Open Web Data for Education - Linked Data technologies for connecting open educational data

Open Web Data for Education

Linked Data technologies for connecting

open educational data

Mathieu d’Aquin, Philippe Cudre- Mauroux, Besnik Fetahu, Marieke Guy The Open University, University of Fribourg, L3S Hanover, Open Knowledge Foundation

@mdaquin @FetahuBesnik @mariekeguy

Slides at: http://slideshare.net/mdaquin

Primary School

Secondary School

Higher Education

The way it used to be… (Excessively simplifying)

Primary School

Secondary School

Higher Education

Now… (Still simplifying, I guess)

Other institutions through online courses

Open Universities

coursera

e d X

UDACITY

MIT

OCW

OpenLearn

MOOCs

and OER

Siri, I want to become a

professional photographer.

What should I do?

“I want to be a photographer,

what should I do?”

I found this Open University

course (T189), that you can

enrolled to in the regional centre

2 miles from here (cost £427).

“OK, anything free I can try

first?”

There is an Introduction to

Photography course on MIT

OCW, and a Computational

Photography course on coursera

starting soon.

Needs data from everybody, contributed to one

common data space (… linked data maybe?)

coursera

e d X

UDACITY

MIT

OCW

OpenLearn

courses

courses

courses

requirements requirements

topics

topics

topics

topics

learning

outcomes learning

outcomes

learning

outcomes locations

locations

results results

results

assessment

Outline of the talk(s)/tutorial

1- The state of open/linked data in education

II- How to contribute to open/linked data in education

III- Case study - The Bowlogna Ontology

IV- Making things with open/linked data in education

V- Open Education – more than just open data

State of open data in education

Universities Repositories

Publishers Thesaurus, vocabularies, etc.

Government bodies

Historically, mostly open educational

resources, i.e., these guys

But more and

more of them

and them now!

And hopefully, very soon, them?

Loosely based on http://data.linkededucation.org/linkedup/catalog/

LinkedUp Catalogue of Web Data for Education

http://data.linkededucation.org/linkedup/catalog/

Pause

What are we missing?

How to contribute

In other words:

How to represent

data in education for

sharing

Examples of sharing

linked open data in

education

Bias: We like Open and Linked Data

Open University

Website

Open University

VLE

KMi Website

Mathieu’s

Homepage

Mathieu’s

List of

Publications

Mathieu’s

Twitter

The Web

M366 Course

page

Person: Mathieu

Publication: Pub1

Organisation:

The Open University

Course: M366

Country: Belgium

Book: Mechatronics

author

workFor

availableIn

offers

setBook

The Web of Linked Data

Need for common vocabularies

VIVO

LRMI

DataCube TEACH

Geo

Ontology

Dublin

Core FOAF

DOAP

SIOC

BIBO

Media

Ontology

AIISO

SKOS

17/11/13 LinkedUp – Author Name 15

From LinkedUp data catalogue

Example: AIISO

foaf:Organization

aiiso:School

rdfs:subClassOf

aiiso:College

aiiso:Course

aiiso:Department

rdfs:subClassOf

rdfs:subClassOf

aiiso:Institution

rdfs:subClassOf

aiiso:Faculty

rdfs:subClassOf

aiiso:KnowledgeGroupin

g

rdfs:subClassOf

aiiso:Module

rdfs:subClassOf

aiiso:Programme

rdfs:subClassOf

aiiso:part_of

foaf:Agent

aiiso:responsibleFor

aiiso:responsibleFor

aiiso:teaches

Example: BIBO

bibo:Article

bibo:AcademicArticle

bibo:Document

bibo:Book

bibo:AudioVisualDocument

bibo:DocumentPar

t

bibo:BookSection

bibo:Chapter

bibo:EditedBook

bibo:Issue

bibo:Journal

rdfs:subClassOf

rdfs:subClassOf rdfs:subClassOf

rdfs:subClassOf

rdfs:subClassOf

rdfs:subClassOf rdfs:subClassOf

bibo:partOf

All bibo:partOf

<=1 bibo:partOf

<=1 bibo:partOf

Example: LRMI

A common framework common metadata framework for describing or “tagging” learning resources on the web, with Schema.org

http://www.lrmi.net/the-specification

Schema.org/CreativeWork “e.g. assignment” educationalUse

timeRequired

Schema.org/Duration learningResourceType

“e.g. presentation”

