Domain Categorization of Open Educational Resources Based on Linked Data

  • Janneth Chicaiza
  • Nelson Piedra
  • Jorge Lopez-Vargas
  • Edmundo Tovar-Caro
Part of the Communications in Computer and Information Science book series (CCIS, volume 468)


One of the main objectives of open knowledge, and specifically of Open Educational Resource movement, is to allow people to access the resources they need for learning. The first step to that a learner starts this process is to find information and resources according to his/her needs. One of the reasons why OERs could stay hidden and therefore to be underutilized is that each institution and producer of this kind of resources, labels them using tags or informal and heterogeneous knowledge schemes. This issue was identified in the Open Education Consortium (until recently called OpenCourseWare Consortium) study, where respondents noted that one way to improve the courses is to make a “major better categorization of courses according to subject areas”. In previous works, the authors present the Linked OpenCourseWare Data project, which published metadata of courses coming from different open educational datasets. So far there are over 7000 indexed courses associated to 626 topic names or knowledge fields, however, appear different names meaning similar areas or they are written in different languages and also correspond to different detail level. The semantic lack in the relations between areas and subjects make it difficult to find associations between topics and to list recommendations about resources for learners. In this work, authors present a process to support semi-automatic classification of Open Educational Resources, taking advantage from linked data available in the Web through systems made by people who can converge to a formal knowledge organization system.


OCW linked data classification knowledge area discovery of resources web of data thesaurus DBPedia 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Piedra, N., Tovar, E., Colomo-Palacios, R., López, J., Chicaiza, J.: Consuming and producing linked open data: The case of Opencourseware. Program: Electronic Library and Information Systems 48, 16–40 (2014)CrossRefGoogle Scholar
  2. 2.
    OpenCourseWare Consortium: OCWC User Feedback Survey Results » Announcements (2013),
  3. 3.
    Francesconi, E., Faro, S., Marinai, E., Perugi, G.: A Methodological Framework for Thesaurus Semantic Interoperability. In: Proceeding of the Fifth European Semantic Web Conference, pp. 76–87 (2008)Google Scholar
  4. 4.
    Tovar, E., Piedra, N., López, J., Chicaiza, J., Martínez, O.: Linked OpenCourseWare Data: a demonstration of the potential use of OCW Universia linked Data. OpenCourse Ware Consortium Global Meetings, Cambridge, U.K (2012)Google Scholar
  5. 5.
    Bizer, C., Heath, T., Berners-Lee, T.: Linked Data - The Story So Far. International Journal on Semantic Web and Information Systems 5(3), 1–22 (2009)CrossRefGoogle Scholar
  6. 6.
    Bizer, C.: The Emerging Web of Linked Data. IEEE Intelligent Systems 24(5), 87–92 (2009)CrossRefGoogle Scholar
  7. 7.
    Cano, A.E., Varga, A., Rowe, M., Ciravegna, F., He, Y.: Harnessing Linked Knowledge Sources for Topic Classification in Social Media. In: Proceedings of the 24th ACM Conference on Hypertext and Social Media, pp. 41–50 (2013)Google Scholar
  8. 8.
    Husby, S.D., Barbosa, D.: Topic Classification of Blog Posts Using Distant Supervision. In: Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics, pp. 28–36 (2012)Google Scholar
  9. 9.
    Muñoz-García, O., García-Silva, A., Corcho, O., de la Higuera, M., Navarro, C.: Identifying Topics in Social Media Posts using DBpedia. In: Proceedings of the Networked and Electronic Media Summit (NEM summit 2011), Torino, Italia (2011)Google Scholar
  10. 10.
    Syed, Z., Finin, T., Joshi, A.: Wikipedia as an ontology for describing documents. In: Proc. of the Second Int. Conference on Weblogs and Social Media. AAAI Press (2008)Google Scholar
  11. 11.
    Hashimoto, C., Kurohashi, S.: Blog Categorization Exploiting Domain Dictionary and Dynamically Estimated Domains of Unknown Words. In: Proceedings of ACL 2008: HLT, pp. 69–72 (2009)Google Scholar
  12. 12.
    Troussov, A., Parra, D., Brusilovsky, P.: Spreading Activation Approach to Tag-aware Recommenders: Modeling Similarity on Multidimensional Networks. In: Proceedings of Workshop on Recommender Systems and the Social Web at the 2009 ACM Conference on Recommender Systems, RecSys 2009, New York, NY, October 25 (2009)Google Scholar
  13. 13.
    van Gendt, M., Isaac, A., van der Meij, L., Schlobach, S.: Semantic Web Techniques for Multiple Views on Heterogeneous Collections: A Case Study. In: Gonzalo, J., Thanos, C., Verdejo, M.F., Carrasco, R.C. (eds.) ECDL 2006. LNCS, vol. 4172, pp. 426–437. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  14. 14.
    Olieman, A.M.: Mastery Profiling through Entity Linking, to Support Project Team Formation in Higher Education. Graduate Thesis - University of Amsterdam - Information Studies (2013)Google Scholar
  15. 15.
    W3C: SKOS Simple Knowledge Organization System Reference (2009),
  16. 16.
    Chang, J., Blei, D.: Hierarchical Relational Models for Document Networks. The Annals of Applied Statistics 4(1), 124–150 (2010)CrossRefzbMATHMathSciNetGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Janneth Chicaiza
    • 1
  • Nelson Piedra
    • 1
  • Jorge Lopez-Vargas
    • 1
  • Edmundo Tovar-Caro
    • 2
  1. 1.Departamento de Ciencias de la ComputaciónUniversidad Técnica Particular de Loja
  2. 2.Dpto. Lenguajes y Sistemas Informáticos e IngenieríaUniversidad Politécnica de MadridSpain

Personalised recommendations