Learning Analytics for Adaptive Learning And Standardization

Learning Analytics for Adaptive Learning And Standardization

Research Fellow, KERIS

Yong-Sang CHO, Ph.D

[email protected]

FB: /zzosang Twitter: @zzosang

LASI – Asia 2017August 26, 2017

Table of Contents

• What is an Adaptive Learning

• Reference Model Design for Implementation of Adaptive Learning

• One step further: Exploring Data Flow and Exchange

• Issues and Concern: Privacy and Data Protection

• Topic List: What JTC1/SC36 WG8 is doing now

“Anyone who has ever been in a classroom – where as a student or instructor –knows that not all students procced at the same pace.” <Tyton Partners>

What is an Adaptive Learning?

Adaptive learning is

“dynamically adjust to the level or type of course content based

on an individual’s abilities or skill attainment, in ways that

accelerate a learner’s performance with both automated and

instructor interventions."

<Horizon Report 2017 – HE edition >

<Source: http://http://er.educause.edu/articles/2016/10/adaptive-learning-systems-surviving-the-storm>

“Enabled by machine learning, adaptive learning technologies

can adapt to a student in real time, providing both instructors

and students with actionable data.

The goal is to accurately and logically move students through

a learning path, empowering active learning, targeting at-risk

student populations, and assessing factors affecting

completion and student success. "

<Horizon Report 2017 – HE edition >

<Source: http://http://er.educause.edu/articles/2016/10/adaptive-learning-systems-surviving-the-storm>

Quality

Cost Access

Also adaptive learning may be a key (or hammer?)

to break “Iron Triangle”

Case Study: CogBook

“After using CogBooks for one semester, student success

rates rose from 76% to 94% and the dropout rate reduced

from 15% to 1.5%. "

<Source: https://www.cogbooks.com/2016/02/04/improve-student-success-and-retention-with-adaptive-courseware>

Reference Model Design forImplementation of Adaptive Learning

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 Editionhttp://www.nmc.org/publication/nmc-horizon-report-2015-higher-education-edition/>

Resources

AnalyticsCurricula

Point of

Adaptive Learning

Conceptual relationship among curricula, resources and LA

<Source: Prospects for the application of learning analytics – Use cases and Service Model,Yong-SangCho, Journal of Information and Communication, 2014>

Abstract layer of reference model for LA

Input data items for learning analytics

Data

Collection

Data Processing &

Storing

Visualization Analyzing

Privacy

Policy

• lecture

• material

• learning tool

• quiz/assessment

• discussion forum

• message

• social network

• homework

• prior credit

• achievement

• system log

……

personalization, intervention

and prediction, etc

Outcomes from learning analytics

Data

pro

ce

ss

ing

an

d a

na

lys

is

secured data exchange

Learning & Teaching

Activity

• Reading

• Lectures

• Quiz

• Projects

• Homework

• Media

• Tutoring

• Research

• Assessment

• Collaboration

• Annotation

• Gaming

• Social Messaging

• Scheduling

• Discussion

…… Feedback &

Recommendation

<Source: ISO/IEC TR 20748-1:2016 Learning Analytics Interoperability – Part 1: Reference model>

Analytics Data Store(Micro Data)

Analytics Data Store(Analyzed Data)

Data

Ma

nip

ula

tion

Data Analysis

Analysis

Interface

Analysis

Algorithm

Analysis

Processing

Output

Generation

Statistic Analysis

Topic Analysis

Network Analysis

Pattern Analysis

Dynamic Modeling

Association Analysis

Constant Information(Curricula, Learning

Resources, Preferences)

Data

Con

trol

Dashboard Integration

Content Recommendation

Learning Path Recommendation

(Curriculum Support)Social Analysis

<Source: ISO/IEC TR 20748-1:2016 Learning Analytics Interoperability – Part 1: Reference model>

Zoom-in diagram for data analysis

One step further:Exploring Data Flow and Exchange

- Get the data! -

xAPI

Transcript/learning datacan be delivered to LMSs, LRSs or reporting tools

Experience data

LMS: Learning Management SystemLRS: Learning Record Store

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

Case Study: Video Lecture Capture and OpenLRS

<University of Michigan at LAIS- Asia 2016>

<source: http://www.lasi-

asia.org:8080/wp/?page_id=660>

Case Study: xAPI and Caliper utility for single LRS

<UC Berkeley at LAIS- Asia 2016>



What will be happen?

“ISO/IEC TS 20748-3 Learning Analytics Interoperability

- Part 3: Guideline for data interoperability” will be come !!!

Issues and Concern:Privacy and Data Protection

Unlawful

Learning Analytics?

«learning analytics will be unlawful and the sch

ool

owner will not be able to maintain the most vita

l

data protection principle: the data principal (the

student) will not have control of and a say

concerning the use of his or her own informatio

n»

Lawfulness, Purpose limitation,

Data minimisation, Consent, etc.



<Tore Hoel at LAIS- Asia 2016 >

What is the Law?




The LACE DELICAT

E

Checklist

to implement

trusted

Learning

Analytics




What will be happen?

“ISO/IEC TS 20748-4 Learning Analytics Interoperability

- Part 4: Privacy and data protection policies ” will be come !!!

Topic List :What JTC1 SC36/WG8 is doing now

(2017 Melbourne) Resolution 3: Reaffirm of study group's topics for learning

analytics interoperability and encourage participation to NBLOs

SC36/WG8 reaffirms the study group's topics for learning analytics interoperability:

• Systems governance for learning analytics (assigned in June 2015)

• Data framework for learning analytics interoperability (assigned in June 2015)

• Principles of data design for learning analytics (assigned in November 2015)

• Privacy and data protection (assigned in April 2016)

• Learning analytics model or profile (assigned in June 2016)

• Ethics guideline for learning analytics providers and systems (assigned in

November 2016)

• Intelligence methods for learning analytics using machine learning technologies

(assigned in November 2016)

• Multi-Modal Learning Analytics (assigned in August 2017)

Note: SC36/WG8 informs for study group leaders, Yong-Sang Cho (leader), Tore

Hoel, Yasuhisa Tamura, Jaeho Lee and Jerry Leeson.

Thank You !!!

Korea Education & Research Information Service

Yong-Sang CHO, Ph.D

[email protected]

FB: /zzosang Twitter: @zzosang

Learning Analytics for Adaptive Learning And Standardization

Education

Transcript of Learning Analytics for Adaptive Learning And Standardization