Schema.org/URL useRightsUrl

Schema.org/Audience

LRMI/EducationalAudience

subClass

audience

educationalRole “e.g. HE student”

Case-Study: Bowlogna Ontology

Fostering Open Curricula and Agile Knowledge Bases for Europe’s Higher Education Landscape

• The Bowlogna ontology

• Extending & managing Bowlogna data

– Entity-centric data management

The Bologna Reform

• Started in June 1999

• Framework for higher education systems

• 47 Countries

• Common academic degrees

• Common study structure

• Common terminology

20

The university setting after Bologna

• A lot of data is available – Not following standard schemas

– Comprehensive and available data is a success factor

• Shared data – Erasmus exchanges

– Courses in a given language

• Analytic tools may help monitoring university performance

21

An ontology about Bologna

• A Lexicon for the Bologna Reform

– Basic set of terms for the new system

– Stable across time and institutions

– Developed by a professional terminologist

22

The ontology creation process

• The Bowlogna Ontology

– 29 top classes (67 in total)

– Classes: student, professor, evaluation, teaching

unit, ECTS credit, semester, etc.

– Concept definitions in English, French, German

23

Bowlogna Ontology

24

Bowlogna Ontology

• Private / Public parts

– Public data can be shared with other uni (e.g.,

course descriptions)

– Private data in sensible (e.g., evaluation results)

• Private data might contain more instances

• Aggregations over private data may be shared

(e.g., number of enrolled students)

25

Managing Bowlogna Data

• Entity-Centric Data Management

– Searching for entities

– Linking entities

– Typing entities

– Storing entities

26

Entities as Mediation

• Rising paradigm – Store information at the entity granularity

– Integrate information by inter-linking entities

• Advantages? – Coarser granularity compared to keywords

• More natural, e.g., brain functions similarly (or is it the other way around?)

• Easier to integrate 3rd party information

– Denormalized information compared to RDBMSs • Schema-later, heterogeneity, sparsity

• Pre-computed joins, “Semantic” linking

• Drawbacks?

27

Searching for Entities (1)

The Descendants

TheDescendants

type

title

GeorgeClooney

George Clooney

name

May 6, 1961

dateOfBirth

type

ShaileneW

Shailene Woodley

name

Nov. 15, 1991

dateOfBirth

type

playsIn

playsIn

• Main idea: combine unstructured and structured search

– Inverted index to locate first candidates

– Graph queries to refine the results

• Graph traversals (queries on object properties)

• Graph neighborhoods (queries on data type properties)

Inverted Index

Keywords

HTTP

DBMS

SPARQL

28

Searching for Entities (2)

LOD Cloud

index()

User

Query Annotation and Expansion

Inverted Index

RDF

Store

Ranking FunctionsRanking

FunctionsRanking Functions

query()

Entity SearchKeyword Query

intermediate

top-k resultsGraph-Enriched

Results

Graph Traversals(queries on object

properties)

Neighborhoods(queries on datatype

properties)

Structured

Inverted Index

WordNet

3rd party

search engines

Final Ranking Function

Pseudo-Relevance Feedback

29

Linking Entities (1)

• ZenCrowd: linking textual content to entities

• Uses sets of algorithmic matchers to match

entities to online concepts

• Uses dynamic templating to create micro-

matching-tasks and publish them on MTurk

• Combines both algorithmic and human

matchers using probabilistic networks

30

Linking Entities (2)

Micro Matching

Tasks

HTML

Pages

HTML+ RDFa

Pages

LOD Open Data Cloud

Crowdsourcing

Platform

Z enCrowd

Entity

Extractors

LOD Index Get Entity

Input Output

Probabilistic

Network

Decision Engine

Mic

ro-

Ta

sk M

an

ag

er

Workers Decisions

Algorithmic

Matchers

31

Storing Entities (1)

• Fundamental impedance mismatch between

graphs of entities and…

– N-ary / decomposition storage model

– Inverted Indices

– Key-value paradigms

32

Storing Entities (2)

• dipLODocus[RDF]

– Materialize the joins!

