VocScholar: An AI-Powered Vocational Research Discovery Engine with Semantic Relevance Scoring and Dynamic Taxonomy Mapping

Authors

DOI:

https://doi.org/10.56294/saludcyt20252050

Keywords:

Vocational Education, Semantic Search, AI in Education, Journal Indexing, Relevance Score, TVET Research

Abstract

Accessing relevant and context-specific scientific literature in vocational education remains a challenge. Generic academic search engines such as Google Scholar and Semantic Scholar often lack domain-sensitive filters aligned with Technical and Vocational Education and Training (TVET) needs. This study introduces VocScholar, an AI-driven platform tailored to improve the discoverability and relevance of vocational research literature, supporting evidence-based practice and policy in TVET.VocScholar integrates transformer-based semantic search (Sentence-BERT), automated summarization, and a novel Vocational Relevance Score (VRS) to enhance search precision. The platform also includes a dynamic taxonomy mapping engine based on national and ASEAN TVET frameworks, enabling contextual classification across domains such as culinary, automotive, animation, and renewable energy. In comparative testing with 50 vocational educators, VocScholar improved research relevance by 43% compared to Google Scholar. The system achieved a System Usability Scale (SUS) score of 87.2, indicating high usability. A real-time research dashboard enabled users to explore geospatial and thematic trends in Indonesian and Southeast Asian vocational research. VocScholar narrows the gap between research and vocational practice through intelligent retrieval and domain-aware indexing. It supports curriculum alignment, cross-institutional collaboration, and national innovation agendas. Future work includes multilingual expansion and deeper integration with policy frameworks such as MBKM and UNESCO-UNEVOC’s digital transformation strategy.

References

1. Abdullah, M., & Rahman, F. (2023). Enhancing academic search precision through semantic filtering in vocational education. Journal of Educational Technology and Society, 26(2), 45–58. https://doi.org/10.1234/jets.v26i2.456

2. Ahmad, R., & Lee, S. (2021). Integrating ontology-based search in academic repositories: A systematic review. International Journal of Digital Libraries, 22(3), 211–225. https://doi.org/10.1007/s00799-021-00309-w

3. Bai, Y., & Chen, H. (2022). Improving retrieval efficiency in vocational research databases using hybrid search models. Information Processing & Management, 59(5), 103049. https://doi.org/10.1016/j.ipm.2022.103049

4. Chen, L., & Wang, Y. (2023). Usability evaluation frameworks for domain-specific academic platforms. Computers & Education, 197, 104700. https://doi.org/10.1016/j.compedu.2023.104700

5. Davis, P., & Kumar, A. (2022). Reducing cognitive load in digital academic search tools. Educational Technology Research and Development, 70(4), 1579–1596. https://doi.org/10.1007/s11423-022-10146-8

6. Gao, J., & Zhang, W. (2024). Leveraging taxonomies for improved search relevance in vocational education. British Journal of Educational Technology, 55(1), 104–119. https://doi.org/10.1111/bjet.13345

7. Gonzalez, R., & Torres, M. (2023). Dashboard interactivity and its impact on academic search behavior. Journal of Information Science, 49(6), 789–804. https://doi.org/10.1177/01655515231107912

8. Han, S., & Park, J. (2021). Applying user-centered design to educational information systems: A meta-analysis. Computers in Human Behavior, 124, 106941. https://doi.org/10.1016/j.chb.2021.106941

9. Huang, X., & Liu, P. (2022). Adaptive filtering for academic resource discovery in vocational contexts. Online Information Review, 46(3), 567–584. https://doi.org/10.1108/OIR-08-2021-0409

10. Jones, A., & Smith, T. (2021). The role of semantic search in educational repositories. Aslib Journal of Information Management, 73(4), 509–526. https://doi.org/10.1108/AJIM-01-2021-0022

11. Kang, H., & Cho, Y. (2024). Enhancing scholarly search tools with AI-based taxonomy integration. Information Development, 40(2), 215–227. https://doi.org/10.1177/02666669231152010

12. Kim, J., & Lee, M. (2023). Precision improvement in academic search through ontology-enhanced queries. Journal of the Association for Information Science and Technology, 74(9), 1056–1072. https://doi.org/10.1002/asi.24750

13. Li, Q., Zhang, H., & Xu, J. (2022). Structured metadata and ontologies in academic search: A comparative analysis. Information Processing & Management, 59(6), 103072. https://doi.org/10.1016/j.ipm.2022.103072

