Data and Interoperability

Overview

Learning analytics is fundamentally about data, so it is vital that data can be moved between systems as easily as possible. In this work package we are surveying specifications relevant to learning analytics to identify gaps and priorities for further work. We are also working with interested parties in the standards community to support and initiate projects on learning analytics.

We have published a number of studies (see list of Learning Analytics Reviews) and some substantial deliverables (see publications under D7.x in the LACE Deliverable Overview page)

This work is being led by Dai Griffits at University of Bolton, UK,  and Tore Hoel at Høgskolen i Oslo og Akershus, Norway.

Recent Posts

The Dutch xAPI Specification for Learning Analytics (DSLA)

Have you ever wanted to store the data collected from any learning environment in a standardised way but did not know how? Look no further, you are in the right place now! After working with xAPI for several years, we have compiled a registry of xAPI specifications for learning activities...Read More »


More Interviews in our video library

LACE organised in collaboration with University of Amsterdam the 1st Institutional Readiness Day for Learning Analytics in Amsterdam to explore the advantages and challenges to implement learning analytics in Higher Education.

After a very successful Open Learning Analytics Summit in Amsterdam in 2014, we were this year focusing on institutional readiness for...Read More »


New Flyer for 2016

As LACE is entering the last year of its funded period, we therefore developed an updated flyer with a nice overview of all tangible outcomes and potential collaboration possibilities. The Flyer was first distributed at the annual LACE event at BETT 2016. Here the digitale version for all those...Read More »


LACE Workshop at Open University of Catalonia

LACE has been invited to discuss ‘data interoperability‘ and ‘learning analytics supported instructional design methods‘ at the University of Catalonia (Universitat Oberta de Catalunya) at an Open Conference with various workshops.

With all the fog around questions like ‘What is the right Learning Analytics Infrastructure?’ and  ‘Do we collect the data in...Read More »


Learning Analytics : promesses et réalités

LACE has been invited to contribute to the French Conference on the State-Of-The-Art of Learning Analytics and actions points for a national research agenda for Learning Analytics. The conference has been held in Paris at the French Ministry of Education (07.12.2015).

Picture by: https://twitter.com/tkoscielniak

Over 60 people...Read More »


Institutional readiness for learning analytics - a lot of piloting and consultations remains before we are ready

Institutional readiness for learning analytics. Is sounds like a dream. And it is a dream.  , it was the title for a conference LACE project organised in collaboration with University of Amsterdam middle of December. Through exploring  a number of pilots organised at UvA, a detour...Read More »


IMS Caliper published – we now have a clearer picture how activity streams should be described

IMS Caliper, claimed to be “the world’s first interoperability standard for educational click stream data”, is now publicly available after a long period of testing among the consortium members. A Best Practice Guide, an Implementation Guide, and a Conformance and Certification Guide have been published together with a number of...Read More »


Don’t worry…be XAPI !

devlearn

Your LACE reporter Fabrizio Cardinali, CEO Skillaware, live from DevLearn 2015, MGM Grand Las Vegas

The “innovation in the making” motto displayed all across  this year’s DevLearn conference and exhibit spaces at MGM Grand Las Vegas, September 30 to October 2

Don’t worry…be XAPI !

That...Read More »


Call for Datasets

At the recent LAK15 conference, the high demand to have an overview of available datasets for Learning Analytics research has become evident. Based on the discussions at LAk15, we created a Call for Dataset descriptions together with the Journal for Learning Analytics (JLA), which will be published in a Special Issue.

We...Read More »


About Today's Ethics and Privacy in Learning Analytics (#EP4LA) Workshop

Later today members of the LACE project team are facilitating a half-day workshop session at the LAK15 Conference on Ethics and Privacy in Learning Analytics (#EP4LA).

As described in a blog post published recently on the LACE web site:

This interactive workshop aims to raise awareness of major ethics and...Read More »


Barriers and Enablers for Data Sharing - a Survey

Without data, no learning analytics. Data sharing is a precondition for even thinking about the benefits of personalised learning, improved retention, better learning design, and all the other promises of learning analytics. To make data sharing happen, we need to understand the barriers and enablers. This is the aim of...Read More »


Korean perspective on Learning Analytics: Development through a test bed based on Open Source

This guest blog post is the second in our new series of country reports from scholars renowned for their contribution to national and international learning analytics research. Yong-Sang Cho is leading the learning technology standards development in South Korea and is now pioneering learning analytics systems development in this country.

