A comparative analysis of job satisfaction prediction models using machine learning: a mixed-method approach
| Date | 14 August 2024 |
| Pages | 41-60 |
| DOI | https://doi.org/10.1108/DTA-10-2023-0697 |
| Published date | 14 August 2024 |
| Author | Jaekyeong Kim,Pil-Sik Chang,Sung-Byung Yang,Ilyoung Choi,Byunghyun Lee |
A comparative analysis of job
satisfaction prediction models
using machine learning:
a mixed-method approach
Jaekyeong Kim
School of Management, Kyung Hee University, Seoul, Republic of Korea and
Department of Big Data Analytics, Kyung Hee University, Seoul, Republic of Korea
Pil-Sik Chang
Department of Business Administration, Graduate School, Kyung Hee University,
Seoul, Republic of Korea
Sung-Byung Yang
School of Management, Kyung Hee University, Seoul, Republic of Korea
Ilyoung Choi
Division of Business Administration, Seo Kyeong University,
Seoul, Republic of Korea, and
Byunghyun Lee
Department of Big Data Analytics, Graduate School, Kyung Hee University,
Seoul, Republic of Korea
Abstract
Purpose –Because the food service industry is more dependent on customer contact and human resources than
other industries, it is crucial to understand the factors influencing employee job satisfaction to ensure that employees
provide satisfactory service to customers. However, few studies have incorporated employee reviews of jobportals
into their research. Many job seekers tend to trust company reviews posted by employees on job portals based on the
information provided by the company itself. Thus, this study utilized company reviews and job satisfaction ratings
from employees in the food service industry on a job portal site, Job Planet, to conduct mixed-method research.
Design/methodology/approach–For qualitative research, we applied the Latent Dirichlet Allocation (LDA)
model to food service industry company reviews to identify 10 job satisfaction factors considered important by
employees. For quantitative research, four algorithms were used to predict job satisfaction ratings: regression
tree, multilayer perceptron (MLP), random forest and XGBoost. Thus, we generated predictor variables for six
cases using the probability values of topics and job satisfaction ratings on a five-point scale through LDA and
used them to build prediction algorithms.
Findings –The analysis showed that algorithm accuracy performed differently in each of the six cases, and
overall, factors such as work-life balance and work environment have a significant impact on predicting job
satisfaction ratings.
Originality/value –This study is significant because its methodology and results suggest a new approach
based on data analysis in the field of human resources, which can contribute to the operationand planning of
corporate human resources management in the future.
Keywords Job satisfaction, Topic modeling, Mixed-method research, Job portal site, Job review,
Prediction algorithm
Paper type Research paper
1. Introduction
The annual revenue of Korea’s food service sector is approximately KRW 74 trillion, with its
share in the industry growing continuously (Im et al., 2021). Becausethe food service industry is
highlydependent on customercontact and humanresources, humanservices, suchas customer
services, are relatively more important than in other industries (Kim, 2014). Thus, food service
Data
Technologies and
Applications
41
The current issue and full text archive of this journal is available on Emerald Insight at:
https://www.emerald.com/insight/2514-9288.htm
Received 19 October 2023
Revised 22 April 2024
Accepted 13 May 2024
Data Technologies and
Applications
Vol. 59 No. 1, 2025
pp. 41-60
© Emerald Publishing Limited
2514-9288
DOI 10.1108/DTA-10-2023-0697
companies devote considerable managerial efforts to providing satisfactory services to
customers.It is also important to improve servicequality, and customer satisfactionis the role
employeesplay in providing services (Karatepe and Sokmen, 2006). However,when employees
aredissatisfiedwith their jobs,it is difficult forthem to providesatisfactoryservice to customers,
which can lead to negative consequences such as voluntaryturnover (Brotheridge and Lee,
2003). In other words, it is crucial to identify the fac tors that influence employee job satisfaction
to ensure that employees provide satisfactory services to customers (Bellet et al., 2023).
Numerous studies have analyzed the factors thatsignificantly affectemployee job satisfaction
(Krekel et al.,2019;Pereraan d John, 2020;Wang et al., 2020), mainlyusing quantitativeresearch
methodologies, suchas surveys. The advantageof the survey methodis that the informationis
directly collected from research participants, allowing for detailed content andprecise causal
analyses (Huang and Huang, 2015). Therefore, it is still widely used in variousareas, such as
market research, consumer behavior, advertising effectivenessand brand awareness analysis.
