DOI QR코드

DOI QR Code

A Child Emotion Analysis System using Text Mining and Method for Constructing a Children's Emotion Dictionary

텍스트마이닝 기반 아동 감정 분석 시스템 및 아동용 감정 사전 구축 방안

  • 박영준 (동서대학교 소프트웨어학과) ;
  • 김선용 (동서대학교 소프트웨어학과) ;
  • 김요한 (동서대학교 소프트웨어학과)
  • Received : 2024.04.29
  • Accepted : 2024.06.12
  • Published : 2024.06.30

Abstract

In a society undergoing rapid change, modern individuals are facing various stresses, and there's a noticeable increase in mental health treatments for children as well. For the psychological well-being of children, it's crucial to swiftly discern their emotional states. However, this proves challenging as young children often articulate their emotions using limited vocabulary. This paper aims to categorize children's psychological states into four emotions: depression, anxiety, loneliness, and aggression. We propose a method for constructing an emotion dictionary tailored for children based on assessments from child psychology experts.

급격하게 변화되는 사회 속에서 현대인들은 다양한 스트레스를 경험하고 있으며, 아동 또한 정신 건강 진료량이 눈에 띄게 증가하고 있다. 소아정신건강장애 등 아동의 정신 건강 문제를 예방하기 위해서는 감정 상태를 빠르게 파악해야 하지만, 유아기 아동들은 몇 가지 단어만을 사용하여 자신의 감정을 표현하는 경우가 많기에 어려움이 있다. 본 논문에서는 아동 심리 상태를 우울, 불안, 외로움, 두려움 등 4가지의 감정으로 세분화하고 아동 심리 전문가의 점수를 기반으로 한 아동용 감정 사전 구축 방안을 제안한다. 또한, STT 및 텍스트 마이닝 기반의 아동 감정 분석 시스템을 제안하고 실제 음성 데이터로 성능을 평가하였다. 평가 결과는 제안한 아동용 감정 분석 시스템이 아동 감정 상태를 정확하게 파악할 수 있음을 보여준다.

Keywords

Acknowledgement

"본 연구는 2024년 과학기술정보통신부 및 정보통신기획평가원의 SW중심대학사업의 연구결과로 수행되었음"(2019-0-01817)

References

  1. J. Park and M. Chung, "Relationships Between Strategies for Coping with Stress and Behavior Problems in School - age Children," Korean Journal of Child Studies, vol. 22, no. 3, pp. 107-122, 2001. 
  2. Salary Information Management Department, "Analysis of Depression and Anxiety Disorder Treatment Status in the Recent 5 Years (2017-2021)," Health Insurance Review & Assessment Service - press release, 2022. 
  3. J. Song, J. Lee, and L. Kim, "The Effect of Mother's Self-reflection on Children's Resilience: The Mediating Effect of Co-parenting," Korean Journal of Child Care and Education Policy (KJCCEP), vol. 17, no. 3, pp. 3-21, 2023.  https://doi.org/10.1186/s40723-023-00105-8
  4. H. Oh, "A Study on Children's Emotion and Psychology about Color By Age Group," Master's Thesis of Cheju National University, 2005. 
  5. J. Choi and S. Kim, "Early Detection Assistance System for Rare Diseases based on Patient's Symptom Information," Journal of the Korea Institute of Electronic Communication Sciences, vol. 18, no. 2, pp 373-378, 2023.  https://doi.org/10.13067/JKIECS.2023.18.2.373
  6. J. Lee, M. Moon, Y. Jeong, and S. Park, "Development of Dog Name Recommendation System for the Image Abstraction", Journal of the Korea Institute of Electronic Communication Sciences, vol. 18, no. 2, pp 313-320, 2023.  https://doi.org/10.13067/JKIECS.2023.18.2.313
  7. S. Park, C. Na, M. Choi, D. Lee, and B. On, "KNU Korean Sentiment Lexicon - Bi-LSTM-based Method for Building a Korean Sentiment Lexicon," Journal of Intelligence and Information Systems, vol. 24, no. 4, pp. 219-240, 2018.  https://doi.org/10.13088/JIIS.2018.24.4.219
  8. M. Nam, E. Lee, and J. Shin, "A Method for User Sentiment Classification using Instagram Hashtag," Journal of Korea Multimedia Society, vol. 18, no. 11, 2015. 
  9. Y. Kim and M. Song, "A Study on Analyzing Sentiments on Movie Reviews by Multi-Level Sentiment Classifier," Journal of Information System, vol. 22, no. 3, pp. 71-89, 2016. 
  10. S. Park, C. Eom, B. On, and D. Jeong, "An AR-KNU Sentiment Lexicon-based University Reputation Assessment Using Online News Data," Journal of Korean Institute of Information Technology, vol. 17, no. 3, pp. 11-21, 2019.