– Dense-pack the values

– Provide new indices

– Co-locate

– Co-locate

– Co-locate

33

Typing Entities

34

Type rankingType ranking

Type ranking

Text

extraction

(BoilerPipe)

Named Entity

Recognition

(Stanford NER)

List of

entity

labels

Entity linking

(inverted index:

DBpedia labels ⟹

resource URIs)

foreach

List of

entity

URIs

Type retrieval

(inverted index:

resource URIs ⟹ type URIs)

List of

type

URIs

Type rankingRanked

list of

types

Trank • Input: a knowledge base G, an Entity e, a context c in

which e appears. • Output: e’s types ranked by relevance wrt the context c.

References

• The Bowlogna ontology: Semantic Web J. 2013

• Searching for entities: SIGIR 2012

• Linking entities: WWW 2012, VLDB J. 2013

• Storing entities: ISWC 2011

• Typing entities: ISWC 2013

35

Pause

What else needs representing in educational

data?

What to do with it

Resource

Discovery

Research

Exploration

Social

Example: UK HESA/UNISTAT Key Information Set

http://www.hesa.ac.uk/unistatsdata

“Unistats, which incorporates the KIS, provides course level information on all undergraduate higher education courses provided in the UK, which are of at least one year’s duration and consist of 120 or more credits of study” [1]

Includes statistics about the success rate of degrees (courses), the type of assessment, and what students do afterwards (further study, jobs).

[1] http://www.hesa.ac.uk/includes/C13061_resources/Unistats_checkdoc_definitions.pdf?v=1.12

Simple application:

Tell me the job you

want to do, I tell you

what degree (in the

UK) you might want

to study

Currently: It is Open Data (kind of)

Building an application on top of this?

Need to download the data, unzip parse the xml, re-interpret it into own model, store the data, provide querying facility, and finally, build the application.

Doing it as linked data with a SPARQL endpoint does that once for everybody!

http://data.linkededucation.org/linkedup/catalog/browse/

90 lines of HTML/Javascript,

written in a couple of hours

select distinct ?course ?label ?link ?perc where {

?o <http://purl.org/linked-data/cube#dataSet>

<http://data.linkedu.eu/kis/dataset/commonJobs>.

?o <http://data.linkedu.eu/kis/ontology/job>

<http://data.linkedu.eu/kis/job/354>.

?o <http://data.linkedu.eu/kis/ontology/course>

?course.

?course <http://purl.org/dc/terms/title> ?label.

?course

<http://data.linkedu.eu/kis/ontology/courseUrl>

?link.

?o

<http://data.linkedu.eu/kis/ontology/percentage>

?perc.

filter ( ?perc > 0 )

} order by desc(?perc)

Using this SPARQL Query:

Example: Resource Discovery (http://discou.info)

data.open.ac.uk

Semantic

Indexing

Semantic Index

Named Entity

Recognition

Podcasts, OpenLearn

Units and Articles

Semantic Entities

(Dbpedia)

Indexes

BBC Programme or iPlayer page

Synopsis

Similarity-

Based Search

Indexes

Interface

Resource

descriptions

Resources URIs +

common topics

API/Service view

Interface

(Javascript)

Injected with bookmarklet

Named Entity

Recognition Indexing

Similarity

Search

Common

Topic

Extraction

Programme

URI

Scored

semantic

entities

Prg. URI &

Res. URI

Common Sem. Entity

Scored sem.

Entities & Prg

URI

Prg.

URI Resource

URIS

Same thing, with just text (discou.info/alfa)

And on course material (open + closed data)

17/11/13 LinkedUp – Besnik Fetahu 49

17/11/13

Source: http://lod-cloud.net/state, September 2011

Domain Number of

datasets Triples % (Out-)Links %

Media 25 1,841,852,061 5.82 % 50,440,705 10.01 %

Geographic 31 6,145,532,484 19.43 % 35,812,328 7.11 %

Government 49 13,315,009,400 42.09 % 19,343,519 3.84 %

Publications 87 2,950,720,693 9.33 % 139,925,218 27.76 %

Cross-domain 41 4,184,635,715 13.23 % 63,183,065 12.54 %

Life sciences 41 3,036,336,004 9.60 % 191,844,090 38.06 %

User-generated

content 20 134,127,413 0.42 % 3,449,143 0.68 %

295 31,634,213,770

503,998,829

Example: Topic Exploration

What is the data about?

