Logo PTI Logo FedCSIS

Proceedings of the 21st Conference on Computer Science and Intelligence Systems (FedCSIS)

Annals of Computer Science and Information Systems, Volume 47

Interoperable educational data: What if data is no longer available?

,

DOI: http://dx.doi.org/10.15439/2026F5613

Citation: Kristine Hein,

Full text

Abstract. The integration of skill-centric educational data into data warehouses is a key enabler for data-driven analysis in education and labor market research. However, the efficacy of this process is hindered when underlying data sources undergo changes or become partially unavailable. This paper explores the question of how interoperable educational data can be maintained under such conditions. To this end, it uses the transition from the German platforms BERUFENET and Kursnet to meinNOW as a case study. We hereby propose a data engineering architecture that combines large-scale API-based extraction, relational data warehousing, and semantic enrichment using the European Skills, Competences, Qualifications and Occupations (ESCO) framework. The preservation of data continuity is of particular importance, and this is achieved through versioning, schema mapping, and the reconstruction of missing information. The findings indicate that while full continuity cannot be guaranteed due to structural and semantic changes in source systems, a consistent approximation of longitudinal data can be achieved. This necessitates the explicit management of schema evolution and uncertainty in reconstructed attributes. The paper emphasizes the necessity of critical reflection when interpreting longitudinal educational data derived from evolving sources.

References

  1. M. Udtha, K. Nomie, E. Yu, and J. Sanner, “Novel and emerging strategies for longitudinal data collection,” Journal of Nursing Scholarship, vol. 47, no. 2, pp. 152–160, 2015.
  2. S. I. Baek and Y. M. Kim, “Longitudinal analysis of online community dynamics,” Industrial Management & Data Systems, vol. 115, no. 4, pp. 661–677, 2015.
  3. A. Fischer and J. Dörpinghaus, “Web mining of online resources for german labor market research and education: Finding the ground truth?” Knowledge, vol. 4, no. 1, pp. 51–67, 2024.
  4. J. Dörpinghaus, J. Binnewitt, D. Samray, and K. Hein, “Understanding informatics in continuing vocational education and training data in germany,” ACM Transactions on Computing Education, vol. 24, no. 3, pp. 1–22, 2024.
  5. J. Dörpinghaus, J. Binnewitt, S. Winnige, K. Hein, and K. Krüger, “Towards a german labor market ontology: Challenges and applications,” Applied Ontology, vol. 18, no. 4, pp. 343–365, 2023.
  6. D. Martić, A. Fischer, and J. Dörpinghaus, “Extending the german labor market ontology with online data,” in INFORMATIK 2024. Gesellschaft für Informatik eV, 2024, pp. 2019–2030.
  7. J. Dörpinghaus, D. Samray, and R. Helmrich, “Challenges of automated identification of access to education and training in germany,” Information, vol. 14, no. 10, p. 524, 2023.
  8. A. Dutt, M. A. Ismail, and T. Herawan, “A systematic review on educational data mining,” Ieee Access, vol. 5, pp. 15 991–16 005, 2017.
  9. S. K. Mohamad and Z. Tasir, “Educational data mining: A review,” Procedia-Social and Behavioral Sciences, vol. 97, pp. 320–324, 2013.
  10. K. Hein, “Linked labor market data: Towards a novel data housing strategy,” in 2024 19th Conference on Computer Science and Intelligence Systems (FedCSIS). IEEE, 2024, pp. 355–362.
  11. R. M. Chang, R. J. Kauffman, and Y. Kwon, “Understanding the paradigm shift to computational social science in the presence of big data,” Decision support systems, vol. 63, pp. 67–80, 2014.
  12. I. Moalla, A. Nabli, L. Bouzguenda, and M. Hammami, “Data warehouse design approaches from social media: review and comparison,” Social Network Analysis and Mining, vol. 7, no. 1, p. 5, 2017.
  13. C. Romero and S. Ventura, “Educational data mining: A survey from 1995 to 2005,” Expert systems with applications, vol. 33, no. 1, pp. 135–146, 2007.
  14. J. Dörpinghaus and M. Tiemann, “Vocational education and training data in twitter: Making german twitter data interoperable,” Proceedings of the Association for Information Science and Technology, vol. 60, no. 1, pp. 946–948, 2023.
  15. European Commission, “Esco – european skills, competences, qualifications and occupations,” https://esco.ec.europa.eu/, 2023, accessed: 202603-25.
  16. E. M. Sibarani, S. Scerri, C. Morales, S. Auer, and D. Collarana, “Ontology-guided job market demand analysis: a cross-sectional study for the data science field,” in Proceedings of the 13th international conference on semantic systems, 2017, pp. 25–32.
  17. E. Ilkou, H. Abu-Rasheed, M. Tavakoli, S. Hakimov, G. Kismihók, S. Auer, and W. Nejdl, “Educor: An educational and career-oriented recommendation ontology,” in International Semantic Web Conference. Springer, 2021, pp. 546–562.
  18. S. M. Pryima, O. V. Strokan, J. V. Rogushina, A. Y. Gladun, and A. Mozgovenko, “Ontology-based methods and tools for validation of non-formal learning outcomes.” in UkrPROG, 2020, pp. 50–60.
  19. S. Criscuolo, D. Spoladore, A. Mahroo, E. Conti, B. Volta, F. Isgro, P. Arpaia, and M. Sacco, “Towards machine learning-based ontology mapping to bridge o* net and esco skills,” in 2025 IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering (MetroXRAINE). IEEE, 2025, pp. 299–304.