1. Big Data and Learning Analytic in
Education: Research and Practice
Munassir Alhamami
ETEC647E
Spring, 2013
2. Overview
• Big data and Learning analytics was featured in
the NMC Horizon Report:
2010, 2011, 2012, 2013, Higher Education Edition
• Big data is a collection of data sets so large and
complex that it becomes difficult to process using
on hand database management tools or
traditional data processing applications. The
challenges include
capture, curation, storage, search, sharing, transf
er, analysis, and visualization. Wiki
3. Overview
• The term owes its beginnings to data mining
efforts in the commercial sector that used
analysis of consumer activities to identify
consumer trends. Learning analytics is an
emergent field of research that aspires to use
data analysis to inform decisions made on
every tier of the educational system.
4. Big Data for education in research
• Making general statements: huge samples of population
• U.S. Department of Education: Office of Educational
Technology 2012.
• 1=User Knowledge Modeling:
• What content does a student know (e.g., specific skills and
concepts or procedural knowledge and higher order
thinking skills)
• 2=User Behavior Modeling:
• What do patterns of student behavior mean for their
learning? Are students motivated?
• 3= User Experience Modeling
• Are users satisfied with their experience?
5. Big Data for education in research
• 4= User Profiling:
• What groups do users cluster into?
• 5= Domain Modeling:
• What is the correct level at which to divide topics into
modules and how should these modules be
sequenced?
• 6= Learning component analysis and instructional
principle analysis:
• Which components are effective at promoting
learning? What learning principles work well? How
effective are whole curricula?
6. Big Data for education in research
• 7= Trend analysis: What changes over time
and how?
• 8= Adaptation and Personalization: What next
actions can be suggested for the user? How
should the user experience be changed for the
next user? How can the user experience be
altered, most often in real time?
7. Big Data for education in Practice
• Learning analytics leverages student-related data to
build better pedagogies, target at-risk student
populations, and to assess whether programs
designed to improve retention have been effective and
should be sustained — important outcomes for
administrators, policy makers, and legislators.
• Learning analytics envision being able to tailor learning
to students’ personal needs and interests — relying on
data to make carefully calculated adjustments and
suggestions to keep learners motivated as they master
concepts or encounter stumbling blocks.
8. Examples
• 1= One of the earlier applications of learning
analytics by a university was Purdue
University’s Signals project, which was
launched in 2007. Project Signals incorporates
data from student information
systems, course management systems, and
course grade books to generate risk levels so
that at-risk students can be targeted for
outreach.
9. Examples
• 2= Efforts to use student data to personalize
education have been made by Saddleback
Community College in Orange County with their
Service-Oriented Higher Education
Recommendation Personalization Assistant, or
SHERPA, system. This software compiles detailed
profiles of each student, recording information
about work schedules, experiences with
professors, and other personal information,
throughout their time at the university
10. Examples
• 3= At Austin Peay State University in
Tennessee, university advisors use the Degree
Compass, software that employs predictive
analytic techniques, to help students decide
which courses they will need to complete their
degree along with courses in which they are
likely to be successful (go.nmc.org/apsu). With
these insights, advisors and counselors hope
to illuminate a student’s best learning path
11. Examples
• 4= In late 2012, CourseSmart, a digital textbook
provider with five partners in the textbook
publishing industry, announced the launch of its
analytics package, CourseSmart Analytics, which
closely tracks a student’s activity as they interact
with online texts, and interprets that data for
professors, providing them with an engagement
score for a particular text. At this level, professors
can use the results of CourseSmart Analytics to
assess student efforts, as well as their own
decisions in the selection of effective and
engaging texts.
12. Examples
• 5= The Glass Classroomgo.nmc.org/gclass .
Santa Monica College’s Glass Classroom
initiative strives to enhance student and
teacher performance through the collection
and analysis of large amounts of data. Using
real-time feedback, adaptive courseware
adjusts based on an individual’s performance
in the classroom in order to meet educational
objectives.
13. Examples
• 6= Stanford University’s Multimodal Learning
Analytics go.nmc.org/multimo In partnership
with the AT&T Foundation, Lemann
Foundation, and National Science
Foundation, Stanford is exploring new ways to
assess project-based learning activities
through students’ gestures, words, and other
expressions.
14. Applications
• 1= Reading. Kno, an e-textbook
company, launched the “Kno Me” tool, which
provides students with insights into their
study habits and behaviors while using e-
textbooks. Students can also better pace
themselves by looking at data that shows
them how much time has been spent working
through specific texts, and where they are in
relation to their goals: go.nmc.org/kno.
15. Applications
• 3= Writing and Composition. In writing
intensive courses, Mobius Social Learning
Information Platform is used at University of
North Carolina Greensboro to facilitate
anonymous peer-to-peer feedback and
grading. When students submit an essay, it is
automatically distributed to the rest of their
randomly chosen peer group, and an
algorithm turns their feedback into statistics
and performance reports: go.nmc.org/mob.
16. Applications
• jPoll at Griffith University go.nmc.org/jpoll
• jPoll is an enterprise-wide tool developed by
Griffith University in Australia, directed at
capturing, maintaining, and engaging students
in a range of interactive teaching situations.
Originally developed as a replacement for
clicker-type technologies, jPoll is helping
educators identify problem areas for students
via learning analytics.
17. Conclusion
• Will Big Data Transform How We Live, Work,
and Think??
• Read the book:
• Big Data: A Revolution That Will Transform
How We Live, Work, and Think by Kenneth
Cukier and Viktor Mayer-Schonberger
18. References
• Bienkowski, M., Feng, M., & Means, B. (2012). Enhancing Teaching and
Learning Through Educational Data Mining and Learning Analytics: An Issue
Brief. U.S. Department of Education Report (October).
http://www.ed.gov/edblogs/technology/files/2012/03/edm-la-brief.pdf
• Johnson, L., Smith, R., Willis, H., Levine, A., and Haywood, K., (2011). The
2011 Horizon Report. Austin, Texas: The New Media Consortium. Retrieved
from http://www.nmc.org/pdf/2011-Horizon-Report.pdf
• Johnson, L., Adams, S., and Cummins, M. (2012). The NMC Horizon Report:
2012 Higher Education Edition. Austin, Texas: The New Media Consortium.
Retrieved from http://nmc.org/pdf/2012-horizon-report-HE.pdf
• Johnson, L., Adams Becker, S., Cummins, M., Estrada, V., Freeman, A., &
Ludgate, H. (2013). NMC Horizon Report: 2013 Higher Education Edition.
Austin, Texas: The New Media Consortium. pp. 24-27. Retrieved
fromhttp://www.nmc.org/pdf/2013-horizon-report-HE.pdf