Using Linked Data in Learning Analytics tutorial - Introduction and basics of manipulating linked data
1. Using Linked Data in Learning Analytics
LAK 2013 tutorial
Mathieu d’Aquin (@mdaquin, mdaquin.net)
(Knowledge Media Institute, The Open University, UK)
Stefan Dietze
(L3S Research Center, DE)
Hendrik Drachsler
(CELSTEC, Open Universiteit Nederland, NL)
Eelco Herder
(L3S Research Center, DE)
2. Why a Linked Data Tutorial at LAK 2013?
A Naïve view
Learning Analytics is an application of data analytics on
educational data, in learning environment and for
the purpose to improve the learning and teaching
experience.
Linked Data is a set of technologies and principles to
expose, publish and interconnect data on the Web. It
is very popular nowadays for opendata,
eGovernment, academia and the industry because of
the flexibility and the global integration possibilities
it provides.
So, Linked Data used to find, collect and process large
amounts of interconnected data to be used in
analytics. But It is not only the input! Can be used to
complete local data, enrichment them, or for
interpretation of the results.
3. Schedule
8.30 Intro to the tutorial
Linked data and its potential in learning analytics scenarios
Basics of manipulating linked data
10.30 Coffee break
11.00 Using Linked Data in Analytics Tools
Evaluation of the Linked Data applications
12.30 Lunch
13.30 Introduction to the LAK Data challenge
Presentations from the LAK Data Challenge particiants
15.30 Tea break
16.30 Current state of Linked Data in Learning Analytics
Results of the challenge
Wrap up
17.30 Finished
4. The LAK Data Challenge (preview)
Soude Fazeli – Open Universiteit Nederland (Netherlands). Socio-semantic Networks of Research
Publications in the Learning Analytics Community
Michael Derntl, Nikou Günnemann and Ralf Klamma – RWTH Aachen (Germany). A Dynamic Topic
Model of Learning Analytics Research
Ricardo Alonso Maturana, María Elena Alvarado, Susana Lopez-Sola, María José Ibáñez and Lorena Ruiz
Elósegui – GNOSS (Spain). Linked Data based applications for Learning Analytics Research:
faceted searches, enriched contexts, graph browsing and geographic visualisation
Nikola Milikic, Uros Krcadinac, Jelena Jovanovic, Bojan Brankov and Srdjan Keca – University of
Belgrade, UZROK Labs (Serbia).Paperista: Visual Exploration of Semantically Annotated Research
Papers
Sadia Nawaz, Farshid Marbouti and Johannes Strobel – Purdue University (United States). Analysis of
the Community of Learning Analytics
Bernardo Pereira Nunes and Besnik Fetahu – L3S Research Center (Germany). Cite4Me: Semantic
Retrieval and Analysis of Scientific Publications
Davide Taibi, Ágnes Sándor, Duygu Simsek, Simon Buckingham Shum, Anna De Liddo and Rebecca
Ferguson – Italian National Research Council, Xerox Research Center (France), The Open University
(UK). Visualizing the LAK/EDM Literature Using Combined Concept and Rhetorical Sentence
Extraction
Amal Zouaq, Srecko Joksimovic and Dragan Gasevic – Royal Military College of Canada, Simon Fraser
University, Athabasca University (Canada). Ontology Learning to Analyze Research Trends in
Learning Analytics Publications
5. Your guides to the wild world of linked data
Mathieu Stefan Hendrik
@mdaquin @stefandietze @hdrachsler
Eelco
@eelcoherder
(put he is not actually here)
6. Linked data and its potential in learning analytics
scenarios
7. Linked Data
Person: Mathieu
Open University
Website
Publication: Pub1
author
workFor
Open University
VLE
Course: M366
offers
KMi Website M366 Course
page Organisation:
The Open University
Mathieu’s
Homepage availableIn
setBook
Mathieu’s
List of Mathieu’s
Publications Twitter Country: Belgium
Book: Mechatronics
The Web The Web of Linked Data
8. From Linked Data to the Semantic Web
rNews
Music
Ontology Geo
Ontology
SIOC Media
Ontology
Dublin
Core
DBPedia
FOAF
Ontology
DOAP
FMA BIBO
Ontology
LODE
Gene
Ontology
10. Data.open.ac.uk
Course information:
580 modules/ description of the course, information about the levels and number of
credits associated with it, topics, and conditions of enrolment.
