1.Occupation classification model based on DistilKoBERT: using the 5th and 6th Korean Working Condition Surveys
Tae-Yeon KIM ; Seong-Uk BAEK ; Myeong-Hun LIM ; Byungyoon YUN ; Domyung PAEK ; Kyung Ehi ZOH ; Kanwoo YOUN ; Yun Keun LEE ; Yangho KIM ; Jungwon KIM ; Eunsuk CHOI ; Mo-Yeol KANG ; YoonHo CHO ; Kyung-Eun LEE ; Juho SIM ; Juyeon OH ; Heejoo PARK ; Jian LEE ; Jong-Uk WON ; Yu-Min LEE ; Jin-Ha YOON
Annals of Occupational and Environmental Medicine 2024;36(1):e19-
Accurate occupation classification is essential in various fields, including policy development and epidemiological studies. This study aims to develop an occupation classification model based on DistilKoBERT. This study used data from the 5th and 6th Korean Working Conditions Surveys conducted in 2017 and 2020, respectively. A total of 99,665 survey participants, who were nationally representative of Korean workers, were included. We used natural language responses regarding their job responsibilities and occupational codes based on the Korean Standard Classification of Occupations (7th version, 3-digit codes). The dataset was randomly split into training and test datasets in a ratio of 7:3. The occupation classification model based on DistilKoBERT was fine-tuned using the training dataset, and the model was evaluated using the test dataset. The accuracy, precision, recall, and F1 score were calculated as evaluation metrics. The final model, which classified 28,996 survey participants in the test dataset into 142 occupational codes, exhibited an accuracy of 84.44%. For the evaluation metrics, the precision, recall, and F1 score of the model, calculated by weighting based on the sample size, were 0.83, 0.84, and 0.83, respectively. The model demonstrated high precision in the classification of service and sales workers yet exhibited low precision in the classification of managers. In addition, it displayed high precision in classifying occupations prominently represented in the training dataset. This study developed an occupation classification system based on DistilKoBERT, which demonstrated reasonable performance. Despite further efforts to enhance the classification accuracy, this automated occupation classification model holds promise for advancing epidemiological studies in the fields of occupational safety and health.
2.Occupation classification model based on DistilKoBERT: using the 5th and 6th Korean Working Condition Surveys
Tae-Yeon KIM ; Seong-Uk BAEK ; Myeong-Hun LIM ; Byungyoon YUN ; Domyung PAEK ; Kyung Ehi ZOH ; Kanwoo YOUN ; Yun Keun LEE ; Yangho KIM ; Jungwon KIM ; Eunsuk CHOI ; Mo-Yeol KANG ; YoonHo CHO ; Kyung-Eun LEE ; Juho SIM ; Juyeon OH ; Heejoo PARK ; Jian LEE ; Jong-Uk WON ; Yu-Min LEE ; Jin-Ha YOON
Annals of Occupational and Environmental Medicine 2024;36(1):e19-
Accurate occupation classification is essential in various fields, including policy development and epidemiological studies. This study aims to develop an occupation classification model based on DistilKoBERT. This study used data from the 5th and 6th Korean Working Conditions Surveys conducted in 2017 and 2020, respectively. A total of 99,665 survey participants, who were nationally representative of Korean workers, were included. We used natural language responses regarding their job responsibilities and occupational codes based on the Korean Standard Classification of Occupations (7th version, 3-digit codes). The dataset was randomly split into training and test datasets in a ratio of 7:3. The occupation classification model based on DistilKoBERT was fine-tuned using the training dataset, and the model was evaluated using the test dataset. The accuracy, precision, recall, and F1 score were calculated as evaluation metrics. The final model, which classified 28,996 survey participants in the test dataset into 142 occupational codes, exhibited an accuracy of 84.44%. For the evaluation metrics, the precision, recall, and F1 score of the model, calculated by weighting based on the sample size, were 0.83, 0.84, and 0.83, respectively. The model demonstrated high precision in the classification of service and sales workers yet exhibited low precision in the classification of managers. In addition, it displayed high precision in classifying occupations prominently represented in the training dataset. This study developed an occupation classification system based on DistilKoBERT, which demonstrated reasonable performance. Despite further efforts to enhance the classification accuracy, this automated occupation classification model holds promise for advancing epidemiological studies in the fields of occupational safety and health.
