.uk/rd/projects/implementing-the-feltag-agenda


http://www.jisc.ac.uk/rd/projects/research-at-risk










About Learning Analytics…

6Learning Analytics - Initial Meetings 2015

Effective Learning Analytics ChallengeRationale

Universities and colleges don't have enough useful data about students and how they are learning. What they have they don’t analyse and interpret. They are missing opportunities to use technology to provide feedback to students. They need to support staff who could be using analytics and a standard set of tools and technologies to monitor and intervene.

Who it affects and how

Students are missing out on the possibility of an improved experience, better retention, and better achievement.

Staff are missing the opportunity to develop skills to use analytics to improve support, teaching and curriculum design.

Timescale

Pilot tools and metrics 1-2 years

Impact on retention, achievement and progression 3-4 years.


What do we mean by Learning Analytics?

The application of big data techniques such as machine based learning and data mining to help learners and institutions meet their goals:

For our project:

» Improve retention (current project)

» Improve achievement (current project)

» Improve employability (current project)

» Personalised learning (future project)


About Learning Analytics…Products and Solutions


Jisc’s Learning Analytics Project

10

Three core strands:

Learning Analytics Service

Toolkit Community


Learning Analytics - Initial Meetings 2015

Jisc’s Learning Analytics Service Walkthrough

11

Learning Analytics Service



A user perspective…


Dashboards

14

Visual tools to allow lecturers, module leaders, senior staff and support staff to view:

» Student engagement

» Cohort comparisons

» etc…

Based on either commercial tools from Tribal(Student Insight) or open source tools from Unicon/Marist (OpenDashBoard)



First version will include:

» Overall engagement

» Comparisons

» Self declared data

» Consent management

Bespoke development by Therapy Box

16

Student App



Alert and Intervention System

Tools to allow management of interactions with students once risk has been identified:

» Case management

» Intervention management

» Data fed back into model

» etc…

Based on open source tools from Unicon/Marist (Student Success Plan)



Timeline and next steps…



Phase 1&2Sep 15 – Apr 16

Phase 2&3 Jan – Sept 16

Transition to Service

Sept 16 – July 17

Jisc Learning Analytics Service

Sept 2017

22

Jisc/UniconDiscovery


Implementation

Wish to explore readiness and products

Know you are ready and what you want

Want to get involved in tech work first

Blackboard Discovery

Unicon/Marist pre-implementation

Tribal pre-implementation

Other pre-implementation

Blackboard Trial

Moodle Trial

Other Learning Analytics

Implementation

Tech Trials Discovery Pre-implementation Implementation


Next Steps

Review Legal and Ethical issues – Code of Practice

Discovery Stage – See offers from Blackboard and Unicon

Technical Overview – Register and enrol https://courses.alpha.jisc.ac.uk

Technical Trials – Set up Learner Records Warehouse, install VLE plugin, identify and

share, look data sets for student information

Technical Implementation – chose preferred analytics solution (Tribal Student Insights or

Unicon processor and dashboard). Jan 2016 onwards for implementation.



https://courses.alpha.jisc.ac.uk

The student app…


Student Learning Analytics App 26

When first logging in the student is able to select their institution from a pre-populated lists of UK universities. If the students’ institution is using other parts of Jisc’s learning analytics architecture, in particular the learning analytics warehouse, then much more data will be available to the app.


The screen will be an activity feed or timeline, we plan to integrate this dynamic and engaging concept, so essential to applications such as Twitter and Facebook.

Photos or badges could be included next to the text.


Stats – Provides an engagement and attainment overview and drilling down to gives comparative activity graphs.

Log – Allows you to log time spent on specified activities e.g. reading for an assignment

Target – Allows you set personal targets to improve your engagement e.g. study for 10 hours this week


The engagement and attainment overview mirrors what many fitness apps do: it provides an overview of your “performance” to date. Critically here we show how you compare to others. This will be based on data about you and others held in the learning analytics warehouse.


In the activity comparison screen you’ll see a graph of your engagement over time and how it compares with that of others. You can select a particular module or look at your whole course.

You can compare yourself with people on my course, people on this module and top 20% of performers (based on grades).

Comparing yourself to prior cohorts of students on a module might be of interest in the future too.