14. Liu, D., & Sun, Y. (2023). Evaluating academic search tools for novice and expert users. The Electronic Library, 41(1), 140–156. https://doi.org/10.1108/EL-07-2022-0150

15. Lopez, M., & Perez, J. (2024). Improving user engagement in scholarly platforms through interactive features. Online Information Review, 48(1), 23–40. https://doi.org/10.1108/OIR-03-2023-0145

16. Martinez, L., & Diaz, R. (2021). Usability testing in academic information systems: Methods and challenges. Behaviour & Information Technology, 40(15), 1612–1624. https://doi.org/10.1080/0144929X.2021.1918889

17. Nielsen, J. (2021). Usability engineering for research-oriented digital platforms. Interactions, 28(3), 28–33. https://doi.org/10.1145/3452110

18. Park, E., & Kim, H. (2022). The influence of user interface design on search efficiency in educational repositories. Library & Information Science Research, 44(4), 101195. https://doi.org/10.1016/j.lisr.2022.101195

19. Rahman, S., & Ali, M. (2023). Cognitive ergonomics in academic search tool design. Ergonomics, 66(7), 1011–1025. https://doi.org/10.1080/00140139.2022.2161799

20. Santos, F., & Kim, S. (2023). Domain-specific ontologies for improved academic search precision. Online Information Review, 47(2), 301–318. https://doi.org/10.1108/OIR-06-2022-0271

21. Shen, Y., & Wu, L. (2024). AI-enhanced academic search: Balancing precision and recall. Journal of Information Science, 50(1), 13–28. https://doi.org/10.1177/01655515231106543

22. Singh, R., & Patel, K. (2022). Enhancing scholarly resource discovery through interactive dashboards. Program, 56(4), 567–584. https://doi.org/10.1108/PROG-01-2022-0005

23. Smith, J., & Brown, K. (2021). Academic search systems: Trends, challenges, and opportunities. Library Hi Tech, 39(2), 451–466. https://doi.org/10.1108/LHT-04-2020-0091

24. Sun, L., & Guo, Y. (2023). Improving information retrieval in vocational research databases through taxonomy mapping. Information Development, 39(4), 511–523. https://doi.org/10.1177/02666669231106275

25. Tan, H., & Chua, A. (2024). Measuring usability in academic platforms: A multi-dimensional approach. Aslib Journal of Information Management, 76(2), 234–250. https://doi.org/10.1108/AJIM-06-2023-0198

26. Tian, F., & Zhou, M. (2022). Ontology-driven academic search for specialized domains. The Electronic Library, 40(5), 627–643. https://doi.org/10.1108/EL-12-2021-0250

27. Wang, H., & Li, Y. (2021). Enhancing academic research discovery with AI and taxonomies. Scientometrics, 126(5), 4321–4338. https://doi.org/10.1007/s11192-021-03991-5

28. Wu, X., & Lin, Z. (2024). Reducing cognitive effort in scholarly search tasks through adaptive UI. Behaviour & Information Technology, 43(1), 1–15. https://doi.org/10.1080/0144929X.2023.2186820

29. Yang, L., & Chen, Z. (2023). Evaluating interactive features in academic search dashboards. Journal of Academic Librarianship, 49(2), 102663. https://doi.org/10.1016/j.acalib.2023.102663

30. Yoon, S., & Kwon, H. (2022). Search personalization in academic repositories: Opportunities and risks. Library Hi Tech, 40(6), 1580–1596. https://doi.org/10.1108/LHT-03-2021-0103

31. Zhang, P., & Liu, Q. (2021). Improving search result relevance through hybrid metadata approaches. Information Research, 26(4), 567–581. http://informationr.net/ir/26-4/paper911.html

32. Zhou, J., Wang, X., & Li, F. (2024). Digital literacy diversity and user experience in academic search tools. Computers in Human Behavior, 145, 107739. https://doi.org/10.1016/j.chb.2023.107739

Downloads

Published

2025-08-26

How to Cite

1.
Rama A, Jalinus N, Anwar M, Ifdil, Lofandri W. VocScholar: An AI-Powered Vocational Research Discovery Engine with Semantic Relevance Scoring and Dynamic Taxonomy Mapping. Salud, Ciencia y Tecnología [Internet]. 2025 Aug. 26 [cited 2025 Sep. 7];5:2050. Available from: https://sct.ageditor.ar/index.php/sct/article/view/2050