The Use of Large Language Models for the Analysis of Professional Competencies in the Regional Labor Market of the Republic of Belarus

An integrated approach to the analysis of professional competencies in the Belarusian labor market using large language models is presented. A methodology is proposed that includes data collection using web scra­ pers, preliminary processing using a multi-level cleaning system and normalization of text information, classification and analysis of competencies based on interaction with large language models. Detailed skill profiles for each professional group are formed, clusters of complementary competencies are identified, and stable combinations of skills required in various professional fields are determined. High efficiency of using large language models for the tasks of extracting information on competencies from unstructured text descriptions of vacancies is demonstra­ ted with accuracy and completeness indicators exceeding 85%. A methodology for labor market analysis has been developed that integrates traditional big data analysis methods with the capabilities of modern language models.

1. Vankevich А. V., Kalinouskaya I. N. (2024) Using Big Data in Labor Market Analysis: Theoretical Approaches and Methodological Tools. Digital Transformation. 30 (4), 23–32. https://doi.org/10.35596/1729-7648-2024- 30-4-23-32 (in Russian).

2. Vankevich А. V., Kalinouskaya I. N. (2024) Digitalisation and Jobs: The Case of Organisations in the Vitebsk Area of Belarus. Journal of New Economy. 25 (4), 106–126. DOI: 10.29141/2658-5081-2024-25-4-6.

3. Makovskaya N. V. (2020) Modern Features of the Functioning of the Labor Market in Belarus. Mogilev, Mogilev State A. Kuleshov University (in Russian).

4. Vankevich A., Kalinouskaya I. (2021) Better Understanding of the Labour Market Using Big Data. Ekonomia i Prawo. Economics and Law. 20 (3), 677–692. DOI: 10.12775/EiP.2021.040.

5. Kalinouskaya I. N. (2024) Development of Human Resource Management of an Organization in the Context of the Digitalization of the Economy: Methodology, Theory, Practice. Vitebsk, Vitebsk State Technological University (in Russian).

6. Kalinouskaya I. N. (2025) Methodological Support for Human Resource Management of an Organization in Modern Conditions. Vitebsk, Vitebsk State Technological University (in Russian).

7. Barcaroli G., Nurra A., Salamone S. (2015) Internet as Data Source in the Istat Survey on ICT in Enterprises. Austrian Journal of Statistics. 44 (2), 31–43. DOI: 10.17713/ajs.v44i2.53.

8. Bakaev M., Avdeenko T. (2016) Prospects and Challenges in Online Data Mining: Experiences of Three-Year Labour Market Monitoring Project. Lecture Notes in Computer Science. 9714, 15–23. DOI: 10.1007/978-3-319-40973-3_2.

9. Gan C., Zhang Q., Mori T. (2024) Application of LLM Agents in Recruitment: A Novel Framework for Resume Screening. Journal of Information Processing. https://doi.org/10.48550/arXiv.2401.08315.

10. Erdem M. E. (2023) Automatic Resume Screening with Content Matching. 2023 8th International Conference on Computer Science and Engineering (UBMK). 554–558.