The Big Picture: What is the data about?

17/11/13 LinkedUp – Besnik Fetahu 50

Domain Number of

datasets Triples % (Out-)Links %

Media 25 1,841,852,061 5.82 % 50,440,705 10.01 %

Geographic 31 6,145,532,484 19.43 % 35,812,328 7.11 %

Government 49 13,315,009,400 42.09 % 19,343,519 3.84 %

Publications 87 2,950,720,693 9.33 % 139,925,218 27.76 %

Cross-domain 41 4,184,635,715 13.23 % 63,183,065 12.54 %

Life sciences 41 3,036,336,004 9.60 % 191,844,090 38.06 %

User-generated

content 20 134,127,413 0.42 % 3,449,143 0.68 %

295 31,634,213,770

503,998,829

and many

more

languages

(16)…

and many

more

organisatio

ns (184)…

The Big Picture: How to find the right information?

17/11/13 LinkedUp – Besnik Fetahu 51

How to find information

about “renewable

energy”?

search into individual

resources in all these

sources?

338 sources of information

~300 million individual

resources

- Manual inspection costly!

- Current infrastructure is not

reliable for such large scale

queries!

now what? Generate representative topics

for the individual data sources

Topics linking the data sources

into a central and interlinked

graph

Explore the graph for specific

concepts e.g. “renewable

energy”

Constructing Topic Profiles

17/11/13 LinkedUp – Besnik Fetahu 52

book

thesis

proceedings series

audio document manuscript

newspaper report The types of

information

existing in the

data source

individual

resources

Linux in wenigen Stunden beherrschen ; absolut keine Vorkenntnisse nötig! ; ideal für Einsteiger und Umsteiger ; Animationen, Videos und Sprachausg. erklären LINUX Schritt für Schritt.

"British Association for Biofuels and Oils“ The prime objective of the Association is to persuade Government to modify the tax on Biodiesel so as to give this splendidly 'green' fuel a chance to establish itself to the advantage of the environment. This means a tax structure which ensures that the pump price of Biodiesel is at least competitive with fossil diesel. A second objective is to see established in Britain a Biodiesel plant of sufficient size to get the appropriate economies of scale in production costs.

organization

"British Association for Biofuels and Oils“

The prime objective of the Association is to persuade Government to modify the tax

on Biodiesel so as to give this splendidly 'green' fuel a chance to establish itself

to the advantage of the environment. This means a tax structure which

ensures that the pump price of Biodiesel is at least competitive with fossil diesel.

A second objective is to see established in Britain a Biodiesel plant of sufficient

size to get the appropriate economies of scale in production costs.

Linux in wenigen Stunden beherrschen ; absolut keine

Vorkenntnisse nötig! ; ideal für Einsteiger und Umsteiger;

Animationen, Videos und Sprachausg. erklären

LINUX Schritt für Schritt.

http://de.dbpedia.org/page/Linux

category-de:Freies_Betriebssystem

category-de:Linux

category-de:Unixoides_Betriebssystem

http://de.dbpedia.org/page/Animation

category-de:Animation

http://de.dbpedia.org/page/Videoclip

category-de:Video

http://dbpedia.org/page/Biodiesel

category:Biodiesel

category:Biofuels

category:Liquid_fuels

http://dbpedia.org/page/Economy

category:Economics

category:Economic_systems

http://dbpedia.org/page/Price category:Pri

cing

category:Marketing

http://dbpedia.org/page/Biofuel category:Bioenerg

y

category:Biomass

category:Fuels

category:Renewable_fuels

Constructing Topic Profiles (I) individual resources

Linux in wenigen Stunden beherrschen; absolut keine Vorkenntnisse nötig! ; ideal für Einsteiger und Umsteiger;

Animationen, Videos und Sprachausg. erklären LINUX Schritt für Schritt.

"British Association for Biofuels and Oils“ The prime (…) to persuade Government to modify the tax on

Biodiesel so as to give (…) to the advantage of the environment.

