• Journal of the Korea Society of Computer and Information
• /
• v.28 no.4
• /
• pp.21-29
• /
• 2023

In this paper, we propose an AI-based system for automatically classifying industry and occupation codes in the population census. The accurate classification of industry and occupation codes is crucial for informing policy decisions, allocating resources, and conducting research. However, this task has traditionally been performed by human coders, which is time-consuming, resource-intensive, and prone to errors. Our system represents a significant improvement over the existing rule-based system used by the statistics agency, which relies on user-entered data for code classification. In this paper, we trained and evaluated several models, and developed an ensemble model that achieved an 86.76% match accuracy in industry and 81.84% in occupation, outperforming the best individual model. Additionally, we propose process improvement work based on the classification probability results of the model. Our proposed method utilizes an ensemble model that combines transfer learning techniques with pre-trained models. In this paper, we demonstrate the potential for AI-based systems to improve the accuracy and efficiency of population census data classification. By automating this process with AI, we can achieve more accurate and consistent results while reducing the workload on agency staff.

• Journal of the Korea Convergence Society
• /
• v.12 no.4
• /
• pp.23-30
• /
• 2021

An Automated Industry and Occupation Coding System assigns statistical classification code to the enormous amount of natural language data collected from people who write about their industry and occupation. Unlike previous studies that applied information retrieval, we propose a system that does not need an index database and gives proper code regardless of the level of classification. Also, we show our model, which utilized KoBERT that achieves high performance in natural language downstream tasks with deep learning, outperforms baseline. Our method achieves 95.65%, 91.51%, and 97.66% in Occupation/Industry Code Classification of Population and Housing Census, and Industry Code Classification of Census on Basic Characteristics of Establishments. Moreover, we also demonstrate future improvements through error analysis in the respect of data and modeling.

• Korea journal of population studies
• /
• v.29 no.3
• /
• pp.1-27
• /
• 2006

Labor market participation and occupational status for workers majoring in(natural) science and engineering are estimated and compared with workers of other majors at three levels: employment, prestigious occupations, and good occupations. For this, we utilized 2% Public Use Sample of 2000 Korea Census. The results of two-stage probit models, which adjust sample selection bias, do not support the argument that graduates of science and engineering majors are relatively disadvantaged. Workers of engineering majors are more likely to have 'good occupations' at their early job careers, but their advantages fade away quickly as they are aging. Especially at their 40s, their probability of having 'good occupations' start to be likely lower than workers of social science majors. This may be due to low human capital accumulation rates at work places along with quickly outdated skills which are acquired in colleges.

• Journal of the Korean Regional Science Association
• /
• v.32 no.1
• /
• pp.105-122
• /
• 2016

Recently people are starting to pay attention to the vacant house. Vacant house across the country are expected to be a Million. Ministry of Land, Transport and Maritime Affairs has created a new legal provisions regarding maintenance to Vacant on the Construction Law. But Vacant house information systems in government are not available Other countries to clarify the role each entity to manage these Vacant and manages the Vacant. The national government has made the operating budget support program for the Vacant management. The local government has made legislation of self-government to create a DB for the Vacant management. A non-profit corporation is developing a program operated by the Vacant, and the Vacant intermediaries to consumers. Therefore, our country is also to expand the national budget for the Vacant administration, local governments should establish a comprehensive management system for managing and providing Vacant house research and DB.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.33 no.6
• /
• pp.2503-2508
• /
• 2013

Single-person households in the Seoul Metropolitan Area have increased sharply during recent 20-30 years. Despite of decreasing in the total population, the number of single-person household is predicted to increase continuously. However, the effect of single-person household growth on the domestic transport sector has not been studied concretely. In this study, the differences on trip generation characteristics by household size and attributes were figured out by analyzing Seoul Metropolitan Area Household Travel Behavior Survey (SMA-HTBS). Firstly, trip generation rates (trips/day/person) were produced by household attribute, household member attribute and trip attribute based on SMA-HTBS. Secondly, trip generation rate of single-person household and that of multi-person (2 or more) household were compared by significance test. It was found that trips generation characteristics of single-person household is quite different from those of multi-person household by housing type, residential type, living area, and transport mode. The result of this paper is expected to contribute developing more sophisticated trip generation model and transport policy reflecting trip generation characteristics of single-person household.