Recently,mixed-methodresearch has beenwidely used to understand employeejob satisfaction
by combiningquantitative methods, such as surveys, with qualitative research methods, such
as open-ended surveys and interviews (Cain et al., 2020;DiPietro et al., 2020;Mulyawan et al.,
2021). Quantitative research methods summarize and generalize phenomena easily; however,
they do not provide an in-depth understanding. Qualitative research methods provide rich
descriptions; however, they are limited in their ability to observe and generalize specific
phenomena (Babbie, 2020). Thus, mixed-method research has the advantages of both
quantitative and qualitative research methodologies to gain a deeper understanding of
phenomena (Creswell et al.,2011). However, previous human resource studies using mixed-
method research, have mainly combined surveys and interviews to analyze the factors that
affect job satisfaction. Only a few mixed-method studies have collected and used employee
reviews of companies on online job portals. It should also be noted that, nowadays, job seekers
tend to trust reviews written by people who have worked for a company more than the
information providedby companies (Lakin, 2015). As these reviewscan be a valuable sourceof
information not only for job seekers but also for companies developing human resource (HR)
strategies, it is important to collect and analyze employee reviews (Kim, 2010). Additionally,
company reviews include job details, and it is easy to collect a large amount of data from online
job portals. Therefore, we conducted a mixed-method research by utilizing the reviews and
ratings created by employees of the food service industry. In this study, we collected positive
and negativereviews and jobsatisfaction ratingson a 5-point scale,submitted by employeesin
the food service industry on Job Planet, one of Korea’s leading job portals and then applied
Latent Dirichlet Allocation (LDA) to the reviews to conduct a qualitative study to explore the
factors of job satisfaction among food service industry employees. Thereafter, we built a job
satisfaction prediction algorithm using the probability values of topics and job satisfaction
ratingson a 5-point scale obtainedthrough LDA and conducteda quantitativestudy to identify
the factors with a significant impact on job satisfaction prediction. In other words, this study
used mixed-method research, whichcombines qualitativeand quantitativemethods, to analyze
the job satisfactionof employees in the foodservice industry indetail. By presentingimportant
factors related to the job satisfaction of employees in the food service industry, this study can
provide empirical data for the establishment of human resource policies and efficient
management of employee job satisfaction in the future. The specific research questions are as
follows.
RQ1. What are the job satisfaction factors inherent in reviews?
RQ2. What algorithm accurately predicts job satisfaction?
RQ3. Which job satisfaction factors have the most significant impact on predictive
performance?
DTA
59,1
42
Get this document and AI-powered insights with a free trial of vLex and Vincent AI
Get Started for FreeStart Your Free Trial of vLex and Vincent AI, Your Precision-Engineered Legal Assistant
-
Access comprehensive legal content with no limitations across vLex's unparalleled global legal database
-
Build stronger arguments with verified citations and CERT citator that tracks case history and precedential strength
-
Transform your legal research from hours to minutes with Vincent AI's intelligent search and analysis capabilities
-
Elevate your practice by focusing your expertise where it matters most while Vincent handles the heavy lifting
Start Your Free Trial of vLex and Vincent AI, Your Precision-Engineered Legal Assistant
-
Access comprehensive legal content with no limitations across vLex's unparalleled global legal database
-
Build stronger arguments with verified citations and CERT citator that tracks case history and precedential strength
-
Transform your legal research from hours to minutes with Vincent AI's intelligent search and analysis capabilities
-
Elevate your practice by focusing your expertise where it matters most while Vincent handles the heavy lifting
Start Your Free Trial of vLex and Vincent AI, Your Precision-Engineered Legal Assistant
-
Access comprehensive legal content with no limitations across vLex's unparalleled global legal database
-
Build stronger arguments with verified citations and CERT citator that tracks case history and precedential strength
-
Transform your legal research from hours to minutes with Vincent AI's intelligent search and analysis capabilities
-
Elevate your practice by focusing your expertise where it matters most while Vincent handles the heavy lifting
Start Your Free Trial of vLex and Vincent AI, Your Precision-Engineered Legal Assistant
-
Access comprehensive legal content with no limitations across vLex's unparalleled global legal database
-
Build stronger arguments with verified citations and CERT citator that tracks case history and precedential strength
-
Transform your legal research from hours to minutes with Vincent AI's intelligent search and analysis capabilities
-
Elevate your practice by focusing your expertise where it matters most while Vincent handles the heavy lifting
Start Your Free Trial of vLex and Vincent AI, Your Precision-Engineered Legal Assistant
-
Access comprehensive legal content with no limitations across vLex's unparalleled global legal database
-
Build stronger arguments with verified citations and CERT citator that tracks case history and precedential strength
-
Transform your legal research from hours to minutes with Vincent AI's intelligent search and analysis capabilities
-
Elevate your practice by focusing your expertise where it matters most while Vincent handles the heavy lifting