This means a tax (…)that the pump price of (….) A second objective

is to see established in Britain a Biodiesel plant of (…)appropriate

economies of scale in production costs.

topic profiles from the individual sources

biodiesel

biofue

l liquid fuels

economy

economic

systems

bioenergy

fuel

biomass

linu

x

video

17/11/13 LinkedUp – Besnik Fetahu 54

Exploring topics: Finding the right information? How to find information

about “renewable

energy”?

search individual resources

from all information sources?

explorable topic

graph biodiesel

biofuel

liquid fuels

economy

economic systems

bioenergy

fu

el

biomass

linux

video

• Searching for topics about “renewable

energy”, we find the following?

• 5 datasets

• data-gov-uk, clean-energy-reegle,

educationalprograms_sisvu,…

• Thousands of resources talking about:

biodiesel, biofuel, wind farms,

hydroelectricity, solar power, sugar

canes, etc.

Finding resources about “Renewable Energy”

17/11/13 LinkedUp – Besnik Fetahu 55

• From millions of resources from all information

sources to top matching ranked resources

about “Renewable Energy”

• Resources with “Renewable Energy” as a

topic convey information about different forms

of renewable energy:

• Solar Energy

• Wind-farms

• Biogas

• Hydroelectricity etc.

http://enipedia.tudelft.nl/wiki/Windmar_Renewable_Energy

http://enipedia.tudelft.nl/data/page/eGRID/Plant/57050

http://enipedia.tudelft.nl/wiki/Us_Energy_Biogas_Corp

http://www.reegle.info/profiles/JP

Topic Profiling: Applications!

17/11/13 LinkedUp – Besnik Fetahu 56

http://data-observatory.org/lod-profiles/profile-explorer/

http://data-observatory.org/lod-

profiles/sparql-endpoint

http://data-observatory.org/lod-profiles/

More examples: Data mining, knowledge

discovery, analytics

Learning

Analytics

Exploring communities

Course

management

Pause

What applications for educational Web data?

Open Education

Removing barriers to education

Open Education

Food for thought

More minds online

• Around 2.7 billion people (40% of the world's population)

will be connected to the Internet by the end of 2013 – UN

sources

• Several billion more in the forthcoming years – from

developing countries, many with disabilities

• Worldwide demand for higher education

• New pedagogies needed for large-scale student teaching

Open Data in Education

Overview

Open data in education

• All open data that can be used for educational purposes

(e.g research data, GLAM data etc.) Data exploited/used

by education.

Open data that comes out of education institutions

• Administrative data created by educational institutions

that can improve efficiency, allow students to make

informed decisions etc.

Both relevant to the LinkedUp Project

What type of data?

http://www.slideshare.net/louiscrusoe/open-education-data

How can we use open data

…to meet educational needs?

By supporting students

• Through creation of new tools that enable new ways to

analyse and access data e.g. maps of disabled access, tools

for disciplines

• By enriching resources, making it easier to share and find

them, and how to personalize the way they are presented

• By allowing student to explore resources, concepts, ideas

and objects in various areas

• To make informed choices on education e.g. by comparing

scores, course data etc.

How can we use open data

…to meet educational needs?

By supporting schools and institutions

• Learning analytics data can help retain students

• Use data can enable efficiencies in practice e.g. library data can

help support book purchasing

• Benchmarking and performance measuring

By supporting governments and policy

• Open data can lead to change in policy

• Open data can lead support transparency & enable efficiency

• Data on equity and equality issues (3rd world countries)

• Education reform

Education & Development

How can open data help?

• Data is crucial for planning, managing budgets and spending,

and evaluation

• Transparency of data is essential

• Interesting work going on to build tools to analyse data,

building capacity etc.

