LAK dataset

Analytics on Learning Analytics…

In collaboration with strategic partners, SoLAR is making it possible to perform computational analyses on the Learning Analytics research literature. We are making publicly available machine-readable versions of research sources for scientometrics and other methodologies.

Technical Partners

Content Partners

This site provides access to structured fulltext and metadata from key research publications in the field. This advances SoLAR’s mission, as it provides not only more comprehensive search facilities to discover relevant work in the growing corpus, but also enables researchers to analyse the field — for instance, to track the evolution of a topic over time, or to identify correlations with related communities.

The ACM International Conference on Learning Analytics and Knowledge (LAK) sponsored by SoLAR is the field’s premier research forum, providing common ground for academics, administrators, software developers and companies to shape and debate the state of the art in learning analytics and related fields. The ACM conditions of providing the full text of the LAK Conference Proceedings specify:

  • ACM is providing this ACM Digital Library data solely for research purposes, gratis. Should software that is beneficial to the users of the ACM Digital Library be developed using this data, whenever feasible, ACM would appreciate an as-is perpetual royalty-free license to that software to be used by ACM solely in the context of ACM’s Digital Library services to benefit the Computer Science community.

Dataset

Metadata has been extracted to create a corpus with the full text, and metadata including  authors, affiliations, titles, keywords and abstracts. The schema used to describe the papers in the dataset is based on two established schemas: the Semantic Web Conference Ontology (already used to describe metadata about publications from the Semantic Web conferences and related events) and the Linked Education schema.

The data is accessible in various forms:

  1. Zipped XML file for download [LAK] [EDM]
  2. R format (thanks Adam Cooper) hosted on the KMi Crunch R server [LAK+EDM]
  3. Using semantic web infrastructure, a public SPARQL endpoint provides access to structured RDF metadata according to LOD principles. The endpoint is available via http://data.linkededucation.org/openrdf-sesame/repositories/lak-conference?query=[your sparql query]
    View some example queries.

LAK Data Challenge

Beyond publishing the data, we will also support its innovative use and exploitation through a public LAK Data Challenge, co-located with the ACM LAK’13 Conference.

Examples of analyses are already beginning to be shared…

People and Organisations

Contacts

  • Data enquiries: Davide Taibi (davide.taibi atsign itd.cnr.it)
  • LAK Data Challenge enquiries: Stefan Dietze (dietze atsign l3s.de)

Related publications

Research reporting the results of analyses will be added as activity builds around the dataset, to demonstrate the possibilities.

Please refer to the following publication for further information and when referring to the LAK Dataset:

Taibi, D. and Dietze, S. (2013), Fostering Analytics on Learning Analytics
Research: the LAK Dataset. In: CEUR WS Proceedings Vol. 974, Proceedings
of the LAK Data Challenge, held at LAK2013 – 3rd International Conference on
Learning Analytics and Knowledge (Leuven, BE, April 2013). (PDF online at: http://ceur-ws.org/Vol-974/lakdatachallenge2013_preface.pdf)