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.