• Journal of the Korean association of regional geographers
• /
• v.13 no.6
• /
• pp.651-673
• /
• 2007

In the studies on residential move, there has been tendency of dichotomy where short distance moves are largely caused by housing to adjust to changes in households while long distance moves are induced by shift in labor market. However, some empirical studies have proven that residential move is so complex process that the simple dichotomy should be elaborated. In this sense, the present study seeks to identify compounded course of residential move in Korea. In determining migration history, families with younger householders, renters, householders with higher educational attainment and smaller households show a higher probability to move. In case of mobility, women were more prone to move compared to man. Women compared to man, older age augmented the probability to own a house after migration. Families with householders following an occupation of sales and technical service showed lowest tendency to own houses while it marked the highest in the group of professionals. Higher land price of a region was negatively related to owning houses after migration. The present study revealed that factors in macro level as well as micro level significantly affect the move of individuals with varying effects in accordance with migration history.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.11
• /
• pp.5508-5513
• /
• 2013

This paper seeks to empirically analyze the effect of WLFP on fertility in Korea using the 1985~2010 Korean Population and Housing Census 1% Sample data. The results show that except in year 1985(+0.336) WLFP had a significant negative effect on fertility rates in years 1990, 2000, 2005, 2010. The size of the negative effect increases from 1990(-0.611) to 2005(-2.273). In 2010(-0.793), however, the negative effect considerably decreases when compared with the 2005 result. This alleviation is partially due to policies that have promoted compatibility between work and family life. Policy makers should therefore focus on expansion of policies for the compatibility of work and family, and give more attention to increasing take-up rate for the current policies.

• The Journal of the Korea Contents Association
• /
• v.15 no.10
• /
• pp.570-586
• /
• 2015

The purpose of this study is to analyze the effects of middle-aged retirement planning on individual's quality of life and overall satisfaction, and moderating effects of social and psychological sense of crisis, and the differences of measured variables in the demographic characteristics. Retirement planning that may be the most important factor in the country's social costs is aimed to provide a basis for fixing the interest in advance of retirement planning training and retirement. The subjects are workers who live in the Seoul metropolitan area and Gyonggi-do. Total sample size is 350, then 335 samples were collected on the data. The results of this study can be summarized as follows. First, house ownership and education level among demographic variables affects satisfaction of their life. People who do not own a house shows higher satisfaction, and higher education level affects satisfaction positively. Second, satisfaction is affected by transition to rest negatively, on the other hand, it is affected by expect of new beginning positively. Besides, No moderating effect of social and psychological crisis showed that negative life evaluation role to the independent variables. Third, cognitive information is affected by transition to rest and imposed disruption positively. Besides, job dissatisfaction adjusts between them. Fourth, improvement of life quality is not affected by expect of the retirement planning. On the other hand, there is not moderating effects of social and psychological sense of crisis.

• The Journal of Korean Association of Computer Education
• /
• v.7 no.4
• /
• pp.51-60
• /
• 2004

This paper proposes an automated coding system of Korean standard industry/occupation for census which reduces a lot of cost and labor for manual coding. The proposed system converts natural language responses on survey questionnaires into corresponding numeric codes using information retrieval techniques and document classification algorithm. The system was experimented with 46,762 industry records and occupation 36,286 records using 10-fold cross -validation evaluation method. As experimental results, the system show 87.08% and 66.08% production rates when classifying industry records into level 2 and level 5 codes respectively. The system shows slightly lower performances on occupation code classification. We expect that the system is enough to be used as a semi-automate coding system which can minimize manual coding task or as a verification tool for manual coding results though it has much room to be improved as an automated coding system.

• Korea journal of population studies
• /
• v.32 no.1
• /
• pp.93-111
• /
• 2009

This study aims to find out changes of marital status and average marital life expectancy in Korea according to educational attainment. The study produces Korean marriage life table to accomplish the goal of study by introducing Wolfbein-Wool style working life table. Specific data utilized in this study are collected from the Population & Housing Census 2005 and Death Census 2005. Educational attainment is divided into four categories to accommodate to this study: elementary school course and lower, middle school course, high school course, college course and higher. Marriage rate, divorce rate, widowhood rate and death rate according to educational attainment are used as basicdata to analyze marital life expectancy. The results of this study are as follows: 1. As subjects age is younger, the average marital life expectancy of the highly educated tends to be higher. The disparity of average marital life expectancy according to educational attainment is apt to become narrow as subjects age is older. However, the gap between people who graduated from middle school and high school in older age group does not distinctive. 2. Males marital life expectancy is higher than females controlling for their educational attainment. 3. Males live with their wife for most of their lives but females live alone more than 10 years in every single educational categories. Based on the above, this study concludes that the average marital life expectancy is differentiated among age and sex according to educational attainment. Marital rate tends to be higher as educational level is higher. Divorce rate is lower in the highlyeducated group as their age is younger but this is apt to reverse as age is older. Furthermore, bereavement rate shows division according to educational attainmentsince one tends to marry other who has similar level of education with him or her. Therefore, educational attainment acts as an significant factor in Korean average life expectancy.