search for


Turnover rate prediction among IT firms according to job satisfaction and dissatisfaction factors: Using topic modeling and machine learning
Journal of the Korean Data & Information Science Society 2021;32:1035-47
Published online September 30, 2021;
© 2021 Korean Data and Information Science Society.

Jinwook Choi1 · Dongwon Shin2 · Hanjun Lee3

1Smart media Service Research Center, Korea University
2Industry Academic Cooperation Foundation, Myongji University
3Department of Management Information Systems, Myongji University
Correspondence to: 1 Research professor, Smart Media Service Research Center, Korea University, Seoul 02841, Korea.
2 Researcher, Industry Academic Cooperation Foundation, Myongji University, Yongin 17058, Korea.
3 Corresponding author: Assistant professor, Department of Management Information Systems, Myongji University, Seoul 03674, Korea. E-mail:
This work was supported by the NationalResearch Foundation of Korea(NRF) grant funded by the Korea government(MSIT) (No. NRF-2019R1G1A1084863).
Received August 27, 2021; Revised September 7, 2021; Accepted September 7, 2021.
This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License ( which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.
Job turnover in the IT industry is a major challenge for companies in technology accumulation, development, and management, and thus, research on this is essential. However, there are still few studies related to turnover and personnel management in the IT field. This study examines the satisfaction and dissatisfaction factors of employees that affect the turnover rate and proposes a model for predicting the turnover rate of IT companies using these factors. To this end, we collected 21,589 reviews from employees of 129 IT companies listed on the domestic stock market on Jobplanet, an online company review site, and conducted topic modeling. Using topics extracted, machine learning-based predictive models for turnover rate were proposed. In addition, this study analyzed the degree of influence of each employee satisfaction and dissatisfaction factor on the turnover rate through variable importance evaluation.
Keywords : Employee satisfaction, firm review, machine learning, topic modeling, turnover rate.