Information
• Foundations
• Sources of information
• Getting access to information
• Analysis
• Modeling
Competition
• Split into two groups
– Group A
– Group B
• Given two learning scenarios
• Generate a list of all the differ...
Scenarios
Face-to-face lecture
(group A)
• 300 students
• 1 lecture theatre
• Assume each student has
any other technology...
http://echo360.com/teaching-tools
Questions
• Eric Mazur?
• YouTube?
• What does it tell you about learning?
• Video interlude?
Big Data
• CERN LHC produced 23 petabytes in 2011
(Clow, 2013)
• Google was processing 7,300 petabytes in
2008
• Square Ki...
http://research.microsoft.com/en-us/collaboration/fourthparadigm/
Different mindsets
The volume and scope of data can be so large
that it is possible to start with a data-set and
apply com...
Retail example
“As Pole’s computers crawled through the
data, he was able to identify about 25 products
that, when analyse...
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
Peoples...
665 Gb == how many petabyes?
665 Gb == how many petabyes?
0.000634193
MIS
Records on all
students, including
socio-demographic
VLE
Every click by each
user, every activity
by staff and student...
Orde
r
Variable Indicator
1 % of student usage between 9am and 9pm 906
2 # of days from start of term when student
last ac...
http://xkcd.com/552/
Sources of information
• A chance for revenge
• Two groups
– List all of the sources of information that might
become your...
How do you access it?
• Given your list of information sources
– Could you access that data?
– What barriers are their to ...
Some barriers
• Data interoperability
– Privacy concerns
– Diversity of data sets and sources
– Lack of standard represent...
http://flickr.com/photos/tonymangan/754511201/
Pitfalls
it also triggers significant conceptual and practical
discontinuiti...
http://dilbert.com/strips/comic/2010-10-12/
Retail examples
“Because, you see, customers who drink lots of
milk and eat lots of red meat are very, very good
car insur...
Retail example
“My daughter got this in the mail!” he said.
“She’s still in high school, and you’re sending her
coupons fo...
Retail example
“But even if you’re following the law, you can do
things where people get queasy”.
http://onforb.es/196nzty
JISC risks
• Legal
– Data protection (privacy), Confidentiality & Consent,
FOI, IPR
• Ethical
– Principles for collection,...
Considerations Slade & Prinsloo
• Who benefits and under what conditions?
– All key stakeholders (other users)
– Students ...
Findings
• Policy focuses on academic analytics and
research
• Mostly in response to legislative requirements
• May not be...
Forms of analysis
• Usage tracking
• Simple and complex statistical analysis
• Social network analysis
• Predictive modeli...
http://flickr.com/photos/tonymangan/754511201/
Pitfalls
Data-driven decision making does not
guarantee effective decision ...
http://flickr.com/photos/tonymangan/754511201/
Pitfalls Complex and likely to fail
made little use of the intelligence
rev...
4   information
Upcoming SlideShare
Loading in...5
×

4 information

340

Published on

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
0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total Views
340
On Slideshare
0
From Embeds
0
Number of Embeds
1
Actions
Shares
0
Downloads
2
Comments
0
Likes
0
Embeds 0
No embeds

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
  • 4 information

    1. 1. Information • Foundations • Sources of information • Getting access to information • Analysis • Modeling
    2. 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. 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. 4. http://echo360.com/teaching-tools
    5. 5. Questions • Eric Mazur? • YouTube? • What does it tell you about learning? • Video interlude?
    6. 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 http://www.computerweekly.com/feature/What-does-a-petabyte-look-like
    7. 7. http://research.microsoft.com/en-us/collaboration/fourthparadigm/
    8. 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. 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.” http://onforb.es/196nzty
    10. 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. 11. 665 Gb == how many petabyes?
    12. 12. 665 Gb == how many petabyes? 0.000634193
    13. 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. 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. 15. http://xkcd.com/552/
    16. 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. 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. 18. Some barriers • Data interoperability – Privacy concerns – Diversity of data sets and sources – Lack of standard representation – Distribution across space, time and media
    19. 19. http://flickr.com/photos/tonymangan/754511201/ 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. 20. http://dilbert.com/strips/comic/2010-10-12/
    21. 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 http://bit.ly/19X0ta3
    22. 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?” http://onforb.es/196nzty
    23. 23. Retail example “But even if you’re following the law, you can do things where people get queasy”. http://onforb.es/196nzty
    24. 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. 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. 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. 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. 28. http://flickr.com/photos/tonymangan/754511201/ 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. 29. http://flickr.com/photos/tonymangan/754511201/ Pitfalls Complex and likely to fail made little use of the intelligence revealed by the analytics process (MacFadyen & Dawson, 2012, p. 49)
    1. A particular slide catching your eye?

      Clipping is a handy way to collect important slides you want to go back to later.

    ×