Factors for Consideration in Learning Analytics; Analysing Student Activity on the KLE to produce a more personalised and supportive system of education

Traditionally a student's progress and level of engagement has been measured by assessment and physical attendance. However, in a student's day-to-day interactions with a University, other real-time measures are being generated e.g. VLE interaction. The analysis of this data has been termed Learning Analytics (LA). Following on from successful work at the University of Greenwich (de Quincey and Stoneham, 2014), this project aims to identify potential sources of data at Keele that are suitable for LA and how they can be used to produce a more personalised and supportive system of education, in the form of a Learner Dashboard.

Transcript

1. Factors for Consideration in Learning Analytics;
   Analysing Student Activity on the KLE to
   produce a more personalised and supportive
   system of education
   Dr Ed de Quincey, Dr Mark Turner, Dr Theo Kyriacou, Dr Nikki Williams
   School of Computing and Mathematics, KeeleUniversity Photo by GotCredit
   www.gotcredit.com
   

   View Slide

2. TRADITIONALLY A STUDENT’S PROGRESS AND LEVEL OF
   ENGAGEMENT HAS BEEN MEASURED BY ASSESSMENT
   Photo by Alberto G.
   https://www.flickr.com/photos/albertogp123/5843577306
   

   View Slide

3. HOW ELSE CAN WE MEASURE ENGAGEMENT
   AND PROGRESS IN REAL-TIME?
   Photos by
   Cropbot https://en.wikipedia.org/wiki/Lecture_hall#/media/File:5th_Floor_Lecture_Hall.jpg
   See-ming Lee https://www.flickr.com/photos/seeminglee/4556156477
   

   View Slide

4. Learning Analytics
   has been defined as a method for
   “deciphering trends
   and patterns from
   educational big data
   … to further the
   advancement of a
   personalized,
   supportive system
   of higher education.”
   (Johnson et al., 2013)
   Co-authorship network map of physicians publishing on hepatitis C (detail)
   Source: http://www.flickr.com/photos/speedoflife/82749 93170/
   

   View Slide

5. NTU student dashboard:
   Learning analytics to improve retention
   

   View Slide

6. Blackboard Analytics
   

   View Slide

7. PRESENTING STUDENT DATA BACK TO STUDENTS and LECTURERS,
   USING USER CENTRIC QUERIES, FORMATS and METAPHORS
   

   View Slide

8. View Slide

9. WP1. KLE Data Review
   A review of activity log data that are
   currently available via the KLE.
   ✓
   ✖
   

   View Slide

10. ✓
    ✖
    

    View Slide

11. WP1. KLE Data Review
    A review of activity log data that are
    currently available via the KLE.
    ✓
    ✖
    Around 11 “reports” available
    9 Course Reports, a Performance Dashboard and a Retention Centre
    Inconsistent formats
    Reports take a long time to run
    No way to bulk download all “raw” data
    Single Course User Participation Report is the most
    useful BUT have to run for each student
    

    View Slide

12. WP1. KLE Data Review (and WP2. LA Pilot Study)
    A set of log files, generated from
    previous KLE module activity.
    ✖
    ✖
    Data Persistence
    Logs deleted after 6 months
    Data Protection/Usage Policy
    Current policies do not cover usage for Learning
    Analytics
    

    View Slide

13. Identified and Reviewed 22 Learning Analytics Systems
    

    View Slide

14. Review of Existing Systems
    Few systems available for general use
    ✖
    Primarily targeted at educators. Only 5 of the 22
    systems being designed purely for use by students
    Only 4 of the studies gathered the requirements for
    the systems directly from students
    Currently analysing visualisation techniques used
    and types/sources of data used
    

    View Slide

15. WP3. Requirements Gathering
    Set as Coursework Case Study
    Contextual Interviews with staff
    2nd Year Computing Module
    84 students in 14 groups
    Asked questions as they complete tasks on the KLE
    2 completed so far
    

    View Slide

16. WP3. Requirements Gathering
    Preliminary results from Thematic Analysis of key
    features students said the dashboard should include:
    Students want an overview of their activity/learningi.e.
    everything one place
    Comparison to average seems important
    Common metaphor was a timeline/calendari.e. students
    wanting a way of showing their progress against deadlines
    Common functionality was support for (Instant) Messaging/
    Discussion
    

    View Slide

17. 'My Timeline': Past events which have been completed successfully provide
    gratification to the user in the form of positive icons such as thumbs up or smiley faces.
    The past timeline balances with the upcoming events to try and alleviate future workload
    stress by demonstrating positive success at the same time.
    

    View Slide

18. Digital Synchable Diary: The diary can be edited and synced to
    various devices; A countdown system to exams and assignments;
    The ability for students to set prioritiesto set work.
    

    View Slide

19. Course/Module Progress Bar: a progress bar based upon the how far in the course
    users are. Indicating how much of the course they should know and how much time is
    left until the course finishes.
    

    View Slide

20. Score Indicator: The score indicator is a metric derived from an algorithm
    which would track a student’s engagement with course materials and
    other important areas of engagement that students should be utilising
    (comments,discussion).
    

    View Slide

21. Degree Classification Requirements: Panel showing the Percentage
    needed in Future Assignments to get certain Degree Classifications.
    

    View Slide

22. Comparison with peers: The chance for the user to see how
    they are comparing with the top 20% of the class and how they
    are doing comparedwith the average mark.
    

    View Slide

23. Goals and Trophies: The student will get a list of goals or tasks
    sent to their dashboard and there they can also add more tasks
    of their own.
    

    View Slide

24. News Feed: An aggregated news feed is a pattern followed on many
    major platforms, and provides a intuitive way to group content into a
    digestible stream of informationfrom multiplesources (modules).
    

    View Slide

25. Discussion Forum: An open forum within the learning dashboard application, to allow
    students to post questions about specific issues related to their course or to materials,
    and for staff to then see where collective issues were found
    

    View Slide

26. WP3. Requirements Gathering
    Contextual Interviews with staff
    • Accesses does not necessarily mean engagement.
    • Only interested in low values e.g. not accessed for a long time.
    • Current inaccurate Dashboard and the Retention Centre alerts makes
    people feel less trustful of the data.
    • Information in current reports interesting rather than being useful.
    • Comparison against average values (for a module/class) is
    important as it provides context to the data, otherwise it is not clear
    what is 'good' or 'bad'.
    • The reports need to be easy and quick to run/use.
    • No easily accessible method for seeing a student’s overall level of
    interaction on all modules
    

    View Slide

27. WP4. Implementation of Prototype LA Dashboard
    WP5. Pilot Study into uses of LA Dashboard within a Module
    Python programme that utilises 2 reports to calculate files uploaded since last login
    

    View Slide

28. View Slide

29. View Slide

30. Personalised (semi) automated reminder emails
    

    View Slide

31. Good morning
    class…
    Do you prefer lecturing in the dark?
    

    View Slide