Putting Intelligence in Open Data - With examples in education
2 likes1,823 views
The document discusses using semantic web and linked data technologies in education. It provides examples of how the Open University publishes various educational resources as linked open data, including course descriptions, publications, podcasts, videos and more. It also demonstrates how this data can be queried with SPARQL and used to build applications like interactive maps. The use of linked data is shown to support applications involving learning analytics, data mining, and automatically explaining patterns in educational data.
![SPARQL
Show some basic slides there
Front page
Sparql endpoint
Update follow up application slide
Discou – CRC – tackboard – REF - openlearn
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](https://image.slidesharecdn.com/crete-26-05-2014-140527011209-phpapp02/85/Putting-Intelligence-in-Open-Data-With-examples-in-education-8-320.jpg)
Putting Intelligence in Open Data - With examples in education
- 1. Putting intelligence With examples in education Mathieu d’Aquin (@mdaquin) Knowledge Media Institute, The Open University, UK in web data
- 2. Mathieu d’Aquin (@mdaquin) Knowledge Media Institute, The Open University, UK Research Fellow – Background in Artificial Intelligence, Knowledge Engineering, Reasoning Working on Semantic Web, Linked Data and Knowledge Technologies Especially applied to education and personal information management/Privacy Research Lab, ~75 people, many industrial and academic collaborations, Leader in semantic web, linked data, TEL, learning analytics, new media research Open and Distance Learning University, the biggest university in the UK in number of students (~250,000 per year), 13 regional centres, + national centres. Almost all teaching at distance. Putting intelligence With examples in educationin web data
- 4. The Semantic Web Connected knowledge where entities, concrete and abstract, have formal attached meaning/interpretations The Web Network of documents interconnected with hyperlinks The Linked Data Web Graph of data objects connected by labelled hyperlinks
- 6. 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 and people: 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… Content
- 8. SPARQL Show some basic slides there Front page Sparql endpoint Update follow up application slide Discou – CRC – tackboard – REF - openlearn 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
- 9. Simple example Interactive map of Open University Buildings in the UK
- 10. Spaces Floors ID Address Post- code Buildings build 1 build1- address Postcode- mk76aa name “Berrill building” data.open.ac.uk Milton Keynes inDistrict Buckingha mshire inCounty Mk76aa- location location lat long 52.024924 -0.709726 data.ordnancesurvey.co.uk
- 11. Many other (simple) applications
- 12. Data Linked Data The Semantic Web
- 14. Example in education: DiscOU See discou.info | d'aquin et al @ Demo ISWC 2012
- 15. Example in research: The Listening Experience Database Project with Royal College of Music and the Open University's Art Faculty Goal: Create a large database of evidence of people listening to music (of any genre, at any time, in any place) See led.kmi.open.ac.uk
- 16. Linked data and ontologies to support data crowd- sourcing
- 17. Results ~700 contributions so far
- 18. Data/Information/Knowledge on the Semantic Web NLP Information retrieval Recommender Systems Data Mining Step further: intelligent applications and knowledge discovery
- 19. The Linked Data Web Graph of data objects connected by labelled hyperlinks The Semantic Web Connected knowledge where entities, concrete and abstract, have formal attached meaning/interpretations Intelligent Web information and knowledge processing Discovering knowledge models
- 20. Example in Education: The LinkedUp Data Catalogue See data.linkededucation.org/linkedup/catalogue/ See d'Aquin et al in ERCIM News 96
- 22. Summary visualisation of extracted schema
- 23. FCA-based technique to extract URI patterns in RDF datasets
- 24. Interactive mapping onto canonical ontologies
- 25. See d'Aquin et al @ WebSci2013 Getting a top level view of an area through its datasets … and looking at relationships between datasets (see the Datanode ontology)
- 26. Example(s) in Education: Learning Analytics Location of students showing particular interest based on their enrolment into courses
- 27. ID course post- code Students data.open.ac .uk Topics data.ordnancesurvey. co.uk Districts Location Clustering Other resources DBpedia Geonames
- 28. How to interpret the results? See d'Aquin and Jay @ LAK2013 Sequence mining to find common study pathways and FCA_Linked Data to interpret them
- 31. Can we use linked data automatically to explain data patterns? See Tiddi et al. @ ESWC2014 Taking inspiration from ILP: Interest in studying Health and Social Care Positive examples Negative examples Swansea East London Machester Milton Keynes Sheffield Brighton Southampton Bristol … …. Background Knowledge?
- 32. Linked Data Traversal See Tiddi et al. @ ESWC2014 Swansea Manchester Sheffield Southampton East London Milton Keynes Bristol Brighton 51.2 -2.3 Dbpedia:Milton_Keynes Dbpedia:Labour 241K yago:unitary_authority opencyc:unitary_authority freebase:Bristol 198K 350mm Dbpedia:Bristol yago:city opencyc:city Dbpedia:Tory Dbpedia:Southampton freenase:Southampton 240mm 270K 290K sameAs sameAs sameAssameAs sameAs sameAs type type long lat poppop pop pop pop party party party rain rain
- 33. SummaryIntelligent information processing The Semantic Web Linked Data Web The Web Making smart thing with what we can find in the web Naturally integrated data, flexible model for rapid development Large scale, collaborative, distributed, uncontrolled Connected, decentralised, independent
- 34. Future Understand this Make explicit the competence of data in being used at the upper level, what is being done to it when going from raw to processed. Formalise the practice level in addition to the symbol, syntax and semantic levels, to boost development benefits. Create generic, standard processes for the development of intelligence semantic web systems.
- 35. Future And build more with it... New environments even more demanding – more sophistication and intelligence required! See mksmart.org
- 36. Thank You! More at: http://people.kmi.open.ac.uk/mathieu http://mdaquin.net m.daquin@open.ac.uk @mdaquin These slides at: http://slideshare.net/mdaquin Team: Ilaria Tiddi Alessandro Adamou Enrico Daga Keerthi Thomas
- 37. More complex reasoning example (in personal data management): Epistemic reasoning for privacy on Facebook • Screenshot See d'Aquin and Thomas @ Demo ISWC 2013
- 39. Facebook Ontology (extract) Person Post Photo Video Status update Comment Agent App subclass author likes includes subclass author on Place in {Everyone, Friends_of_Friends, All_Friends, Custom} scope
- 40. Example epistemic rules Ka Post(X) :- author(X, a) Ka Post(X) :- scope(X, All_Friends), author(X, Y), friend(Y, a) Ka Post(X) :- includes(X,Y), friend(Y, a) Ka wasIn(P, Y) :- includes(X,Y), in(X,P), Ka Post(X) Ka wasWith (Y,Z) :- includes(X, Y), includes(X, Z), Ka Post(X)