State and future of linked data in learning analytics
Download as PPT, PDF1 like1,128 views
The document outlines the agenda for a tutorial on using linked data in learning analytics. It discusses the current and potential uses of linked data in learning analytics, including as a data modeling approach, as a data source, and for ontological models and integration. It also summarizes results from the LAK Data Challenge, which involved using linked data for tasks like statistical analysis, network analysis, recommendation, and visualization. While linked data is not yet widely used in learning analytics, the document argues it will become more standard as the benefits become better understood and more education and resources are provided to the community.
State and future of linked data in learning analytics
- 1. State of Linked Data in Learning Analytics And future…
- 2. 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
- 3. What is (sometimes) being done Linked data as basic underlying data modelling Linked data as data source Semantic Web for ontological models and integration Some use in recommendation Some use in visualisation / social network analysis
- 4. Going further Some other tool SPARQL endpoint SPARQL SPARQL CSV Results proxy Open Refine Excel RDF
- 5. Going further Some ! other tool SPARQL endpoint I SPARQL SPARQL N CSV G Results O R proxy B Open Refine Excel RDF
- 6. From the LAK Data Challenge Statistical analysis, network analysis Exploration, facet search and browsing Recommendation Visualisation / visual analytics Search and retrieval Rethorical / narrative analysis Trend Analyis
- 7. From LAK Linked data and semantic web in the CFP… but LAK 2013 1 paper with a strong linked data component 1 tutorial (this one) LAK 2012 1 workshop (LALD 2012) LAK 2011 1 paper on semantic social analysis 7
- 8. Going further data.ox.ac.uk mEducator data.open.ac.uk Lodum.de … Gephi Tableau Weka … Results / findings / insights / aggregates / … Interpretation Understanding
- 9. Challenges Data: Technology: Overview of what exist Data mining in linked data Integration – can we jointly query all of Linked data quality specification these things? Heterogeneity, dealing with multiple Provenance sources Coverage, adoption Skills: Development with new technologies Usage: Dealing with large, distributed data Linked data for interpretation Change with respect to usual data Linked data for enrichment management approaches Linked data for re-purposing Moving away from traditional Linked data for result publication cataloguing approaches
- 11. Collecting and cataloguing data http://data.linkededucation.org/linkedup/catalog/
- 12. Architecture
- 13. Process
- 14. CKAN-based catalogue http://datahub.io/group/linked-education
- 15. Data browsing interface http://data.linkededucation.org/linkedup/catalog/
- 16. SPARQL endpoint http://data.linkededucation.org/linkedup/catalog/sparql
- 17. Vocabularies in the datasets
- 18. Types in the datasets
- 19. Lightweight-Global integration Simple manual mapping of the types (classes) in the datasets to a set of selected vocabularies
- 20. Supporting development http://data.linkededucation.org/linkedup/devtalk/
- 21. Education/training events LAK 2013 tutorial Using Linked Data in Learning Analytics WWW 2013 tutorial Open learning and linked data Rio de Janeiro, 14th May 2013 SSSW 2013 (http://sss.org/2013) Summer School on Ontology Engineering and the Semantic Web Cercedilla (near Madrid), Spain 7-13 July 2013 Deadline to apply: 12th April 2013
- 22. And of course, the Challenge! http://linkedup-challenge.org
- 23. Take home message Linked Data is essential to Learning Analytics: provides a flexible, reusable source of information for all the steps of the analytics process Still some efforts to make for a complete understanding by the Learning Analytics community of the benefits of adopting (and learning) linked data But, through various channels, will soon become standard practice 10. April 201323