Workshop on visual learning analytics that was part of LASI 2014 - http://www.solaresearch.org/events/lasi-2/lasi2014/ Examples of learning dashboards were presented during the workshop by Sven Charleer: http://www.slideshare.net/svencharleer/learning-dashboard-visual-learning-analytics-workshop-lasi2014-h-harvard

1. Visual learning analytics
Joris Klerkx
Research Expert, PhD.
@jkofmsk
Sven Charleer
Phd candidate
@svencharleer
Erik Duval
Professor
@erikduval
http://www.slideshare.net/jkofmsk

2. Our team
HCI lab
!
technology enhanced le
music
research
(personal) health

3. 3 http://eng.kuleuven.be/datavislab/

5. About you…
Why are you interested in this workshop?

6. Agenda (more or less)
• BEFORE THE BREAK:
• Information visualization (theory)
• Group work - Design & Sketch your first visualizations
• AFTER THE BREAK:
• (Visual) Learning Analytics Dashboards
• Tips `n tricks
• Group work - Design your own learning analytics dashboard

7. WHAT?

8. http://www.slideshare.net/infoscape

9. Information Visualisation is the use of
interactive visual representations to amplify
cognition [Card. et. al]

10. Anscombe`s quartet
!
uX = 9.0
uY = 7.5
sigma X = 3.317
sigma Y = 2.03
Y = 3 + 0.5X
Discover patterns in the data
http://en.wikipedia.org/wiki/Anscombe's_quartet

11. Tell the story behind the data
Will there be enough food?
Communicate data
http://www.footprintnetwork.org/en/index.php/gfn/page/earth_overshoot_day/

12. http://infosthetics.com/
http://visualizing.org
http://www.visualcomplexity.com/vc/
http://visual.ly/
http://flowingdata.com
http://www.infovis-wiki.net
http://datastori.es/
http://helpmeviz.com/
…

13. (Just enough) THEORY

14. How many circles?

15. Humans have advanced perceptual abilities
Our brains makes us extremely good at recognizing visual patterns

16. ¡ Law of Symmetry
Objects must be balanced or
symmetrical to be seen as complete or
whole (Chang, 2002).
Gestalt Principles
http://www.slideshare.net/chelsc/gestalt-laws-and-design-presentation
¡ Law of Proximity
The closer objects are to each other, the
more likely they are to be perceived as a
group (Ehrenstein, 2004)

17. ¡ Law of Similarity
Objects that are similar, with like
components or attributes are
more likely to be organised
together (Schamber, 1986).
Objects are viewed in vertical rows because of
their similar attributes.
¡ Law of Common Fate
Objects with a common movement, that
move in the same direction, at the same
pace , at the same time are organised as a
group (Ehrenstein, 2004).
Gestalt Principles
http://www.slideshare.net/chelsc/gestalt-laws-and-design-presentation

18. ¡ Law of Continuation
Objects will be grouped as a whole if they are co-
linear, or follow a direction (Chang, 2002; Lyons, 2001).
¡ Law of Isomorphism
!
Is similarity that can be behavioural or perceptual,
and can be a response based on the viewers
previous experiences (Luchins & Luchins, 1999;
Chang, 2002). This law is the basis for symbolism
(Schamber, 1986).
There are many more!http://www.slideshare.net/chelsc/gestalt-laws-and-design-presentation
Gestalt Principles

19. Which visual encodings do you see?
London Tube Map

20. http://artspilesenglish.blogspot.be/2011/11/gestalt-theory-exercise-for-3rdlevel.html
http://www.slideshare.net/chelsc/gestalt-laws-and-design-presentation

21. A limited set of visual properties that are detected very rapidly (< 250 ms)
in multi-element display and accurately by the low-level visual system.
Pre-attentive characteristics
Find the red dot
<> Hue
Find the dot
<> shape
Find the red dot
conjunction
not pre-attentive
http://www.csc.ncsu.edu/faculty/healey/PP/

22. Pre-attentive characteristics
Line orientation Length, width Closure Size
Curvature Density, contrast Intersection 3D depth

23. Do not help with showing exact quantitative differences
Pre-attentive characteristics help to spot differences in
multi-element display
E.g. size & radius

24. How to start your visualization?
Data set Visualisation

25. Step 1. Get to know your data
Time? hierarchical? 1D? 2D? nD? network? …
Quantitive, ordinal, categorical?
S. Stevens “On the theory of scales and measurements” (1946)

26. What is the average amount of students that bought the course book ?
Step 2. Formulate questions about your data
What? When? How much? How often? (why?)
When did students start looking at the course material?
How much hours did Peter work on this assignment?
(Why did Peter have to redo his assignment?)
How often did Peter retake the course before he passed?

