Updates from Apereo Learning Analytics Initiative (Apereo LAI)

Updates From Apereo Learning Analytics Initiative (LAI)OPEN APEREO 2015

Josh BaronASSISTANT VICE PRESIDENT

INFORMATION TECHNOLOGY FOR DIGITAL EDUCATION

MARIST COLLEGE

Gary GilbertTECHNOLOGY LEAD FOR INTEGRATION & ANALYTICS

UNICON & APEREO LAI

Sandeep JayaprakashLEARNING ANALYTICS SPECIALIST, MARIST COLLEGE

ANALYTICS LIAISON , APEREO LAI

SOME BRIEF HISTORICAL CONTEXT…

Open Academic Analytics Initiative(OAAI)

Open Academic Analytics Initiative(OAAI)

EDUCAUSE Next Generation Learning Challenges (NGLC)

Funded by Bill and Melinda Gates Foundations

$250,000 over a 15 month period

Goal: Leverage Big Data concepts to create an open-source academic early alert system and research “scaling factors”

OAAI Early Alert System Overview

JAYAPRAKASH, S. M., MOODY, E. W., LAURÍA, E.

J., REGAN, J. R., & BARON, J. D. (2014).

EARLY ALERT OF ACADEMICALLY AT-RISK STUDENTS:

AN OPEN SOURCE ANALYTICS INITIATIVE

. JOURNAL OF LEARNING ANALYTICS, 1(1), 6-47.

More Research Findings…

UPDATES FROM 2014-15

Apereo Learning Analytics Initiative (LAI)

Apereo Learning Analytics Initiative (LAI)

Goal: Operationalize outcomes from Learning Analytics research as means to develop, maintain and sustain modular components that integrate to support an open platform for Learning Analytics

Current Proof-of-Concept Projects◦ Marist College – Learning Analytics Processor (LAP)◦ Unicon – OpenLRS (Learning Record Store) and Student Success Plan (SSP)◦ University of Amsterdam – Larrisa (open-source Learning Record Store)◦ Uniformed Services University – OpenDashboard

Join the mailing list: [email protected](subscribe by sending a message to [email protected])Wiki Page: https://confluence.sakaiproject.org/x/rIB_BQGitHub: https://github.com/Apereo-Learning-Analytics-Initiative

Modular Components of an Open Learning Analytics

Platform

Collection – Standards-based data capture from any potential source using Experience API and/or IMS Caliper/Senor API

Storage – Single repository for all learning-related data using Learning Record Store (LRS) standard.

Analysis – Flexible Learning Analytics Processor (LAP) that can handle data mining, data processing (ETL), predictive model scoring and reporting.

Communication – Dashboard technology for displaying LAP output.

Action – LAP output can be fed into other systems to trigger alerts, etc.

Library of Open Models

OpenDashboard

OpenLRS & Larrisa

Learning Analytics Processor

(LAP)

Student Success

Plan

Apereo LAI Updates Collaborated with the Society for Learning Analytics Research (SoLAR) on 2015 Learning Analytics and Knowledge (LAK) Conference

◦ Introduced new “practitioner” track which was combined with research presentations◦ Organized first annual two-day Open Learning Analytics Hackathon◦ Larger scale activities planned for LAK16 at University of Edinburgh (lak16.solaresearch.org)

Several open learning analytics projects are or have just entered incubation◦ Learning Analytics Processor (LAP), OpenLRS and OpenDashboard◦ Student Success Plan (SSP) already graduated from incubation

Jisc will deploy several Apereo LAI components as part of national UK Learning Analytics service◦ Marist College, Unicon and other partners will be supporting Jisc work◦ Initial offerings to being in September 2015◦ More details and regular updates at: http://analytics.jiscinvolve.org/wp/

Open Learning Analytics Platform Progress

Collection – Any xAPI (and soon IMS Caliper) compliant learning system

Storage – OpenLRS & Larissa

Analysis – Learning Analytics Processor

Communication – Open Dashboard

Action – Student Success Plan

OpenLRS

Learning Analytics Processor

Student Success Plan

Learning Systems

OpenDashboard

xAPI / Caliper

LTI

API

API

API

Learning Record Store & Data Collection• OpenLRS is a secure, standards-based, standalone Learning Record Store built

to fill the need for a high i/o storage mechanism for an Open Learning Analytics Environment