Research publications:
16,000 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…
11. A global data space for education data
mEducator
The Open Data.gov.uk
University education
Research
Orgs., ouputs
Buidings,
Locations
Learning
resources University of
OrganicEduNet Muenster, DE
University of University of
Bristol Southampton
15. What’s the use in Learning Analytics
From Bienkowski, Feng, and Means
areas of LA/EDM applications
• Modeling user knowledge, behavior,
and experience… and connect them to
information about the context of
learning
• Creating profiles of users… that can be
interlinked through common objects
• Modeling knowledge domains…
through online knowledge sources that
Data can be numerous and collectively built
• Trend analysis… that can be
Integration interpreted through related them to
external sources of information
Understanding • Personalization and adaptation…
using indirect connections to other
reference entities
Original image from George Siemens
http://www.elearnspace.org/blog/2010/08/25/what-are-learning-analytics/
16. Example of simple application: Map of OU buildings
Interactive map of Open University
Buildings in the UK
Each dot is a location where buildings can
be found. Going over the dot give
information about the building there
(floors, spaces, car-parks, etc.)
17. data.open.ac.uk
name “Berrill building”
bat1 Milton
Keynes
bat1-
address inDistrict
inCounty
Postcode-
mk76aa
Buckingha
Spaces mshire
location
Floors
Mk76aa-
Buildings location
ID Address Post- lat long
code
52.024924 -0.709726
data.ordnancesurvey.co.uk
18. Simple recommendation: Study at the OU
Each topic as a linked data URI. Each course as a linked data URI. Each resource as a
linked data URI. They are all connected. Use SPARQL to answer the question:
“What are the resources related to this topic or to courses on this topic”
19. Less simple recommendation: Talis Aspire
Lecturers from different universities put their
reading lists online. Publishing using the principles
of linked data means that all resources are
globally identified, creating a network of resources
and reading lists.
Recommendations can then trivially exploit
globally all these local contributions.
21. Resources URIs + Similarity-Based
Interface common topics Search
BBC Programme or iPlayer page
Resource
descriptions
Indexes
Synopsis
Named Entity Semantic Semantic
Recognition Entities Indexing
(Dbpedia)
Podcasts, Indexes
OpenLearn Units
and Articles
data.open.ac.uk Semantic Index
24. Analytics across datasets
Academics in “Arts and Humanities” Topics most commonly mentioned by
most often involved with the media (in news outlets own by the BBC (in
number of news items) number of news items)
From the Open University From news clippings From DBpedia.org
27. Agenda
URIs – the basis
RDF – the representation language
Ontologies/Vocabularies – for schemas and models
SPARQL – for querying
SPARQL Update – for modifying (but we won’t say much about this)
28. URIs – three roles
Example:
http://data.aalto.fi/id/courses/noppa/dept_T3030
An identifier for a An anchor for linking An access point to
data entity Let’s say you have worked representation(s) of
there.