Starting an activity allows you to select the module on which you’re working, choose an activity type from a drop-down list such as reading a book, writing an essay, or attending a lab, and select a time period you want to spend on the activity and whether you want a notification when that period is up.

A timer is displayed in the image box and you can hit the Stop button when you’ve finished. The timer will continue even if you navigate away from the app.


Setting a target is the final bit of functionality we want to include in the app at this stage. Again this is building on the success of fitness tracking apps where you set yourself targets as a way of motivating yourself.


Setting a target involves selecting a learning activity from a pre-populated list and specifying how long you want to be spending on it.

We added a “because” free text box so that learners can make it clear (to themselves) why they want to carry out the activity e.g. I want to pass the exam, tutor told me I’m not reading enough).

Users may be more likely to select a reason from a pre-populated list than to fill in a text field but we’ll monitor this to see whether it’s being used.

Jisc Learning Analytics Toolkit

34

Toolkit


Discovery …

The learning analytics discovery service is a way of

investigating your institution’s readiness for learning

analytics. The process will investigate strategic,

technical, process and data readiness, providing

recommendations for action before moving on to deploy

a learning analytics solution.


http://www.jisc.ac.uk/guides/code-of-practice-for-learning-analytics

Code of Practice


Deeper Dive

http://repository.jisc.ac.uk/5661/1/Learning_Analytics_A-_Literature_Review.pdf

Literature review – basis

for the code of practice


Code of Practice

Privacy

Validity

Responsibility

AccessEnabling positive

interventions

Minimising adverse impacts

Transparency and consent


39

Community

Community


Project Blog, mailing list and network events

Blog: http://analytics.jiscinvolve.org

Mailing: [email protected]


How can institutions get involved…

41

Toolkit



Phase 1&2Sep 15 – Apr 16

Phase 2&3 Jan – Sept 16

Transition to Service

Sept 16 – July 17

Jisc Learning Analytics Service

Sept 2017

Timeline

Jun 15 Sep 15 Jan 16 Apr 16

3. Trial Integration pt1

x 2

1. Jisc complete contracts

2. Jisc Sandbox4. Phase 1 Discovery

5. Phase 1 implementation

x 6

8. Phase 2 implementation

x 6 - 12

6. Trial Integration pt2

x 2

7. Phase 2 Discovery x 6-

12


44

Jisc/UniconDiscovery


Implementation

Wish to explore readiness and products

Know you are ready and what you want

Want to get involved in tech work first

Blackboard Discovery

Unicon/Marist pre-implementation

Tribal pre-implementation

Other pre-implementation

Blackboard Trial

Moodle Trial

Other Learning Analytics

Implementation

Tech Trials Discovery Pre-implementation Implementation


[email protected]

One Castlepark Tower Hill Bristol BS2 0JAT 020 3697 5800

[email protected] jisc.ac.uk

Michael WebbDirector of Technology and Analytics

45

How’s the data collected?



About the student Activity data

TinCan(xAPI)ETL

Data collection

About the student’ data

Personal (demographic) data

Birthdate, gender etc.

Course data

mode of study, level etc.

Grade data

Assignment, module etc.

(aligned with HESA data)


Activity data via Tin Can API

• People learn from interactions with other

people, content, and beyond.

• These actions can happen anywhere and signal

an event where learning could occur.

• When an activity needs to be recorded, the

application sends secure statements in the

form of “Actor, verb, object” or “I did this” to

the Learning Record Store (LRS.)

from: http://tincanapi.com/


http://tincanapi.com/what-is-tin-can/overview/what-is-an-lrs/

http://tincanapi.com/what-is-tin-can/overview/what-is-an-lrs/

Activity Data (trivial!) examples

50

Actor Action Object Result

Michael Accessed VLE

Sally Completed Basic Maths Test 85.0

Kim Module CommentAdded

https://registry.tincanapi.com



‘Recipes’ are key

• ‘Recipes’ are a shared way of describing

activities..

• So the data from ‘accessing a course’ is the

same whether Moodle or Blackboard is

used.

• The same holds for..

• ‘Attend a lecture’

• ‘Borrow a book’

• …


Education

Phase 1 Learning Analytics Intro Slides