3.Occupation classification model based on DistilKoBERT: using the 5th and 6th Korean Working Condition Surveys
Tae-Yeon KIM ; Seong-Uk BAEK ; Myeong-Hun LIM ; Byungyoon YUN ; Domyung PAEK ; Kyung Ehi ZOH ; Kanwoo YOUN ; Yun Keun LEE ; Yangho KIM ; Jungwon KIM ; Eunsuk CHOI ; Mo-Yeol KANG ; YoonHo CHO ; Kyung-Eun LEE ; Juho SIM ; Juyeon OH ; Heejoo PARK ; Jian LEE ; Jong-Uk WON ; Yu-Min LEE ; Jin-Ha YOON
Annals of Occupational and Environmental Medicine 2024;36(1):e19-
Accurate occupation classification is essential in various fields, including policy development and epidemiological studies. This study aims to develop an occupation classification model based on DistilKoBERT. This study used data from the 5th and 6th Korean Working Conditions Surveys conducted in 2017 and 2020, respectively. A total of 99,665 survey participants, who were nationally representative of Korean workers, were included. We used natural language responses regarding their job responsibilities and occupational codes based on the Korean Standard Classification of Occupations (7th version, 3-digit codes). The dataset was randomly split into training and test datasets in a ratio of 7:3. The occupation classification model based on DistilKoBERT was fine-tuned using the training dataset, and the model was evaluated using the test dataset. The accuracy, precision, recall, and F1 score were calculated as evaluation metrics. The final model, which classified 28,996 survey participants in the test dataset into 142 occupational codes, exhibited an accuracy of 84.44%. For the evaluation metrics, the precision, recall, and F1 score of the model, calculated by weighting based on the sample size, were 0.83, 0.84, and 0.83, respectively. The model demonstrated high precision in the classification of service and sales workers yet exhibited low precision in the classification of managers. In addition, it displayed high precision in classifying occupations prominently represented in the training dataset. This study developed an occupation classification system based on DistilKoBERT, which demonstrated reasonable performance. Despite further efforts to enhance the classification accuracy, this automated occupation classification model holds promise for advancing epidemiological studies in the fields of occupational safety and health.
4.Related Factors for Not Washing Hands at School among Adolescents
Hyo Jin SAGONG ; Yu-Mi LEE ; Eunsuk CHOI ; Keonyeop KIM
Journal of Agricultural Medicine & Community Health 2022;47(1):14-26
Objectives:
Handwashing is one of the most effective methods to prevent the spread of infectious diseases. This study assessed the related factors and reasons for not practicing handwashing at school among adolescents.
Methods:
We analyzed data collected from 57,303 adolescents who participated in the 15th Korea Youth Risk Behavior Survey 2019.
Results:
The proportions of not washing hands “before meals at school” and “after using the toilet at school” were 15.9% and 4.4%, respectively. The adjusted odds ratio for not washing hands before meals at school was significantly higher in girls (Odds Ratio [OR]=1.52, 95% Confidence Intervals [CI]=1.42-1.63), metropolitan city (OR=1.32, 95% CI=1.11-1.56), city (OR=1.29, 95% CI=1.08-1.54), higher grade, higher academic performance, lower economic status, not handwashing at home (OR=14.36, 95% CI=13.37-15.42), and without annual personal hygiene education (OR=1.41, 95% CI=1.33-1.49). Reasons for not washing hands at school among adolescents who do not wash their hands before meals at school included ‘it is bothersome (52.3%)’, ‘there is no soap or hand sanitizer (13.8%)’, and ‘I do not feel the need (9.5%)’.
Conclusions
Improving handwashing before meals at school among adolescents requires raising awareness of the importance of handwashing before meals and establishing a suitable environment and handwashing-encouraging culture.
5.Survey on Health behaviors, Work-related Health Problems, and Accidents of Live-line Workers
Korean Journal of Occupational Health Nursing 2021;30(1):21-27
Purpose:
The purpose of this study is to identify health behaviors, work-related health problems, and accidents of live-line workers.
Methods:
The questionnaires were administered to 150 live-line workers in 150 workplaces.A total of 150 questionnaires were collected and 130 were used. Data were analyzed for frequency and percentage by SAS Version 9.3.
Results:
In terms of eating habits, 62.3% were in the regular-group. Smoking status was 61.5% of smokers and drinking status was 87.7% in the drinking-group. Body mass index was 42.9% for obesity. Most of the workers had problems with sleep. Among the work-related health problems were 98.2% for “upper limb muscle pain”, 92.7% for “back pain”, and 97.2% for “body fatigue”. Among the work-related accidents were 91.7% for “cutting”, 88.4% for “excessive movement”, and 88.3% for “falling”.
Conclusion
Safety technology development and effective and efficient work equipment must be used to improve the safety and health of live-line workers. In addition, it is necessary to thoroughly supervise and provide active support for the risk factors and health management to the working environment of live-line workers.
6.Occupational Accident Compensation Insurance Coverage and Occupational Accidents for Special-type Delivery Workers
Journal of Korean Academy of Community Health Nursing 2021;32(1):64-72
Purpose:
The purpose of this study is to analyze occupational accident compensation insurance coverage and occupational accidents incidence for special-type delivery workers.
Methods:
The data for occupational accident compensation insurance coverage and occupational accidents from 2012 to 2017 were analyzed through descriptive statistics.