Here, the Department of Media
You – worked-at this URI the data entity
Technology of the University of In possibly different formats…
Aalto, Finland
29. URI resolving
http://data.aalto.fi/id/courses/noppa/dept_T3030
In the browser curl -H "Accept: application/rdf+xml" -L
(Accept: text/html) http://data.aalto.fi/id/courses/noppa/dept_T3030
<rdf:Description rdf:about="http://data.aalto.fi/data/id/courses/noppa/dept_T3030">
<rdfs:label>RDF description of Department of Media Technology</rdfs:label>
<foaf:primaryTopic>
<aiiso:Department rdf:about="http://data.aalto.fi/id/courses/noppa/dept_T3030">
<aiiso:teaches rdf:resource="http://data.aalto.fi/id/courses/noppa/course_T-111.5077"/>
<aiiso:teaches rdf:resource="http://data.aalto.fi/id/courses/noppa/course_T-111.2211"/>
<aiiso:teaches rdf:resource="http://data.aalto.fi/id/courses/noppa/course_Inf-0.3101"/>
<aiiso:teaches rdf:resource="http://data.aalto.fi/id/courses/noppa/course_T-75.5100"/>
<aiiso:teaches rdf:resource="http://data.aalto.fi/id/courses/noppa/course_T-111.5006"/>
<aiiso:teaches rdf:resource="http://data.aalto.fi/id/courses/noppa/course_Inf-0.1300"/>
<aiiso:teaches rdf:resource="http://data.aalto.fi/id/courses/noppa/course_T-75.5600"/>
<aiiso:teaches rdf:resource="http://data.aalto.fi/id/courses/noppa/course_T-75.4950"/>
<aiiso:teaches rdf:resource="http://data.aalto.fi/id/courses/noppa/course_T-111.1100"/>
<aiiso:teaches rdf:resource="http://data.aalto.fi/id/courses/noppa/course_T-111.6596"/>
<aiiso:teaches rdf:resource="http://data.aalto.fi/id/courses/noppa/course_T-75.5300"/>
<aiiso:teaches rdf:resource="http://data.aalto.fi/id/courses/noppa/course_Inf-0.1220"/>
<aiiso:teaches rdf:resource="http://data.aalto.fi/id/courses/noppa/course_T-111.4360"/>
<aiiso:teaches rdf:resource="http://data.aalto.fi/id/courses/noppa/course_T-111.5701"/>
<aiiso:code>T3030</aiiso:code>
<aiiso:teaches rdf:resource="http://data.aalto.fi/id/courses/noppa/course_T-75.4210"/>
<aiiso:teaches rdf:resource="http://data.aalto.fi/id/courses/noppa/course_T-111.5070"/>
<aiiso:teaches rdf:resource="http://data.aalto.fi/id/courses/noppa/course_T-75.4400"/>
<foaf:name xml:lang="en">Department of Media Technology</foaf:name>
<aiiso:teaches rdf:resource="http://data.aalto.fi/id/courses/noppa/course_T-111.5310"/>
<aiiso:teaches rdf:resource="http://data.aalto.fi/id/courses/noppa/course_T-111.5020"/>
<aiiso:teaches rdf:resource="http://data.aalto.fi/id/courses/noppa/course_T-75.1110"/>
9. April 2013 29
<aiiso:teaches rdf:resource="http://data.aalto.fi/id/courses/noppa/course_T-111.6595"/>
30. RDF – graph data model for linked data and the Web
Basic idea: URIs and literals (String, integers) are nodes - connected by
links labelled by properties (themselves identified as URIs)
http://data.aalto.fi/id/cour rdf:type
aiiso:Department
ses/noppa/dept_T3030
aiiso:School
foaf:name aiiso:part_of rdf:type
“Department of Media Technology” http://data.aalto.fi/id/co
“School of Science”
urses/noppa/org_SCI foaf:name
aiiso:teaches
teach:courseTitle http://data.aalto.fi/id/course rdf:type
“Filosofia” aiiso:Course
s/noppa/course_Inf-0.1202
dc:language
“fi”
33. Remember… data.open.ac.uk
name “Berrill building”
bat1 Milton
Keynes
bat1-
address inDistrict
inCounty
Postcode-
mk76aa
Buckingha
Spaces mshire
location
Floors
Mk76aa-
Buildings location
ID Address Post- lat long
code
52.024924 -0.709726
data.ordnancesurvey.co.uk
34. Ontologies and Vocabularies
Role: Provide common definitions for the types (classes) and properties
(relations) used in the RDF representations, and their expected
behaviour (meaning)
Vocabularies and ontologies we have already seen:
• AIISO: Academic Institution Internal Structure Ontology
• DC: Dublin Core
• FOAF: Friend of a Friend (for people and their connections)
• TEACH: For courses and academic programmes
Use the same mechanisms as Linked Data:
• Classes and properties have URIs
• They connect through special properties (rdf:type, rdfs:domain,
rdfs:range, rdfs:subClassOf, etc.)
