Semantic Synergy: Unlocking Policy Insights and Learning Pathways Through Advanced Skill Mapping

Koundouri, Phoebe and Landis, Conrad and Feretzakis, Georgios (2025): Semantic Synergy: Unlocking Policy Insights and Learning Pathways Through Advanced Skill Mapping. Forthcoming in:

Abstract

This research introduces a comprehensive system based on state-of-the-art natural language processing, semantic embedding, and efficient search techniques for retrieving similarities and thus generating actionable insights out of raw textual information. The system works on automatically extracting and aggregating normalized competencies out of multiple documents like policy files and curricula vitae and making strong relationships between recognized competencies, occupation profiles, and related learning courses. To validate its performance, we conducted a multi-tier evaluation that included both explicit and implicit skill references in synthetic and real-world documents. The results showed near-human-level accuracy, with F1 scores exceeding 0.95 for explicit skill detection and above 0.93 for implicit mentions. The system thereby establishes a sound foundation for supporting in-depth collaboration across the AE4RIA network. The methodology involves a multiple-stage pipeline based on extensive preprocessing and data cleaning, semantic embedding and segmentation via SentenceTransformer, and skill extraction using a FAISS-based search method. The extracted skills are associated with occupation frameworks as formulated in 1 the ESCO ontology and learning paths as training programs in the Sustainable Development Goals Academy. Moreover, interactive visualization software, implemented based on Dash and Plotly, presents interactive graphs and tables for real-time exploration and informed decision-making for involved parties in policymaking, training and learning supply, career transitions, and recruitment opportunities. Overall, the system outlined in this paper—supported by rigorous validation—presents promising prospects for better policy-making, human resource improvement, and lifelong learning based on providing structured and actionable insights out of raw, complex textual information.

• Item Type: MPRA Paper
• Language: English
• Keywords: Natural Language Processing, Skill Extraction, FAISS, ESCO, Semantic Embedding, Policy Analysis, Workforce Development, Educational Pathways, Validation
• Subjects: C - Mathematical and Quantitative Methods > C8 - Data Collection and Data Estimation Methodology ; Computer Programs > C88 - Other Computer Software; I - Health, Education, and Welfare > I2 - Education and Research Institutions > I29 - Other; J - Labor and Demographic Economics > J2 - Demand and Supply of Labor > J24 - Human Capital ; Skills ; Occupational Choice ; Labor Productivity; L - Industrial Organization > L8 - Industry Studies: Services > L86 - Information and Internet Services ; Computer Software; O - Economic Development, Innovation, Technological Change, and Growth > O3 - Innovation ; Research and Development ; Technological Change ; Intellectual Property Rights > O33 - Technological Change: Choices and Consequences ; Diffusion Processes

References

[1] Bird, S., Klein, E., Loper, E.: Natural Language Processing with Python. O’Reilly Media Inc., Sebastopol, CA (2009)

[2] Reimers, N., Gurevych, I.: Sentence-bert: Sentence embeddings using siamese bert-networks. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing, pp. 3982–3992 (2019)

[3] Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781 (2013)

[4] Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: Bert: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 4171–4186 (2019)

[5] Johnson, J., Douze, M., J´egou, H.: Billion-scale similarity search with gpus. IEEE Transactions on Big Data 7(3), 535–547 (2019)

[6] Sougandh, T.G., K, S.S., Reddy, N.S., Belwal, M.: Automated resume parsing: A natural language processing approach. In: 2023 7th International Conference on Computation System and Information Technology for Sustainable Solutions (CSITSS), pp. 1–6 (2023). https://doi.org/10.1109/CSITSS60515.2023.10334236

[7] Gangoda, N., Yasantha, K.P., Sewwandi, C., Induvara, N., Thelijjagoda, S., Giguruwa, N.: Resume ranker: Ai-based skill analysis and skill matching system. In: 2024 Sixth International Conference on Intelligent Computing in Data Sciences (ICDS), pp. 1–8 (2024). https://doi.org/10.1109/ICDS62089.2024.10756304

[8] Decorte, J.-J., Verlinden, S., Van Hautte, J., Deleu, J., Develder, C., Demeester, T.: Extreme Multi-Label Skill Extraction Training using Large Language Models. arXiv preprint arXiv:2307.10778. Accepted to the International workshop on AI for Human Resources and Public Employment Services (AI4HR&PES) as part of ECML-PKDD 2023 (2023). https://doi.org/10.48550/arXiv.2307.10778

[9] Hunkenschroer, A.L., Luetge, C.: Ethics of AI-enabled recruiting and selection: A review and research agenda. Journal of Business Ethics 178(4), 977–1007 (2022) https://doi.org/10.1007/s10551-022-05049-6 21

[10] European Commission: ESCO – European Skills, Competences, Qualifications and Occupations. https://ec.europa.eu/esco/portal/home. Available at https: //ec.europa.eu/esco/portal/home (2021)

[11] Koundouri, P., Landis, C., Toli, E., Papanikolaou, K., Slamari, M., Epicoco, G., Hui, C., Arnold, R., Moccia, S.: Twin Skills for the Twin Transition: Defining Green & Digital Skills and Jobs. December 2023, AE4RIA, ATHENA Research Centre, Sustainable Development Unit. Available at https://ae4ria.org/wp-con tent/uploads/2023/12/white-paper-eu-digital-skills-gap-2023-2-1.pdf (2023)

[12] Koundouri, P., Landis, C., Koltsida, P., Papadaki, L., Toli, E.: Preparing the maritime workforce for the twin transition: Skill priorities and educational needs. DEOS Working Papers, 2417, Athens University of Economics and Business (2024)

[13] Koundouri, P., Aslanidis, P.-S., Dellis, K., Plataniotis, A., Feretzakis, G.: Mapping human security strategies to sustainable development goals: a machine learning approach. Discover Sustainability 6, 96 (2025). Available at https://doi.org/10.1 007/s43621-025-00883-w

[14] Sustainable Development Solutions Network: Sustainable Development Solutions Network (SDSN) Courses. https://sdgacademy.org/courses/. Available at https: //sdgacademy.org/courses/ (2020)

[15] Douze, M., Guzhva, A., Deng, C., Johnson, J., Szilvasy, G., Mazar´e, P.-E., Lomeli, M., Hosseini, L., J´egou, H.: The faiss library (2024) arXiv:2401.08281 [cs.LG]

[16] Honnibal, M., Montani, I., Van Landeghem, S., Boyd, A.: spaCy: Industrialstrength Natural Language Processing in Python. https://doi.org/10.5281/zeno do.1212303 . https://spacy.io

[17] Bolukbasi, T., Chang, K.-W., Zou, J.Y., Saligrama, V., Kalai, A.T.: Man is to computer programmer as woman is to homemaker? debiasing word embeddings. Advances in Neural Information Processing Systems 29, 4349–4357 (2016)

[18] Plotly Technologies Inc.: Dash: A Web Application Framework for Your Data. https://dash.plotly.com/ 22