Read More »

LACE initiative resulted in new Asian SIG on learning analytics

Some of the participants at the first workshop on learning analytics at the ICCE 2014 conference in Japan

A successful workshop and establishment of a new special interest group on learning analytics under the auspices of Asian-Pacific Society of Computers in Education (APSCE), this was the outcome of a LACE project initiative of last year. Till now the focus on learning analytics in the region has been relatively...Read More »


Standards and Learning Analytics – current activities 2014

The development of IT standards and other kinds of technical specifications to support interoperability in educational technology has been underway for more than 15 years, but the focus of attention has usually been on system integration or portability of educational content. The growth of interest in learning analytics has led...Read More »


Examining open learning analytics – report from the Lace Project meeting in Amsterdam

In this guest post Niall Sclater, a consultant at Sclater Digital and currently doing research on Learning Analytics for Jisc, reports on the Open Learning Analytics European Summit on December 1st, 2014, in Amsterdam. The post first appeared in Apereo Learning Analytics Initiative – the Apereo Foundation is a membership organisation acting as a home for several Open Source Software development projects and incubators  – have just announced a webinar, being delivered by four of its...Read More »


How to give students control of their data

Everybody’s talking about Big Data and Learning Analytics, but if you don’t solve privacy first it is going to be killed before it has really started.” These are the words of Larry Johnson, CEO of the New Media Consortium (NMC), known for...Read More »


De-identified LA data is a dream - is solutions built on trust the way out?

When 87 percent of the U.S. population can be uniquely identified with a reasonable degree of certainty by a combination of ZIP code, date of birth, and gender you may realise that it may be pretty hard to de-identify the data exhaust of modern education. Anonymising the data does...Read More »


xAPI starts Community of Practice and Profiles Group

The xAPI specification has foreseen that, at some point in time, Communities of practice will “need to establish and define new Verbs and Activities to meet the need of their constituency”. Now the time has come for defining such a community. This August the first...Read More »


LA on the agenda for international standardisation

The Open Forum Conference session organised by LACE in Oslo in June hit a nerve with the community of standardisation experts attending the conference prior to their full week meeting in Oslo. In the meeting of the ISO committee working on standards for Learning, Education and Training, ISO/IEC JTC 1/SC36,...Read More »


Reflections on the First LACE Project Webinar: Big Picture of Learning Analytics Interoperability

The First LACE Project Webinar

The first LACE project webinar took place yesterday. This title of the launch online event was the “Big Picture of Learning Analytics Interoperability“. The event aimed at raising a number of key questions for those with interests in learning analytics and their interoperability such as “What are...Read More »


Open Learning Analytics - progress towards the dream

In 2011, a number of prominent figures in learning analytics and educational data mining published a concept paper on the subject of Open Learning Analytics (PDF), which they described as a  “proposal to design, implement and evaluate an open platform to integrate heterogeneous learning analytics techniques.” This...Read More »


Learning Analytics and Interoperability - The Big Picture in Brief

Learning Analytics is now moving from being a research interest to a wider community who seek to apply it in practice. As this happens, the challenge of efficiently and reliably moving data between systems becomes of vital practical importance. System interoperability can reduce this challenge in principle, but deciding where...Read More »


Background

The ability to move data around between systems with the minimum amount of effort and loss of information is important for the development for learning analytics and EDM. While there will always be a need to adopt ad hoc approaches both in research and practice, there are currently several situations in which effort has to be expended when it could be avoided. This limits the progress of research and adoption.

We have identified four problems that we seek to reduce:

  1. Learning analytics and EDM research could make more progress in developing and testing algorithms and models if datasets could be more easily merged (both increased in scale and diversity of data).
  2. At present, analysts have to independently map between different data models. It would be more efficient for them if this work was done once and used many times.
  3. The absence of (data) interoperability means that there is wasted time and money spent to create and maintain computer code for multiple data exchanges. This makes it hard for suppliers to service localised or niche markets and hard for innovative products to become established. Few, if any, analytics-based applications will be viable – commercial or Open Source – except those provided by already-dominant suppliers of learning platform software.
  4. Existing specifications and standards have been neither motivated by, or designed for, learning analytics.

Our response is to better define the current state of LA & EDM interoperability and to clearly identify gaps. This will include the feasibility of increased data sharing for operational and research purposes in addition to the information models necessary to make use of exchanged data.

This work is led by University of Bolton/Cetis in close cooperation with Høgskolen i Oslo og Akershus and support from Open Universiteit Nederlend and Infinity Technology Solutions.

How We Work

Our objectives are to:

  • Work with interested parties in the standards community to support and initiate projects on learning analytics
  • Analyse and describe the current state of learning analytics interoperability.
  • Build and capture consensus on shared/mappable concepts.
  • Identify and characterise gaps and suggest priorities for interoperability development work.
  • Determine feasibility, options and roadmap for a data sharing.