• Supports xAPI• Support for IMS Caliper in development

• Technical Stack○ Java / Spring-Boot○ Pluggable Data stores (redis, elasticsearch, mongodb)

Learning Analytics Processor

● A framework for the execution of learning analytics models

● Web application○ Java / Spring○ MySQL / H2

● Predictive Model Mark-up Language (PMML)

● Pentaho Kettle – Data Integration & ETL

● Pentaho WEKA – Data Mining & Predictive Modelling

Learning Analytics Processor

Sakai Admin tool

activities.csv

grades.csv

Learning Analytics Processor (LAP)Student ID, Course ID,

Risk Rating

Demographics from SIS

Go!

grabs files

1

2

3 OAAI XML

Kettle pipeline applies model

4 outputs results

. .

.

.

------------------ EXTRACT -------- TRANSFORM ------- LOAD ---------

RESTful API

Student Success Plan

• Case Management Software• Academic Advising Tools (MAP)• Early Alert / Faculty Access (EAL)• Student Interface (Tasks, MAP, Self

Help)• Student Information System (SIS)

Integration• Reporting Tools / Data Collection

Open Dashboard

• Web application that provides a framework for displaying analytics visualizations and data views called “cards”.

• Cards represent a single discrete visualization or data view but share an API and data model

• LTI compliant• Card library for Learning Analytics

Processing logic

Controllers

Rest API

Data Access

Pure JS Model

Pure JS API

Angular Modules

CardsServices

Framework

LAK15 Hackathon - Open Dashboards

Early Alert Insights ChartCourse Engagement Pathways – Resource & Content Access

Roadmap• Begin to incorporate components of the Hadoop ecosystem

• IMS Caliper

• LTI 2

• Visualization library

Demo

Engaging with the Community

Insights about Learning Analytics

It is not just about infrastructure.

APEREO LAI is also a

safe communal space to build up experience and insights and requirements.

Engaging with Apereo Learning Analytics Initiative (LAI)

We believe in Do-ocracy. If you see an opportunity or area of enrichment then you should take leadership and the community will support you.

Examples Alan - community officer, organizes hackathons & workshops Sandeep - warding incubation process, analytics Patrick - communications officer, student requirements Kate - marketing/communications, Evangelist Josh - many roles (not even going to start) Gary - builds the living daylights out of LAI. Sanity check, etc.

LAK15 LAK16HackathonsInfrastructure WalkthroughsOLA European SummitEthics and privacy workshopsScalable Student Retention SystemsOpen Dashboards

Apereo LAIAmsterdam, Paris, Utrecht, Milton Keynes, Poughkeepsie, Baltimore etc.

Engaging with Apereo Learning Analytics Initiative (LAI) Where to start? LEVEL 1 NINJA (in no particular order):

• Review the LAI homepage https://confluence.Sakaiproject.Org/display/LAI/learning+analytics+initiative

• Read the notes from the regular meetings Join the mailing list: [email protected]

(subscribe by sending a message to [email protected])

• Join the LAI calls (every other Wednesday 11:00 AM EST) : https://confluence.Sakaiproject.Org/display/LAI/community+hangouts

• Review github: https://github.Com/apereo-learning-analytics-initiative

• Take on a role on a subject you care about

Engaging with Apereo Learning Analytics Initiative (LAI) Where to start? LEVEL 2 NINJA (in no particular order):

• Buy the team a beer• Host a hackathon or workshop• Share Learning Analytics requirements at your institution• Pilot Open Learning Analytics components• Consider co-developing and enriching Apereo LAI components• Act as a communication channel between organizations

o SURF, JISC , Apereo, SoLAR, LACE etc.

Unicon, UvA, Marist, Hull, Oxford, USUHS, <<your name here>>

Looking to discuss more?

2015-16 LEARNING ANALYTICS INITIATIVE (LAI) PLANNING DISCUSSION

9:45AM TO 10:30AM, WEDNESDAY 3RD JUNE, MARYLAND D

2015-16 LEARNING ANALYTICS INITIATIVE (LAI) SHOWCASE CORNER

5:30 PM TO 7:00 PM, MONDAY 1ST JUNE, MARYLAND FOYER

Join the mailing [email protected]

(subscribe by sending a message to [email protected])