The Journal of the Convergence on Culture Technology (문화기술의 융합)

The International Promotion Agency of Culture Technology (국제문화기술진흥원)
권호 표지
DOI QR코드

DOI QR Code

An Analysis of Volunteer Military System Perception Changes with Decreasing Fertility Rates using Deep Learning

딥러닝을 활용한 출산율 감소에 따른 모병제 인식 변화분석

  • 구민구 (청주대학교 소프트웨어융합학부) ;
  • 박지용 (청주대학교 소프트웨어융합학부) ;
  • 이현무 (청주대학교 소프트웨어융합학부) ;
  • 노기섭 (청주대학교 소프트웨어융합학부)
  • Received : 2021.11.22
  • Accepted : 2022.01.08
  • Published : 2022.01.31
Download PDF
⟨ Previous Next ⟩

Abstract

A decrease in fertility rates causes problems such as decrease in the working-age population, and has a significant impact on national policies. Currently, the Republic of Korea has a conscription system that imposes military service on all men over the age of 18. However, the transition to the volunteer miliatry system is emerging as a social issue due to the decrease in the fertility rate. In this paper, news articles and comments searched for through the keyword ' volunteer miliatry system' were collected to analyze the social perception of the volunteer miliatry system from 2018, when the fertility rate dropped to less than 1. Some of the collected comments were labeled, and emotional levels were calculated through deep learning models. Through this study, we found that awareness of recruitment system conversion did not increase as the decrease in the fertility rate, and it was confirmed that people's interest is gradually increasing.

한 나라의 출산율 감소는 생산가능인구가 감소하고, 인구구조 고령화에 따른 저축률 저하로 자본축적이 줄어들어 경제성장이 둔화 등의 문제가 발생한다. 현재 대한민국에서는 만 18세 이상의 모든 남성이 병역의 의무를 부과하고 있는 징병 제도를 시행하고 있다. 하지만 출산율 감소로 인해 모병 제도로의 전환이 사회적 이슈로 불거지고 있다. 본 논문에서는 출산율이 1 미만으로 떨어진 2018년부터 모병제에 대한 사회 인식을 분석하고자 '모병제' 키워드를 통해 검색된 뉴스 기사와 댓글을 수집하였다. 수집된 댓글 중 일부에 대해 레이블링을 진행하였고, 딥러닝 모델을 통해 감성 수준을 산출하였다. 본 연구를 통해 출산율 저하에 따라 모병제 전환에 대한 인식이 많이 증가하지 못한 것을 발견하였으며, 모병제에 대한 사람들의 관심도는 점차 증가하는 추세임을 확인하였다.

Keywords

References

  1. M. Kim, "A Study on the Transition of Military Recruitment System in Korea -Focusing on the Transition of the Taiwan Recruiting System,", Asia Culture Academy of Incorporated Association, Vol 21, pp.883-898, 2021. http://dx.doi.org/10.22143/HSS21.12.1.62
  2. S. Ahn, S. Ryu, and S. Hong, "A sentiment analysis model for small-scale unstructured policy data using transfer learning," Journal of the Korean Data And Information Science Society, Vol. 31, No. 2, pp. 405-414, 2020. https://doi.org/10.7465/jkdi.2020.31.2.405
  3. S. Park and K. Lee, "Effective Korean sentiment labeling method using word embedding and semi-supervised learning," Journal of Korean Institute of Intelligent Systems, Vol. 28, No. 2, pp. 185-191, 2018. https://doi.org/10.5391/JKIIS.2018.28.2.185
  4. S. H. HA and T. H. ROH, "Sentiment Analysis for Public Opinion in the Social Network Service," The journal of the convergence on culture technology, Vol. 6, No. 1, pp. 111-120, Feb. 2020. https://doi.org/10.17703/JCCT.2020.6.1.111
  5. J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, "Bert: Pre-training of deep bidirectional transformers for language understanding," arXiv preprint arXiv:1810.04805, 2018. https://doi.org/10.18653/v1/N19-1423
  6. M. Sahay. "How does IMDb's rating systemwork?" Quora. https://www.quora.com/How-does-IMDbs-rating-system-work (accessed Jun 26, 2021).