1. The document discusses the prospects for using learning analytics to achieve adaptive learning models. It describes adaptive learning and different levels of adaptive technologies, including platforms that react to individual user data and those that leverage aggregated data across users.
2. It outlines the pathway to achieving adaptive learning analytics, including using LMS analytics dashboards, predictive analytics, and adaptive learning analytics. Case studies and examples of existing applications are provided.
3. A proof of concept reference model for learning analytics is proposed, including a basic analytics process and an advanced process using predictive and adaptive algorithms. Linked open data for connecting curriculum standards and digital resources is also discussed.
1. Prospect for learning analytics to achieve
adaptive learning model
Yong-Sang CHO, Ph.D
Principal researcher, KERIS
2015-10-16, Seoul, Korea
2. Table of Contents
• What is an adaptive learning
• Pathway to reach adaptive learning analytics
• Case study for exploring data flow and exchange
• Proof of concept: reference model for learning analytics
• Linked data for curriculum standards
• Future works by 2016
4. Adaptive learning is a
“sophisticated, data-driven, and in some cases, nonlinear
approach to instruction and remediation, adjusting to a learner's
interactions and demonstrated performance level, and
subsequently anticipating what types of content and resources
learners need at a specific point in time to make progress."
<Bill and Melinda Gates Foundation>
Source: http://educationgrowthadvisors.com/gatesfoundation
5.
6. Two levels to adaptive learning technologies:
• the first platform reacts to individual user data and adapts
instructional material accordingly,
• while the second leverages aggregated data across a large
sample of users for insights into the design and adaptation
of curricula.
Source: Horizon Report 2015 – Higher Education Edition
http://www.nmc.org/publication/nmc-horizon-report-2015-higher-education-edition/
10. * LMS/VLE Analytics Dashboard
ü Concept: Until recently, data logs were not in a format that non-technical users could
interpret, but these are now rendered via a range of graphs, tables and other visualizations,
and custom reports designed for consumption by learners, educators, administrators and
data analysts
Learners may get basic analytics such as how they are doing relative to the cohort average
(e.g. test Learning Analytics scores, forum contributions, webinar participation)
ü Examples: LMS/VLE vendors provide examples and webinars about their analytics dashboards,
and the enterprise analytics/BI vendors are contextualizing their products to the
education market.
Arizona State University reports that it is seeing returns on its investment in
academic and learning analytics, including a “Student 360” program that integrates
all that the institution knows about a student.
Example of Learning Analytics
<Source: Learning Analytics, UNESCO IITE (2012)>
11. * Predictive Analytics
ü Concept: One of the more advanced uses of analytics that generates huge interest is the possibility
that from the pattern of learners’ static data (e.g. demographics; past attainment) and
dynamic data (e.g. pattern of online logins; quantity of discussion posts) one can classify
the trajectory that they are on (e.g. “at risk”; “high achiever”; “social learner”), and hence
make more timely interventions (e.g. offer extra social and academic support; present
more challenging tasks).
Currently, one of the most reliable predictors of final exam results is still exam
performance at the start of studies.
ü Examples: Work at Purdue University on the Course Signals software is well known. Signals provides
a red/amber/green light to students on their progress.
Their most recent evaluation reports: “Results thus far show that students who have
engaged with Course Signals have higher average grades and seek out help resources at a
higher rate than other students.”
Example of Learning Analytics
<Source: Learning Analytics, UNESCO IITE (2012)>
12. * Adaptive Learning Analytics
ü Concept : Adaptive learning platforms build a model of a learner’s understanding of a specific topic
(e.g. algebra; photosynthesis; dental surgical procedures), sometimes in the context of
standardized tests which dictate the curriculum and modes of testing.
Naturally, dynamic modeling of learner cognition, and preparation of material for
adaptive content engines, are far more resource intensive to design and build than
conventional ‘dumb’ learning platforms.
ü Examples: Significant research and investment in intelligent tutoring systems and adaptive
hypermedia are bringing web platforms to market with a high quality user experience,
and this is likely to continue to be a growth area.
Example of Learning Analytics
<Source: Learning Analytics, UNESCO IITE (2012)>
14. xAPI
Transcript/learning data
can be delivered to LMSs, LRSs
or reporting tools
Experience data
LMS: Learning Management System
LRS: Learning Record Store
15. IMS
Caliper
Source: New Architect for Learning (Rob Abel, 2014)
http://www.slideshare.net/JEPAslide/day3-edupub-tokyoims?qid=76ce5d4a-1ccf-468f-a428-c652584c395a&v=default&b=&from_search=4
18. We want to see iceberg below to understand
what we didn’t know before!!!
• What is a general process for analytics?
• Do we define workflows beyond xAPI or IMS
Caliper?
• How do we prove the concept?
For exploring
19. Data
Collection
Data Storing
& Processing
Analyzing
Visualization
Privacy Policy
Secure Data Exchange
Input Data Items for Learning Analytics
Outcome from Learning Analytics
DataProcessingandAnalytics
Learning Activity
- Reading
- Lectures
- Quiz
- Projects
- Homework
- Media
- Tutoring
- Research
- Assessment
- Collaboration
- Annotation
- Gaming
- Social
- Messaging
- Scheduling
- Discussions
- Lecture (MOOCs, OER)
- Material (reading, etc)
- Learning tool
- Quiz/Assessment Item
- Discussion forum
- Message
- Social Network
- Prior Credit
- Achievement
- System Log
- ……
Learning & Teaching
Activity
Personalization,
Intervention and
Prediction, etc
First layer of reference model for LA
20. (Basic analytics process: dashboard analytics)
1. Student open digital textbook on Readium-JS viewer
2. Data is generated through reading activities by student
3. Data capture API crawl the data and send to event store
4. On the analytics platform check collected data
5. See simple dashboard from collected data (without analysis algorithm)
(Advanced analytics process: predictive and adpative analytics)
6. Design analysis algorithm with data filtering from collected data
7. See advanced dashboard pertaining to customized analysis
8. Calculate personal learning path connected to LOD for curriculum standard
Demo scenario for LA
23. Goal of achievement
School level
Second criteria of science subject (second level)
Curriculum standard per school grade
Achievement statement (third level)
First criteria of science subject (top level)
Curriculum standards – US case
24. Area of content
Grade group
Primary school 3-4 grade group
Primary school 5-6 grade group
Middle school 1-3 grade group
Section
Curriculum standards – Korean case
25. Achievement statement – Korean case
Section of science subject (middle school)
Content of
curriculum
Criteria of achievement
Core achievement criteria
Reason and explanation
for core achievement
30. • Complete development for data capture API (beta version)
- collaborate with IMS Global & ISO/IEC JTC1 SC36
* to improve efficiency of data sharing format
• Complete design and development for test-bed of reference model
- complete test for open source SWs to organize optimized composition
- design interface for analysis algorithm based on R
• Complete design for LOD of achievement standards
- to connect digital resources with specific topics of curriculum standards
* connected digital resources will be used ISO/IEC 19788 MLR
By February 2017
31.
32. Thank You !!!
Korea Education & Research Information Service
Yong-Sang CHO, Ph.D
zzosang@keris.or.kr
FB: /zzosang Twitter: @zzosang