Learning

1
A study in Curriculum Minds
Bureau of
Educational
BEHAVIORAL PREDICTIONS UNIT
Deb Davis Scott Migdalski William
Taylor investigators
Analytics
Learning
Note the play on words from the Television
series Criminal Minds is strictly intended to
provide educational lightheartedness, leading to
a remembrance of the material.
2
Using Analytics to Profile Behaviors for
Student Success

• The Crime Ignorance
• The Evidence
• Reduced test scores
• Unhappy teachers
• Remediation at college level
• The Victims our students
• The Unknown Subject (UnSub)
• The teaching method that suits that student!

3
As we Quest Onward, Remember . . .

• Education is the most powerful weapon you can use
  to change the world.
• - Nelson Mandela

4
The story line

• How can the teacher know?
• Education Experience Instinct
• A vignette of personal reflection

5

• Descriptive?
• Data
• Diagnostic?
• Assignments
• Predictive?
• Future likelihood
• Prescriptive?
• Change the future

6
Learning Analytics Defined

• the measurement, collection, analysis and
  reporting of data about learners and their
  contexts, for purposes of understanding and
  optimising sic learning and the environments in
  which it occurs(Scheffel, Drachsler, Stoyanov,
  Specht, 2014, p. 117)
• In other words, the more we learn about our
  students, the better we can aid them in learning.
• The cycle of learning analytics allows for the
  data to be compiled and analyzed to direct
  intervention for learners.

7
Learning Analytics

• By funneling in elements of descriptive data from
  prior actions and traits, educators can diagnose
  issues and thus predict the pitfalls students may
  face and prescriptively redirect those students.
• How does it happen?
• What does it take?
• How does it work?
• What will it do?

8
Big Data

• What is Big Data?
• Laymans terms - Big data is just a vastly large
  amount of data that cannot be analyzed at one
  time.

• Big Data is state-of-the-art techniques and
  technologies to catch, collection, allocate,
  accomplish and explore petabyte- or larger-sized
  datasets with high-speed and varied patterns that
  predictable data management methods are unable to
  control (Drigas Leliopoulos, 2014).

9
How "Big" is Data?

• Bit (Single Binary Digit) 1 or 0
• 8 bits 1 byte
• 1024 byte 1 Kilobyte
• 1024 Kilobytes 1 Megabyte
• 1024 Megabytes 1 Gigabyte
• 1024 Gigabytes 1 Terabyte
• 1024 Terabytes 1 Petabyte
• To help understand how gigantic Big Data is, look
  at the infographic on the next slide that
  explains about Petabytes!

10
(No Transcript)
11
The Data Story

• How did we get to this point?
• The buildup of Big Data starts before the
  invention of Google in 1998 and before Apple
  began in 1976 (Barnes, 2013).
• Hollerith Tabulating Machine allowed the 1890
  Census to be complete in about a year (Truesdell,
  1965).

12
The Data Story

• Holleriths Tabulation Machine Company merged
  with Computing-Tabulating-Recording Company in
  1911 and became International Business Machines
  Corporation (IBM) in 1924 (Austrian, 1982).
• Tesla predicts pocket computers in 1926 (Kennedy,
  1926)
• Pfleumer creates magnetic tape in 1928 (Weiss,
  2000)

13
The Data Story

• In 1944, Rider predicts 2040 Yale library would
  need 6000 miles of shelving (Kent, Lancour
  Daily, 1980).
• Data storage of tax returns and fingerprints
  planned in 1965 (Kraus, 2011).
• Codd creates relational database model in 1970
  (Gray, 2004)

14
How Learning Analytics can make us better
15
Converting Reality to Data (Adapting Traits)

• Students generally know themselves. (Ngidi,
  2013).
• People have different characteristics which
  affect their life affairs even the way they
  learn is influenced by these personal
  characteristics (Boroujeni, A., Roohani, A.,
  Hasanimanesh, A., 2015, p. 212)
• Aptitude tests discover relevant training
  programs, identify talents, and allow for traits
  to become data (Barrett, 2012)

