Journal of Internet of Things and Convergence (사물인터넷융복합논문지)

The Korea Internet of Things Society (한국사물인터넷학회)
권호 표지
DOI QR코드

DOI QR Code

Understanding Child Abuse Based on Big Data Analysis -A Basic Study on the Development of Machine Learning Algorithm-

빅데이터 분석에 기반한 아동학대의 이해 -머신러닝 알고리즘 개발 기초연구-

  • Bae, Jungho (Child Education, Baekseok Culture University) ;
  • Burm, Eunae (Nursing, Baekseok Culture Universityrsity)
  • 배정호 (백석문화대학교 유아교육과) ;
  • 범은애 (백석문화대학교 간호학과)
  • Received : 2022.06.15
  • Accepted : 2022.07.29
  • Published : 2022.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

The purpose of this study is to provide basic data on policy development using big data analysis and machine learning algorithms as part of preparing measures to prevent child abuse. In order to analyze big data for developing machine learning algorithms to prevent child abuse, frequency analysis, related word analysis, and emotional analysis were performed after defining academic databases and social network service data as big data. related words, and emotional analysis were conducted. As a result of the study, a preventive child abuse algorithm can be developed by preparing a data collection and sharing network system to prevent child abuse from the perspective of children affected by child abuse, perpetrators, and government authorities. Although it will be possible by institutionalizing infant self-esteem, depression, and anxiety tests with clues that depression and anxiety appear due to a decrease in self-concept in the characteristics of children affected by child abuse. We suggest that continuous progress of big data collection and analysis and algorithm development research to prevent child abuse, and expects that effective policies to prevent child abuse will be realized to eradicate child abuse crimes.

본 연구의 목적은 아동학대 예방을 위한 방안 마련의 일환으로 빅데이터 분석과 머신러닝 알고리즘을 활용한 정책개발의 기초자료를 제공하는데 있다. 아동학대 예방을 위한 머신러닝 알고리즘 개발을 위한 빅데이터 분석을 위해 학술데이터베이스와 사회관계망서비스 자료를 빅데이터로 정의하고 빈도, 연관어, 감성분석을 시행하였다. 연구결과 예방적 아동학대 알고리즘은 학술빅데이터 분석에 나타난 아동학대 관련 세 주체 피해아동, 가해양육자, 정부당국의 관점에서 아동학대 예방을 위한 데이터 수집 및 공유 네트워크 시스템 마련을 통해 개발이 가능할 것이다. 또한 아동학대 피해아동의 특성에서 자아개념 저하 등으로 우울 및 불안이 나타남을 단서로 영유아 자아존중감 및 우울, 불안 검사를 제도화함으로써 가능할 것이다. 아동학대 예방을 위한 빅데이터 수집 및 분석, 알고리즘 개발 연구의 지속적 진행을 제안하며 아동학대 예방을 위한 실효적 정책 마련이 실현되어 아동학대범죄가 근절되기를 기대한다.

Keywords

Acknowledgement

이 논문은 2021년 대한민국 교육부와 한국연구재단의 지원을 받아 수행된 연구임 (NRF-과제번호 2021S1A5A8071217)

References

  1. Korea Law Information Center, "CHILD WELFARE ACT," 2022.05.30. https://law.go.kr/LSW/lsInfoP.do?lsiSeq=198257&viewCls=engLsInfoR&urlMode
  2. Ministry of Health and Welfare, "2020 Annual Report on Child Abuse," http://www.mohw.go.kr/react/al/sal0301vw.
  3. S. H. OH & H. A. Kang, "Analysis of News on Child Abuse based on the Major Policy Changes: Using Text Mining," Journal of the Korean society of child welfare, Vol.70, No.3, pp.1-31, 2021.
  4. Amrit, C., Paauw, T., Aly, R., & Lavric, M,. "Identifying child abuse through text mining and machine learning," Expert systems with applications, Vol.88, pp.402-418, 2017. https://doi.org/10.1016/j.eswa.2017.06.035
  5. E.S.Gokten and C.Uyulan,"Prediction of the development of depression and post-traumatic stress disorder in sexually abused children using a random forest classifier," Journal of Affective Disorders, Vol.279, pp.256-265, 2021. https://doi.org/10.1016/j.jad.2020.10.006
  6. J.I.Sorensen, R.M.Nikam and A.K.Choudhary, "Artificial intelligence in child abuse imaging," Pediatric radiology, Vol.51, No.6, pp.1061-1064, 2021. https://doi.org/10.1007/s00247-021-05073-0
  7. J.H,Bae and E.A.Burm, "Strategies for College Entrance Based on Big Data Analysis," Journal of Internet of Things and Convergence, Vol.8, No.2, pp.25-33, 2022. https://doi.org/10.20465/KIOTS.2022.8.2.025
  8. J.H.Bae and E.A.Burm, "Big data analysis for child well-being on academic research," Medico Legal Update, Vol.20, No.1, pp.2058-2062, 2020.
  9. A. Amado, P, Cortez, P. Rita, and S. Moro, "Research trends on Big Data in Marketing: A text mining and topic modeling based literature analysis," European Research on Management and Business Economics, Vol.24, No.1, pp.1-7, 2018. https://doi.org/10.1016/j.iedeen.2017.06.002
  10. J.H.Bae and E.A.Burm, "Big data analysis: Medical accident," Medico-Legal Update, Vol.19, No.1, pp.646-652, 2019. https://doi.org/10.5958/0974-1283.2019.00115.4
  11. J.H.Bae and E.A.Burm, "Big data analysis for child well-being on academic research," Medico Legal Update, Vol.20, No.1, pp.2058-2062, 2020.
  12. A.V.Annapragada, M.D.Donaruma-Kwoh, A.V. Annapragada and Z.A.Starosolski, "A natural language processing and deep learning approach to identify child abuse from pediatric electronic medical records," PLoS ONE Vol.16, No.2, e0247404.
  13. C.Armit, T.Paauw, R.Aly & M.Lavric, "Identifying child abuse through text mining and machine learning," Expert Systems With Applications, 88(1), pp402-418, 2017. https://doi.org/10.1016/j.eswa.2017.06.035
  14. M. Fattori, G. Pedrazzi & Turra, R. "Text mining applied to patent mapping," A practical business case. World Patent Information, 25(4), pp335-342, 2003. https://doi.org/10.1016/S0172-2190(03)00113-3
  15. C.Henry, S.Carnochan, & M.J.Austin, "Using qualitative data-mining for practice research in child welfare," Child Welfare; Arlington, 93(6), pp7-26, 2014.