Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

LAK16 keynote Learning Analytics: Utopia or Dystopia

4,749 views

Published on

Here my April 28 keynote at LAK16 in Edinburgh on Utopian and Dystopian Futures of Learning Analytics

Published in: Education

LAK16 keynote Learning Analytics: Utopia or Dystopia

  1. 1. Learning Analytics: Utopia or Dystopia Prof. dr. Paul A. Kirschner Distinguished University Professor Open University of the Netherlands
  2. 2. Thanks
  3. 3. Disclaimer This keynote is not about: • Privacy issues / Data protection / Big Brother • Ethical aspects / questions • Legal aspects / questions • Commercial interests / Business optimisation • Technology, Techniques, Dashboards, etcetera • … To paraphrase Bill Clinton: It’s the learning, people!
  4. 4. Your task Mr. Phelps – Mission Impossible?
  5. 5. Learning
  6. 6. National Tsing Hua Univerity Learning Sciences
  7. 7. Learning Analytics Model (Siemens, 2013) (Siemens, 2013)
  8. 8. Learning Analytics Model (Siemens, 2013) Dystopia 1: Myopic vision of what learning is
  9. 9. Learning Analytics Model (Siemens, 2013)
  10. 10. Missing link?
  11. 11. Learning Sciences theory as missing link • Variables to include in a model • Potential confounds, subgroups, or covariates in the data • Which results to attend to • Framework for interpreting results • How to make results actionable • Generalisation of results to other contexts and populations
  12. 12. Not only true of the US elections Dystopia 2: Theory Free / Theory Poor LA
  13. 13. What are we looking for?
  14. 14. Meaningful variables? Dystopia 3: Looking at wrong or invalid variables
  15. 15. Dystopia 4: Seeing Correlation as Causal
  16. 16. Spurious correlations http://tylervigen.com/spurious-correlations http://tylervigen.com/discover
  17. 17. Unintended consequences http://interactioninstitute.org/unintended-consequences/ Dystopia 5: Unintended and unwanted effects
  18. 18. Goal orientation http://buehlereducation.com/pedagogy-assessment/goal- orientation-theory-and-education/
  19. 19. Pigeonholing / Profiling / Stereotyping
  20. 20. Predict Utopia 1: Knowing what will happen (and when and why)
  21. 21. Simple data Dietz-Uhler & Hurn (2013). Using Learning Analytics to Predict (and Improve) Student Success: A Faculty Perspective
  22. 22. Adapt / Personalise? Utopia 2: Custom tailored learning and instruction
  23. 23. Learning / study strategies Summarise Highlight/underline Elaborative questions Restudy Generate keywords Distribute practise Variable practise Visualise Explain (Self) Testing Dr. Gino Camp – Welten Institute, OUNL
  24. 24. Variability of practise a‐a‐a‐b‐b‐b‐c‐c‐c‐d‐d‐d versus a‐b‐c‐d‐a‐b‐c‐d‐a‐b‐c‐d Ten steps to complex learning – Van Merriënboer & Kirschner
  25. 25. Recommend / Advise / Intervene Utopia 3: The right thing for the right learner at the right time
  26. 26. Yong Zheng, Center for Web Intelligence, DePaul University Navisro Analytics: Collaborative Filtering and Recommender Systems
  27. 27. Classification system* * Drachsler et al., Panorama of Recommender Systems to Support Learning
  28. 28. Feedback Utopia 4: Enlightening the learner
  29. 29. A better learning environment Utopia 5: Simply the best • Course improvement • Feedback for staff (instructors, tutors) • Grouping students • Planning and scheduling • Resource allocation • Etcetera
  30. 30. Multimodal data, LA ,  & dashboards for (S)SRL)   http://www.slamproject.org/blog
  31. 31. JCAL special issue “Learning analytics in massively multi-user virtual environments and courses" Available online CODE: JCALLAK16
  32. 32. paul.kirschner@ou.nl @P_A_Kirschner

×