(Furnham, Monsen, Ahmetoglu, 2009, p. 770)
16
Using the Past to Predict the Future

• Student Data Points
• Student Behavior Data Points
• Next Stop Lrng Analytics Funnel
• Determine Predictors-Course Success
• Sample Method Linear Regression to Correlate
• Student Data/Course Predictors

17
Adapting Students Traits to Data Points
18
Selecting the Significant Data Points for Course
19
Charting the Most Significant Data Points
20
Selecting Significant Influential Data Points
21
Learning Analytics Dashboards
(Dringus 2012)
22
LA Profiles Prescriptive Interventions

• Using Student Data/Behavior and Applying
  Learning Analytics to PROFILE Todays Learners
  and Improve Teaching and Learning
• (Curriculum Minds Team 2015)

23
Learning Analytics Support Valid Prescriptions
Proactive Course Predictors of Success
Reactive Student Perf. Improv. Plan
Increase Amount of Time Reading, Reviewing, and
Responding to Discussion Board Posts
24
Did we Solve the Case?
25
Summary

• Our students should not be bound by ignorance of
  their own learning style.

26
Conclusion

• We have found our unknown subject That learning
  method that allows early detection of academic
  issues. Using the analytics of learning, we can
  continue to push onward toward the elimination of
  ignorance in this field!
• Break the chains of learning challenges

27
As we Return from this Quest, Remember . . .

• Never doubt that a small group of thoughtful,
  committed citizens can change the world. Indeed,
  it is the only thing that ever has.
• - Margaret Mead

28
Questions?
29
References

• Austrian, G. D. (1982). Herman Hollerith The
  forgotten giant of information processing.
  Columbia.
• Barrett, J. (2012). Ultimate aptitude tests.
  electronic resource assess and develop your
  potential with numerical, verbal and abstract
  tests. London Philadelphia Kogan Page, 2012.
• Barnes, T. J. (2013). Big data, little history.
  Dialogues in Human Geography 3 297302, doi
  10.1177/2043820613514323
• Boroujeni, A., Roohani, A., Hasanimanesh, A.
  (2015). The Impact of Extroversion and
  Introversion Personality Types on EFL Learners'
  Writing Ability. Theory Practice In Language
  Studies, 5(1), 212-218. doi10.17507/tpls.0501.29
• Drigas, A. S. Leliopoulos, P. (2014). The use
  of big data in education. International Journal
  of Computer Science Issues, 11(5). 58.
• Dringus, L. P. (2012). Learning Analytics
  Considered Harmful. Journal Of Asynchronous
  Learning Networks, 16(3), 87-100.

30
References

• Furnham, A., Monsen, J., Ahmetoglu, G. (2009).
  Typical intellectual engagement, Big Five
  personality traits, approaches to learning and
  cognitive ability predictors of academic
  performance. The British Journal Of Educational
  Psychology, 79(Pt 4), 769-782. doi10.1348/9781854
  09X412147
• Kennedy, G., Ioannou, I., Zhou, Y., Bailey, J.,
  O'Leary, S. (2013). Mining interactions in
  immersive learning environments for real-time
  student feedback. Australasian Journal Of
  Educational Technology, 29(2), 172-183.
• Kent, A., Lancour, H., Daily, J. E. (1980).
  Encyclopedia of Library and Information Science,
  29. CRC Press.
• Ngidi, D. P. (2013). Students' personality traits
  and learning approaches. Journal Of Psychology In
  Africa, 23(1), 149-152.

31
References

• Scheffel, M., Drachsler, H., Stoyanov, S.,
  Specht, M. (2014). Quality Indicators for
  Learning Analytics. Journal Of Educational
  Technology Society, 17(4), 117-132.
• Truedsell, Leon E. (1965). The development of
  punch card tabulation in the Bureau of the Census
  1890-1940. United States Government Printing
  Office. p. 51.
• Weiss, E.A. (2000). Magnetic recording, the first
  100 years. IEEE, Annals of the History of
  Computing 22(1). doi 10.1109/MAHC.2000.815472