Results:
Rates of occupational accident compensation insurance coverage of special-type delivery workers decreased gradually from 43.4% in 2012 to 28.5% in 2016, and 29.0% in 2017. Rates of occupational illnesses death per ten thousand workers increased gradually from 2.1‱ in 2013 to 3.1‱ in 2016, and 8.6‱ in 2017. All occupational illness deaths were due to cerebro-cardiovascular diseases. Road traffic accidents and slips accounted for the largest proportion of occupational accidents.
Conclusion
Special-type delivery workers have a high risk of industrial accidents, so it is necessary to raise industrial accident insurance coverage and provide professional and systematic occupational safety and health services.
7.The Impacts of Nurses' Working Environment on Health Problems
Korean Journal of Occupational Health Nursing 2020;29(1):1-7
Purpose:
The purpose of this study is to investigate the effect of work environment on health problems of nurses.
Methods:
The subjects of the study were 395 nurses who were wage workers among KWCS (Korean Working Conditions Survey) respondents in 2014. The work environments were measured by the KWCS questionnaire.
Results:
48.5% of the 395 nurses had health problems. The prevalence of musculoskeletal diseases (34.7%) was the highest among all health problems. The ergonomic work environment was significantly related to musculoskeletal disorders, headache and eye strain, and fatigue. In addition, the increase in work-individual interface area was significantly related to fatigue.
Conclusion
The work environment of nurses affects health problems. It is therefore important to develop strategies that improve the health problems of nurses by reducing ergonomic and psycho-social risk factors.
8.The Impacts of Workplace Discrimination and Violence on Depressive Symptoms among Korean Employees
Korean Journal of Occupational Health Nursing 2020;29(2):160-171
Purpose:
This study explored the association between workplace discrimination and violence and depressive symptoms among Korean employees.
Methods:
Data were obtained from the 4th Korean Working Condition Survey of 2014, which included 21,902 Korean employees. Depressive symptoms were measured using the WHO-5 Well-Being Index questionnaire scales.
Results:
A statistically significant relationship between workplace discrimination and workplace violence was found, and these two variables were also associated with depressive symptoms. After adjusting for variables such as sociodemographic characteristics, physical risk, and psychosocial working environment, workplace discrimination (OR=1.22, p<.001) and workplace violence (OR=1.69, p<.001) were both significantly associated with depressive symptoms.
Conclusion
This study indicates that to promote employees’ psychological health, systems and programs to prevent workplace discrimination and violence are needed. Development of these systems and programs should consider employees’ experiences of workplace discrimination and workplace violence, sociodemographic characteristics, physical risk, and psychosocial working environments.
9.Industrial Accident Compensation Insurance Coverage and Industrial Accidents among Concrete Mixer Truck Drivers
Korean Journal of Occupational Health Nursing 2020;29(2):106-113
Purpose:
This study aimed to analyze industrial accident compensation insurance coverage and industrial accidents among concrete mixer truck drivers.
Methods:
Original data on industrial accidents from 2012 to 2017 were analyzed through descriptive statistics.
Results:
Industrial accident compensation insurance coverage was 44.6% in 2017. Most concrete mixer truck drivers were affiliated with small businesses. A total of 61 industrial accidents occurred in 2012, 65 in 2014, and 80 in 2017. The major types of industrial accident were falls, slips, and crushes.
Conclusion
Because concrete mixer truck drivers are at high risk for industrial accidents, industrial accident compensation insurance coverage and industrial accident prevention should be strongly enforced.
10.Factors affecting the Health Problems of Concrete Mixer Truck Driver
Korean Journal of Occupational Health Nursing 2019;28(1):44-52
PURPOSE: This study aimed to identify the level of health problems and the factors that affect health problems for concrete mixer truck divers. METHODS: The questionnaires were administered to 111 drivers in 6 Remicon workplaces located in D city and 7 Remicon workplaces located in K city from September 10 to 28, 2018. A total of 111 questionnaires were collected and 106 were used, excluding 5 incomplete ones. Data were analyzed with frequency, percentage, χ2 test, multiple logistic regression analysis by SPSS/WIN 23.0. RESULTS: The factors affecting subjective health were eating habits, sleeping hours and drinking conditions. The factors that affected chronic diseases were age, eating habits, sleep hours, and drinking conditions. The factors influencing musculoskeletal complaints were work experience, eating habits, and sleep hours. CONCLUSION: The major influencing factors of health problems were eating habits, sleeping hours. This study suggests that it is necessary to run a systematic health care program for the desirable health behaviors in the communities and industrial fields.
Chronic Disease
;
Delivery of Health Care
;
Diagnostic Self Evaluation
;
Drinking
;
Eating
;
Health Behavior
;
Health Status
;
Logistic Models
;
Motor Vehicles
;
Musculoskeletal Diseases

Result Analysis
Print
Save
E-mail