Your SlideShare is downloading. ×
  • Like
4   information
Upcoming SlideShare
Loading in...5

Thanks for flagging this SlideShare!

Oops! An error has occurred.


Now you can save presentations on your phone or tablet

Available for both IPhone and Android

Text the download link to your phone

Standard text messaging rates apply

4 information


Examining the information aspect of learning analytics. …

Examining the information aspect of learning analytics.

Part of the slides for a workshop titled "Four questions for understanding Learning Analytics" by @beerc and @djplaner

Published in Education , Technology
  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
    Be the first to comment
    Be the first to like this
No Downloads


Total Views
On SlideShare
From Embeds
Number of Embeds



Embeds 0

No embeds

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

    No notes for slide
  • We need to get some fantales or similar
  • 665 Gb == 0.000634193 PetabytesBb – 90 Gb 2004 to 2009 + files 600GbMoodle 2 – 2011 T1 – 30GbMoodle 1.9 – 33 Gb T3, 2009 + 2010Peoplesoft database


  • 1. Information • Foundations • Sources of information • Getting access to information • Analysis • Modeling
  • 2. Competition • Split into two groups – Group A – Group B • Given two learning scenarios • Generate a list of all the different types of information you might gather • Points deducted for “task corruption” • Judges decision is final • Discussion
  • 3. Scenarios Face-to-face lecture (group A) • 300 students • 1 lecture theatre • Assume each student has any other technology Online lecture (group B) • Echo360 or similar • Recordings of all lectures • No f-t-f sessions • Assume each student has any other technology
  • 4.
  • 5. Questions • Eric Mazur? • YouTube? • What does it tell you about learning? • Video interlude?
  • 6. Big Data • CERN LHC produced 23 petabytes in 2011 (Clow, 2013) • Google was processing 7,300 petabytes in 2008 • Square Kilometer Array (2024) – 1,376 petabytes per day • A petabyte of MP3 sounds == 2000+ years continuous play
  • 7.
  • 8. Different mindsets The volume and scope of data can be so large that it is possible to start with a data-set and apply computational methods to produce results and to seek an interpretation or meaning only subsequently. (Clow, 2013, p.2)
  • 9. Retail example “As Pole’s computers crawled through the data, he was able to identify about 25 products that, when analysed together, allowed him to assign each shopper a “pregnancy prediction” score. More important, he could also estimate her due date to within a small window, so Target could send coupons timed to very specific stages of her pregnancy.”
  • 10. Big data and L&T? Source Period Size Blackboard 2004-2009 600 Gb Moodle 1.9 2009 & 2010 30 Gb Moodle 2 2011- 33 Gb Peoplesoft 2001- ~ 2 Gb Total 665 Gb
  • 11. 665 Gb == how many petabyes?
  • 12. 665 Gb == how many petabyes? 0.000634193
  • 13. MIS Records on all students, including socio-demographic VLE Every click by each user, every activity by staff and students Student progression related variables Random Forest Algorithm Best predictors of student progression (Hardman et al, 2012, p. 196)
  • 14. Orde r Variable Indicator 1 % of student usage between 9am and 9pm 906 2 # of days from start of term when student last accessed VLE 768 3 Total # of staff document hits for the staff 609 4 Number of student document hits 409 5 Total # of staff chat hits 398
  • 15.
  • 16. Sources of information • A chance for revenge • Two groups – List all of the sources of information that might become your own “big data” – Limit yourself to “systems” – e.g. Lecture capture, LMS, MIS • Judges decision final
  • 17. How do you access it? • Given your list of information sources – Could you access that data? – What barriers are their to using it for LA?
  • 18. Some barriers • Data interoperability – Privacy concerns – Diversity of data sets and sources – Lack of standard representation – Distribution across space, time and media
  • 19. Pitfalls it also triggers significant conceptual and practical discontinuities within adopting organizations, imposes a heavy knowledge burden, creates enterprise-wide dependencies, and triggers considerable political consequences. (Ramamurthy, Sen and Sinha, 2008, p. 979)
  • 20.
  • 21. Retail examples “Because, you see, customers who drink lots of milk and eat lots of red meat are very, very good car insurance risks versus those who eat lots of pasta and rice, fill up their petrol at night and drink spirits. What that means is we’re able to tailor an insurance offer that targets those really good insurance risk customers” -- Woolies, director of retail services
  • 22. Retail example “My daughter got this in the mail!” he said. “She’s still in high school, and you’re sending her coupons for baby clothes and cribs? Are you trying to encourage her to get pregnant?”
  • 23. Retail example “But even if you’re following the law, you can do things where people get queasy”.
  • 24. JISC risks • Legal – Data protection (privacy), Confidentiality & Consent, FOI, IPR • Ethical – Principles for collection, retention and exploitation – Motivation for LA corporate/individual good? – Customer expectation – Obligation to act – duty of care • Immaturity of what exists (Kay et al, 2012)
  • 25. Considerations Slade & Prinsloo • Who benefits and under what conditions? – All key stakeholders (other users) – Students as major stakeholders? • Conditions for consent, de-identification and opting out • Vulnerability and harm • Collection, analyses, access to and storage of data (Prinsloo & Slade, 2013)
  • 26. Findings • Policy focuses on academic analytics and research • Mostly in response to legislative requirements • May not be sufficient to address the specific ethical challenges arising from learning analytics (Prinsloo and Slade, 2013)
  • 27. Forms of analysis • Usage tracking • Simple and complex statistical analysis • Social network analysis • Predictive modeling • Content and semantic analysis • Recommendation engines • Educational Data Mining (Baker & Yacef, 2009) SPSS, Stata, Nvivo, R LMS & other tools SNAPP
  • 28. Pitfalls Data-driven decision making does not guarantee effective decision making. Having data does not necessarily mean that they will be used to drive decisions or lead to improvements. (Marsh, Pane & Hamilton, 2006, p. 10)
  • 29. Pitfalls Complex and likely to fail made little use of the intelligence revealed by the analytics process (MacFadyen & Dawson, 2012, p. 49)