27. Encode data characteristics into visual form
Step 3: Apply a visual mapping
Simplicity is the ultimate sophistication.
Leonardo da Vinci
Each mark (point, line, area,…) represents a data element
Think about relationships between elements (position)

30. Find all possible ways to visualize a
small data set of two numbers { 75, 37 }
http://blog.visual.ly/45-ways-to-communicate-two-quantities/
+/- 15 minutes
Small groups - sketch
EXERCISE

31. Learning analytics
31

32. Collecting traces that learners leave behind
and using those traces to improve learning
http://erikduval.wordpress.com/2012/01/30/learning-analytics-and-educational-data-mining/
Learning analytics
32

33. What to measure?
Depends on the user
33

34. Example traces of Students
access to learning resources
posts in discussion fora
logins to learning management systems
posts of assignments
replies to posts
votes in lecture response systems
time on page in electronic textbook
location of device used to access course
(and thus proximity to other users)
software lines produced
contributions to shared documents or wikis
etc.
Who?
!
!
What?
!
!
When?
34

35. Analytics for professors
35

36. email, twitter, facebook, web reading, physical
movement, location, proximity, food intake,
sleeping, drinking, emotion tracking, weather
info, attention, brainwaves, …
As learning moves online,
traces also include…
36

37. EXERCISE
1. Brainstorm about a learning analytics data set
!
Choose +/- 5 types of user traces
2. Get to know this data
!
Time? hierarchical? Quantitative? Categorical? …
3. What questions do you have about this data
!
what? when? How much? etc.
4. Apply a visual mapping
!
Marks, position, color, shape,
gestalt principles, pre-attentive characteristics

38. Sketch

39. BREAK

40. LEARNING DASHBOARDS
(SVEN)

41. Tips `n tricks

42. Real data is ugly and needs to be cleaned
http://www.netmagazine.com/features/seven-dirty-secrets-data-visualisation
https://code.google.com/p/google-refine/
http://vis.stanford.edu/wrangler/
Pre-process your data
http://hcil2.cs.umd.edu/trs/2011-34/2011-34.pdf

43. Forget about 3D graphs
Occlusion
Complex to interact with
Doesn’t add anything

44. Size & angle are not pre-attentive: difficult to compare
Limited Short term (visual) memory
Save the pies for dessert (S.Few)
Which student has more blogposts?

46. 0"
5"
10"
15"
20"
25"
30"
blogposts" tweets" comments"on"
blogs"
reports"
submi6ed"
Student'1'
Student"1"
0"
5"
10"
15"
20"
25"
30"
blogposts" comments"on"
blogs"
tweets" reports"
submi6ed"
Student'1'
Student"1"
Use common sense
0" 5" 10" 15" 20" 25" 30"
blogposts"
comments"on"blogs"
tweets"
reports"submi6ed"
Student'1'
Student"1"

47. 0" 10" 20" 30" 40" 50" 60"
Student"1"
Student"2"
Student"3"
Student"4"
blogposts"
tweets"
comments"on"blogs"
reports"submi:ed"
0%# 20%# 40%# 60%# 80%# 100%#
Student#1#
Student#2#
Student#3#
Student#4#
blogposts#
tweets#
comments#on#blogs#
reports#submi;ed#
What/how are you comparing?
What story do you get from it?
Use common sense

48. http://www.perceptualedge.com/
Which graph makes it easier to focus on the pattern of change through
time, instead of the individual values?
Choose graph that answers your questions about
your data

49. http://flowingdata.com/category/statistics/mistaken-data/
BP - leak in gulf of mexico
Don`t use misleading visualizations

50. Don`t use visualizations to lie... http://www.perceptualedge.com/
http://flowingdata.com/category/statistics/mistaken-data/

51. http://flowingdata.com/category/statistics/mistaken-data/http://flowingdata.com/category/statistics/mistaken-data/
Don`t use visualizations to lie...

52. Humans have little short term (visual) memory
Our brain remembers relatively little of what we perceive
Humans have advanced perceptual abilities
Our brains makes us extremely good at recognizing visual patterns
Interaction techniques and visual cues can help

53. http://www.youtube.com/watch?v=OVlJv7ZkvGA

54. http://queue.acm.org/detail.cfm?id=2146416

55. EXERCISE
1. Reiterate over previous visual mappings
!
Incorporate feedback, lessons learned
2. Walk around and present your work to each other
!