• Global Partnership for Education Open Data Project (57 key

education indicators from 29 countries)

• The data revolution in education and development:

http://bit.ly/data-development

• School of data: http://schoolofdata.org

Keep an eye on…

Working Group

Overview

• Binds together people to promote open data, open

educational resources (OER) and open educational

practices

• First activity: Writing the Open Education Handbook

• Mailing list, Twitter feed

• Want to see the discussions around open data in

education pulled into the wider debates around open

education

• http://education.okfn.org

Open Education Handbook

Overview

• First activity of Working Group

• Deliverable for LinkedUp Project

• Collaboratively authored

• Booksprint #1 London

• Booksprint #2 Berlin

• Open Ed Timeline event

• Now on Booktype

• Looking at synergies between

areas

Check out:

Linkeduniversities.org Linkededucation.org education.okfn.org

Linkedup-project.eu linkedup-challenge.org

data.linkededucation.org/linkedup/catalog

data.linkededucation.org/linkedup/devtalk

Picture credits

• http://www.flickr.com/photos/colorblindpicaso/2902713219/

• http://www.flickr.com/photos/army_arch/2860392346/

• http://www.flickr.com/photos/tulanesally/5198784680/

• http://www.flickr.com/photos/erfgoed/6743262901/

• http://www.flickr.com/photos/melystu/4984029996/

• http://www.flickr.com/photos/tulanesally/5202279590/

• http://www.flickr.com/photos/75905404@N00/4152885782/

• http://www.flickr.com/photos/jeffozvold/2253932630/

• http://www.flickr.com/photos/75905404@N00/3482204217/

• http://www.flickr.com/photos/soutra/4254200381/

• http://www.flickr.com/photos/70832171@N07/7911285000/

• http://www.flickr.com/photos/37996583811@N01/7354910368/

• http://www.flickr.com/photos/dbc-photography/4466855461/

• http://www.flickr.com/photos/pnnl/3638446615/

Case-Study: data.open.ac.uk

Case Study: data.open.ac.uk

Course information: 600 modules/ description of the course, information about the levels and number of

credits associated with it, topics, and conditions of enrolment.

Research publications: 25,000 academic articles / information about authors, dates, abstract and venue of the

publication.

Podcasts: 2220 video podcasts and 1500 audio podcats / short description, topics, link to a

representative image and to a transscript if available, information about the course the

podcast might relate to and license information regarding the content of the podcast.

Open Educational Resources: 640 OpenLearn Units / short description, topics, tags used to annotate the resource, its

language, the course it might relate to, and the license that applies to the content.

Youtube videos: 900 videos / short description of the video, tags that were used to annotate the video,

collection it might be part of and link to the related course if relevant.

University buildings: 100 buildings / address, a picture of the building and the sub-divisions of the building into

floors and spaces.

Library catalogue: 12,000 books/ topics, authors, publisher and ISBN, as well as the course related.

Others…

AIISO

BIBO

MEDIA

FOAF

DC

GEO

Deployment

Original systems / Databases

Dedicated extractors

daily

updates

Triple store

RDF

SPARQL endpoint

URI Resolver Web server

owl:sameAs

mlo:offers

mlo:location

http://data.open.ac.uk/course/m366

http://sws.geonames.org/2963597/ (Ireland)

http://data.open.ac.uk/organization/the_open_university

http://education.data.gov.uk/id/school/133849

select distinct ?q (count(distinct ?t) as ?n) where {

?q a <http://purl.org/net/mlo/qualification>.

?q <http://data.open.ac.uk/saou/ontology#hasPathway> ?p.

?p <http://data.open.ac.uk/saou/ontology#hasStage> ?s.

{{?s <http://data.open.ac.uk/saou/ontology#includesCompulsoryCourse>

?c}

union

{?s <http://data.open.ac.uk/saou/ontology#includesOptionalCourse> ?c}}.

?c <http://purl.org/dc/terms/subject> ?t.

[] <http://www.w3.org/2004/02/skos/core#hasTopConcept> ?t.

} group by ?q order by desc(?n)

List of courses (degrees, etc.) at The Open University, with number of

topics they cover

Example:

data.open.ac.uk/query

URI of the query:

http://data.open.ac.uk/query?query=select%20distinct%20...

Example: Map of buildings

Interactive map of Open University Buildings in the UK

Built in 1 hour

Connected to Ordnance Survey for location based on post-codes

Allowed us to find out about issues in the data.

Spaces

Floors

ID Address Post-code

Buildings

bat1

bat1-address

Postcode-mk76aa

name “Berrill building”

data.open.ac.uk

Milton Keynes

inDistrict

Buckinghamshire

inCounty

Mk76aa-location

location

lat long

52.024924 -0.709726

data.ordnancesurvey.co.uk