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.

In modern society, depression is serious issue that causes socioeconomic and family burden. To decrease the incidence of depression, risk factors should be identified and managed. Among many risk factors for depression, this study examined socioeconomic risk factors for depression.

We utilized first (2006), second (2008), and third (2010)-wave data from the Korean Longitudinal Study of Aging (KLoSA). Depressive symptom was measured with the 10-item Center for Epidemiological Studies Depression Scale, Short Form (CES-D-10) in the survey in 2008 and 2010. Three risk factors including job security, employment type and monthly income were measured in the survey in 2006. The association between risk factors and depressive symptom was analyzed by Cox proportional-hazard model.

We analyzed data from 1,105 workers and hazard ratios (HRs) for 3 risk factors were significant entirely. In addition, regular worker with high income group is the most vulnerable group of poor job insecurity on depression among male workers (HR: 1.73; 95% confidence interval [CI]: 1.07–2.81). Finally, HRs for 7 groups who had at least 1 risk factor had higher HRs compared to groups who had no risk factors after stratifying 3 risk factors. In the analysis, significantly vulnerable groups were total 5 groups and the group who had highest HR was temporary/daily workers with poor job security (HR: 2.51; 95% CI: 1.36–4.64). The results concerning women, regardless of job type, were non-significant.

This study presented one or more risk factors among poor job security, low income, temporary/daily employment type increase hazard for depressive symptom in 2 or 4 years after the exposure. These results inform policy to screen for and protect against the risk of depression in vulnerable groups.

This study aimed to investigate the decline in quality of life (QOL) by examining changes in the employment status of workers who had completed medical treatment after an industrial accident.

This study utilized the Panel Study of Worker’s Compensation Insurance cohort (published in October 2020) containing a sample survey of 3,294 occupationally injured workers who completed medical care in 2017. We divided this population into four groups according to changes in working status. A multivariate logistic regression model was utilized for evaluating QOL decline by adjusting for the basic characteristics and working environment at the time of accident. Subgroup analysis evaluated whether QOL decline differed according to disability grade and industry group.

The QOL decline in the “maintained employment,” “employed to unemployed,” “remained unemployed,” and “unemployed to employed” groups were 15.3%, 28.1%, 20.2%, and 11.9%, respectively. The “maintained employment” group provided a reference. As a result of adjusting for the socioeconomic status and working environment, the odds ratios (ORs) of QOL decline for the “employed to unemployed” group and the “remained unemployed” group were 2.13 (95% confidence interval [CI], 1.51–3.01) and 1.47 (95% CI, 1.13–1.90), respectively. The “unemployed to employed” group had a non-significant OR of 0.76 (95% CI, 0.54–1.07).

This study revealed that continuous unemployment or unstable employment negatively affected industrially injured workers’ QOL. Policy researchers and relevant ministries should further develop and improve “return to work” programs that could maintain decent employment avenues within the workers’ compensation system.

Recently, there has been a call to improve the holistic welfare of dependent contractors (DCs). Thus, our study examined the relationship between DCs and mental health symptoms and how this relationship was modified by age, sex, and income status of workers.

A total of 27,980 workers from the Fifth Korean Working Conditions Survey are included in our study. The participants who reported having depression or anxiety over the last 12 months are defined those who had mental health symptoms. We performed exact matching for age group and sex, followed by conditional logistic regression with survey weights. Finally, stratified analyses by age, sex and income level were conducted.

DCs were found to be at increased risk of depression/anxiety compared to other workers. The odds ratio (OR) is 1.52 (95% confidence interval [CI]: 1.06–2.17). In the stratified analyses, vulnerable groups were middle-aged (OR [95% CI]: 1.68 [1.10–2.54]), female (OR [95% CI]: 1.85 [1.20–2.84]), and low-income (OR [95% CI]: 3.18 [1.77–5.73]) workers.

Our study's results reinforce those of other studies that show that DCs are at greater risk of experiencing mental health issues than other workers and that and this risk is greater for middle-aged, female, and low-income workers. These results suggest that appropriate policy efforts should be made to improve the psychological well-being of DCs.