Formal ontologies: define more precisely the intended meaning of types
and properties based on logical constructs
38. Querying: SPARQL
ASK query: is this true?
ask {<http://data.aalto.fi/id/courses/noppa/dept_T3030> a
aiiso:Department} (is it a department?)
ask{<http://data.aalto.fi/id/courses/noppa/dept_T3030> dc:subject ?x}
(is there a subject to this department?)
Select query: Get me some data
select ?org ?name where {
?x a aiiso:Department. ?x aisso:part_of ?org.
?org foaf:name ?name.
filter( ?x != <http://data.aalto.fi/id/courses/noppa/dept_T3030> )
} order by ?name limit 100
(get the organisations with names that have department, except T3030)
Construct query: Build a (sub) RDF graph
construct {?agent1 foaf:knows ?agent2} where
{?agent1 aiiso:responsibleFor ?x. ?agent2:responsibleFor ?x}
(Construct of graph of people knowing each-other because of being responsible from the same thing)
40. Example
select distinct ?course where {
?course
<http://data.open.ac.uk/saou/ontology#isAvailableIn>
<http://sws.geonames.org/2328926/>.
?course a <http://purl.org/vocab/aiiso/schema#Module>
}
Open University courses available in Nigeria (http://sws.geonames.org/2328926
/) on http://data.open.ac.uk/query
41. Example
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)
How many top level subjects are represented in individual Open University
qualifications on http://data.open.ac.uk/query
42. Example
select ?broader ?term ?narrower
where {
graph npgg:subjects {
?subject skos:prefLabel ?term .
?subject skos:broader [ skos:prefLabel ?broader ] .
?_ skos:broader ?subject ; skos:prefLabel ?narrower .
}
filter(regex(?term, "^Stem cells$", "i"))
}
order by ?broader ?narrower
Broader and narrower terms for "Stem cells“ on http://data.nature.com/query
43. Example
select ?doi ?data
where {
?doi a npg:Article ;
npg:hasDataCitation [ npg:hasLink [ ?_ ?data ] ; npg:type ?type ] .
filter(regex(?type, "pdb"))
}
limit 25
Data citations to the Protein Database on http://data.nature.com/query
45. Basic take away message
Linked data is about using the web architecture for sharing and connecting
data, with some form of meaningful interpretation (semantic web)
Potential in Learning Analytics processes: as input data, for data integration,
for enrichment, for interpretation
Based on simple technologies for web-based access to the data: URI, RDF, Web
Schemas, SPARQL
46. Links and References
http://linkeddata.org - http://linkeddatabook.com
http://data.open.ac.uk - http://lucero-project.info
http://linkeduniversities.org - http://linkededucation.org
http://linkedup-project.eu - http://linkedup-challenge.org
http://data.linkededucation.org/linkedup/catalog/
http://talisaspire.com/ - http://discou.info - http://uciad.info
http://http://www.w3.org/TR/rdf-sparql-query/ http://www.w3.org/TR/sparql11-update/
d'Aquin, M. and Jay, N. Interpreting Data Mining Results with Linked Data for Learning Analytics:
Motivation, Case Study and Direction, LAK 2013, http://oro.open.ac.uk/36660/
Kessler C., d’Aquin M. and Dietze S. (eds) Semantic Web Journal Special Issue on Linked Data for
Science and Education. http://iospress.metapress.com/content/m87017012802/
d’Aquin M. Linked Data for Open and Distance Learning. Commonwealth of Learnin report.
http://www.col.org/resources/publications/Pages/detail.aspx?PID=420
d'Aquin, M., Allocca, C. and Collins, T. DiscOU: A Flexible Discovery Engine for Open Educational
Resources Using Semantic Indexing and Relationship Summaries, Demo ISWC 2012.
http://data.open.ac.uk/applications/iswc2012-demo.pdf
Bienkowski, M., Feng M. and Means, B. Enhancing Teaching and Learning Through Educational Data
Mining and Learning Analytics: An Issue Brief. U.S. Department of Education, Office of Educational
Technology http://www.ed.gov/edblogs/technology/files/2012/03/edm-la-brief.pdf