1. Big Data in Education
Mart Laanpere, Ph.D.
Senior researcher
Centre for Educational Technology, Tallinn University
2. Disruptive change in education
• Disruptive innovation (Christensen): creates a new market and
value network and eventually disrupts an existing market and value
network, displacing established market leading firms, products, and
alliances
• Models of disruptive change:
• Napster, iTunes and Spotify disrupting the music industry
• Uber disrupting the taxi business
• Predicting disruptive change in education:
• De-schooling society (Ivan Illich, Seymour Papert)
• Steve Jobs: iPads will change schools
• The promise of MOOCs
• Big Data?
5. Two change processes in education
• Datafication: transformation of different aspects of education (such
as test scores, school inspection reports, or clickstream data from an
online course) into digital data
• Digitization: transition of diverse educational practices into software
code, it is most obvious in the ways that aspects of teaching and
learning are digitized as e-learning software products (Learning
Management Systems, student information systems, e-assessment
tools, interactive learning resources, educational games,
recommender systems etc)
Williamson, 2017
6. What comes to your mind when you think of
Big Data in education?
• Go to Menti.com and enter the code 13 53 04
• Enter three keywords that you associate with Big Data in education
7. Big Data in Education
• What?
• Why?
• How?
• Where?
• Who?
8. Who: two communities
• International Educational Data Mining Society (EDM)
• First event: EDM workshop in 2005
• First conference: EDM2008
• Publishing JEDM since 2009
• http://educationaldatamining.org
• Society for Learning Analytics Research (SOLAR)
• First conference: LAK2011
• Journal of Learning Analytics (founded 2012)
• http://solaresearch.org
9. Hot, interdisciplinary field in RDI
• HackingEDU: 100 000 USD prize for disruptors (Uber for education)
• Education policy and governance
• Commercial interests in the educational technology market
• Philanthropic and charitable goals around supporting alternative
pedagogic approaches
• Emerging forms of scientific expertise such as that of psychology,
biology and neuroscience
• Practical knowledge of innovative practitioners in education
10. A vision of Data-Driven Education
• Personalization: Educators dynamically adjust instruction to accommodate
students’ individual strengths and weaknesses rather than continue to utilize a
mass production-style approach.
• Evidence-Based Learning: Teachers and administrators make decisions about how
to operate classrooms and schools informed by a wealth of data about individual
and aggregate student needs, from both their own students as well as those in
comparable schools across the nation ... rather than by intuition, tradition, and
bias.
• School Efficiency: Educators and administrators use rich insight from data to
explore the relationships between student achievement, teacher performance,
and administrative decisions to more effectively allocate resources.
• Continuous Innovation: Researchers, educators, parents, policymakers, tech
developers, and others can build valuable and widely available new education
products and services to uncover new insights, make more informed decisions,
and continuously improve the education system.
US Center for Data Innovation, 2016
11. Threats of relying on Big Data in education
• Privacy (GDPR)
• Validity: picture is based on only one, narrow facet
• Cultural/linguistic issues
• Learners are programmed by machine
• Simplified computable models, biased towards average
• Reducing the role of teacher
• Any other concerns?
14. Examples of our Big Data/ Learning Analytics
projects in Tallinn University
15. Configurations of digital textbook 2.0
Planetary system
model
Linux
model
Lego
model
Stabile
core
Dynamic
core
No core at all
16. e-Schoolbag: the heart of Educational Cloud
Publisher e-Exam system
EIS
Koolielu.ee
OER repository
Startups
Collection of DLR
e-Schoolbag
eKool (online
Gradebook service)
Learning
analytics
LePlanner
(learning
scenarios)
18. DigiÕppeVaramu: Open Educational Resources
• Estonian Ministry of Education and Research procured a set of web-
based Open Educational Resources that cover the whole curriculum of
Grades 10 - 12
• From June 2017 til August 2018: 80+ expert teachers hired,
10 000 learning objects created, currently piloted in 20+ schools
• Each Learning Object creates a stream of xAPI data that is recorded in
Learning Record Store
• In the future: Single Sing-On allows aggregation of events for one
learner in various digital platforms (anonymisation, masking needed)
• Multimodal learning analytics: online + offline data
https://vara.e-koolikott.ee
19. Innovative pedagogical scenarios
• Mainstream practices within 2nd generation e-learning
systems (LMS) follow the conservative pedagogy:
presentation-practice-test
• Innovative pedagogical scenarios from LEARNMIX project
(learners and teachers as co-authors of “e-textbooks”):
• Flipped classroom
• Project-based learning
• Problem-based learning
• Inquiry-based learning
• Game-based learning
Http://learnmix.tlu.ee
23. Digital
Mirror
Self-assessment:
• By the principal
• By digi-team
• By peer team
Data-driven
decision-making:
• Benchmarking
• Strategic goals
• Action plan
• School-owners’
digital strategy
An online tool for self-assessment
of school’s digital maturity,
Creating digital strategy
24. Samsung Digi Pass: Open Badges for digital
skills profile for disadvantaged youth
• Collect - stuff, tools, memories, friends
• Make sense - annotate, systematize
• Share – know what and how and with whom
• Create – digital production, social skills
• Collaborate – teamwork, social skills
• Show yourself – digital identity, portfolio, pitching
• Be safe, be nice – licenses, privacy, health, ethics
• Fix it - problem solving, troubleshooting
• Improve it – innovation, entrepreneurial mindset
25. SHEILA: Learning Analytics policies in HE
http://sheilaproject.eu
interviews
e interviews, 21 out of 51 institutions were already implementing centrally-supported learning
s, 9 of which had reached institution-wide level, 7 partial-level (including pilot projects), and 5
loration and cleaning stage. Meanwhile, 18 institutions were in preparation to roll out
ning analytics projects, and 12 did not have any concrete plans for an institutional learning
yet.
uestion in the survey revealed that 15 institutions had implemented learning analytics, of which
ll implementation and 13 were in small scale testing phases. Sixteen institutions were in
earning analytics projects, and 15 were interested but had no concrete plans yet.
N O P L A N S
I N P R E P A R A T I O N
I M P L E M E N T E D 9 7 5
12
18
The adoption of learning analytics (interviews)
Institution-wide Partial/ Pilots Data exploration/cleaning
IMP LE ME NTE D 2 13
The adoption of learning analytics (survey)
Institution-wide Small scale
The results show that topics about “privacy and transparency” are considered as both the most impor
easiest to address, whereas “research and data analysis” is comparatively less important than other th
“objectives of learning analytics” is less easy to address than other themes. The overall scores of the im
ranking are higher than the overall scores of the ease-ranking.
4. Survey and interviews
At the time of the interviews, 21 out of 51 institutions were already implementing centrally-supported
analytics projects, 9 of which had reached institution-wide level, 7 partial-level (including pilot project
were at data exploration and cleaning stage. Meanwhile, 18 institutions were in preparation to roll ou
Motivators:
• To improve student learning performance (16%)
• To improve student satisfaction (13%)
• To improve teaching excellence (13%)
• To improve student retention (11%)
• To explore what learning analytics can do for our institution/ staff/ students (10%)