350 rub
Journal Neurocomputers №6 for 2024 г.
Article in number:
Using machine learning to analyze employee loyalty based on textual reviews
Type of article: scientific article
DOI: 10.18127/j19998554-202406-10
UDC: 519.254+519.673+004.942
Authors:

G.N. Zholobova1, E.D. Sinitsyna2

1,2 Financial University under the Government of the Russian Federation (Moscow, Russia)

1 gnzholobova@fa.ru, 2 katya_sinitsyna@mail.ru

Abstract:

In the face of growing competition and a rapidly changing market, a company's success largely depends on the motivation and loyalty of its employees. Traditional methods of assessing loyalty, based on surveys and questionnaires, do not always accurately reflect the emotional state of the personnel. The use of machine learning methods and natural language processing (NLP) opens up new opportunities for analyzing employee reviews, which can significantly improve the understanding of the corporate climate. The goal is to assess the level of loyalty of employees in an IT company by applying machine learning and NLP methods using BERT, DistilBERT, and RoBERTa models. The study showed that BERT, DistilBERT, and RoBERTa models can effectively classify employee reviews by emotional tone, with accuracy up to 78% for the RoBERTa model. The practical significance lies in the application of machine learning models for analyzing employee textual reviews, which helps identify key factors influencing corporate culture and moral climate in the company. This contributes to the development of well-founded personnel management strategies and improvement of employee satisfaction. Implementing such methods in company HR departments can help automate the collection and analysis of reviews, which, in turn, enhances employee loyalty and overall organizational effectiveness.

Pages: 76-85
For citation

Zholobova G.N., Sinitsyna E.D. Using machine learning to analyze employee loyalty based on textual reviews. Neurocomputers. 2024. V. 26. № 6. Р. 76-85. DOI: https://doi.org/10.18127/j19998554-202406-10 (In Russian)

References
  1. Rezapova D.B. Employee engagement in work. University management: practice and analysis. 2016. № 1(101). P. 73–75. (In Russian)
  2. Allen N.J., Meyer J.P. The measurement and antecedents of affective, continuance and normative commitment to the organization. Journal of Occupational Psychology. 1990. V. 63. № 1. P. 1–18. DOI 10.1111/j.2044-8325.1990.tb00506.x.
  3. Gordeeva E.V., Kochkarov R.A., Rylov A.A. Analysis of the text theme recognition problem using machine learning. Neurocomputers. 2023. V. 25. № 4. Р. 7–15. DOI 10.18127/j19998554-202304-02. (In Russian)
  4. Job reviews. Employee reviews of the employer. [Electronic resource] – Access mode: https://dreamjob.ru/, date of reference 25.04.2024. (In Russian)
  5. Bakhshi A., Sharma A.D., Kumar K. Organizational Commitment as predictor of Organizational Citizenship Behavior. [Electronic resource] – Access mode: https://core.ac.uk/download/pdf/234624049.pdf, date of reference 25.04.2024.
  6. Basic emotions. The Center for Medical Prevention and Rehabilitation of the Kaliningrad region. [Electronic resource] – Access mode: https://clck.ru/39Gs2k, date of reference 25.04.2024. (In Russian)
  7. Onuchin A. Employee engagement: from measurement to management. [Electronic resource] – Access mode: https://www.ecop-sy.ru/insights/vovlechennost-personala-ot-izmereniya-k-upravleniyu/, date of reference 25.04.2024. (In Russian)
  8. Handani N.D., Williady A., Kim H.S. An Analysis of Customer Textual Reviews and Satisfaction at Luxury Hotels in Singapore’s Marina Bay Area (SG-Clean-Certified Hotels). Sustainability. 2022. V. 14. № 15. P. 9382. DOI 10.3390/su14159382.
  9. The Kincentric Accomplice Engagement Model (Aon Hewitt). [Electronic resource] – Achievement mode: https://axes.ru/articles/model-vovlechennosti-sotrudnikov-aon-hewitt/, date of reference 25.04.2024. (In Russian)
  10. Bunina E.V. Innovative methods of personnel management. Bulletin of the Magistracy. 2019. № 11-3(98). P. 59–61. (In Russian)
  11. Alzate M., Arce-Urriza M., Cebollada Ja. Mining the text of online consumer reviews to analyze brand image and brand positioning. Journal of Retailing and Consumer Services. 2022. V. 67. P. 102989. DOI 10.1016/j.jretconser.2022.102989.
  12. Young T., Hazarika D., Poria S., Cambria E. Recent Trends in Deep Learning Based Natural Language Processing. IEEE Computational Intelligence Magazine. 2018. V. 13. № 3. P. 55–75. DOI 10.1109/MCI.2018.2840738.
  13. Alshamari M.A. Evaluating User Satisfaction Using Deep-Learning-Based Sentiment Analysis for Social Media Data in Saudi Arabia’s Telecommunication Sector. Computers. 2023. V. 12. № 9. P. 170. DOI 10.3390/computers12090170.
Date of receipt: 30.06.2024
Approved after review: 26.07.2024
Accepted for publication: 26.11.2024