Journal of the Korean BIBLIA Society for library and Information Science (한국비블리아학회지)

Korean Biblia Society for Library and Information Science (한국비블리아학회)
권호 표지
DOI QR코드

DOI QR Code

Examining Suicide Tendency Social Media Texts by Deep Learning and Topic Modeling Techniques

딥러닝 및 토픽모델링 기법을 활용한 소셜 미디어의 자살 경향 문헌 판별 및 분석

  • 고영수 (연세대학교 문헌정보학과) ;
  • 이주희 (연세대학교 문헌정보학과) ;
  • 송민 (연세대학교 문헌정보학과)
  • Received : 2021.08.16
  • Accepted : 2021.09.06
  • Published : 2021.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

This study aims to create a deep learning-based classification model to classify suicide tendency by suicide corpus constructed for the present study. Also, to analyze suicide factors, the study classified suicide tendency corpus into detailed topics by using topic modeling, an analysis technique that automatically extracts topics. For this purpose, 2,011 documents of the suicide-related corpus collected from social media naver knowledge iN were directly annotated into suicide-tendency documents or non-suicide-tendency documents based on suicide prevention education manual issued by the Central Suicide Prevention Center, and we also conducted the deep learning model(LSTM, BERT, ELECTRA) performance evaluation based on the classification model, using annotated corpus data. In addition, one of the topic modeling techniques, LDA identified suicide factors by classifying thematic literature, and co-word analysis and visualization were conducted to analyze the factors in-depth.

자살은 전 세계 사망 원인 중 4위이며 사회, 경제적 손실이 큰 난제이다. 본 연구는 자살 예방을 위하여 소셜미디어에 나타난 자살 관련 말뭉치를 구축하고 이를 통해 자살 경향 문헌을 분류할 수 있는 딥러닝 자동분류 모델을 만들고자 하였다. 또한, 자살 요인을 분석하기 위해 주제를 자동으로 추출하는 분석 기법인 토픽모델링을 활용하여 자살 관련 말뭉치를 세부 주제로 분류하고자 하였다. 이를 위해 소셜미디어 중 하나인 네이버 지식iN에 나타난 자살 관련 문헌 2,011개를 수집한 후 자살예방교육 매뉴얼을 기준으로 자살 경향 문헌 및 비경향 문헌 여부를 주석 처리하였으며, 이 데이터를 딥러닝 모델(LSTM, BERT, ELECTRA)로 학습시켜 자동분류 모델을 만들었다. 또한, 토픽모델링 기법의 하나인 LDA 기법으로 주제별 문헌을 분류하여 자살 요인을 발견하였고 이를 심층적으로 분석하기 위해 주제별로 동시출현 단어 분석 및 네트워크 시각화를 진행하였다.

Keywords

Acknowledgement

본 연구는 정부의 재원으로 한국연구재단의 지원을 받아 수행된 연구임(NRF-2018S1A3A2075114).

References

  1. Ahn, Y. (2019). 2018 National Survey on Suicide. Ministry of Health and Welfare. Available: http://www.mohw.go.kr/react/jb/sjb030301vw.jsp?PAR_MENU_ID=03&MENU_ID=032901&CONT_SEQ=350956
  2. Jung, S. H. (2005). The socioeconomic burden of suicide and depression in South Korea. National Center for Mental Health.
  3. Kim, G. M., Kim, K., Jo, J., & Lim, H. S. (2018). Constructing for Korean traditional culture corpus and development of named entity recognition model using Bi-LSTM-CNN-CRFs. Journal of the Korea Convergence Society, 9(12), 47-52. https://doi.org/10.15207/JKCS.2018.9.12.047
  4. Kim, H. J., Park, S. J., Song, C. M., & Song, M. (2019). Text mining driven content analysis of social perception on schizophrenia before and after the revision of the terminology. Journal of the Korean Society for Library and Information Science, 53(4), 285-307.
  5. Kim, N. & Lee, N. J. (2021). An analysis of changes in social issues related to patient safety using topic modeling and word co-occurrence analysis. The Korea Contents Society, 21(1), 92-104. https://doi.org/10.5392/JKCA.2021.21.01.092
  6. Korea Suicide Prevention Center (2012). Suicide Prevention Training Manual.
  7. Lee, B. O. (2020). A study on the classification of internet suicide suggestions types. Journal of the Korean Society of Civil Security, 19, 153-172.
  8. Lee, J., Jung, J., & Kim, H. (2021). A study on the judgment of nativelikeness of korean learner corpus by deep learning language model. Korean Language And Culture Education Society, 17(1), 155-177. http://doi.org/10.18842/klaces.2021.17.1.007
  9. Lee, S., Kim, S., Lee, J., Ko, Y., & Song, M. (2021). Building and analyzing panic disorder social media corpus for automatic deep learning classification model. Journal of the Korean Society for Information Management, 38(2), 153-172. https://doi.org/10.3743/KOSIM.2021.38.2.153
  10. Ministry of Health and Welfare (2021, May 5). First quarter of 2021 「Corona 19 National Mental Health Survey」. Available: http://www.mohw.go.kr/react/al/sal0301vw.jsp?PAR_MENU_ID=04&MENU_ID=0403&CONT_SEQ=365582&page=1
  11. Park, C., Park, K., Moon, H., Eo, S., & Lim, H. (2021). A study on performance improvement considering the balance between corpus in Neural Machine Translation. Journal of the Korea Convergence Society, 12(5), 23-29. https://doi.org/10.15207/JKCS.2021.12.5.023
  12. Seo, H. & Song, M. (2019). An analysis of the discourse topics of users who exhibit symptoms of depression on social media. Journal of the Korean society for information management, 36(4), 207-226. https://doi.org/10.3743/KOSIM.2019.36.4.207
  13. Song, M. (2017). Textmining. Seoul: Chungram.
  14. Statistics Korea (2020, September 22). The results of statistics on causes of death in 2019. Available: http://kostat.go.kr/portal/korea/kor_nw/3/index.board?bmode=read&aSeq=385220
  15. Clark, K., Luong, M. T., Le, Q. V., & Manning, C. D. (2020). Electra: Pre-training text encoders as discriminators rather than generators. arXiv preprint arXiv:2003.10555.
  16. Devlin, J. (2021). Bert multilingual. GitHub. Available: https://github.com/google-research/bert/blob/master/multilingual.md
  17. Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805.
  18. Du, J., Zhang, Y., Luo, J., Jia, Y., Wei, Q., Tao, C., & Xu, H. (2018). Extracting psychiatric stressors for suicide from social media using deep learning. BMC medical informatics and decision making, 18(2), 77-87. https://doi.org/10.1186/s12911-018-0632-8
  19. Jeon, H. (2021). KoBERT. GitHub. Available: https://github.com/SKTBrain/KoBERT
  20. Kaplan, M. S., Huguet, N., McFarland, B. H., & Newsom, J. T. (2007). Suicide among male veterans: a prospective population-based study. Journal of Epidemiology & Community Health, 61(7), 619-624. http://dx.doi.org/10.1136/jech.2006.054346
  21. NEWS 18 (2021, October 15). Covid-19 Spiked Suicide Attempts in Teenage Girls by 51%: US CDC. Available: https://www.news18.com/news/lifestyle/covid-19-spiked-suicide-attempts-in-teenage-girls-by-51-us-cdc-3848564.html
  22. NIMH (2021, June 6). Suicide. Available: https://www.nimh.nih.gov/health/statistics/suicide
  23. Park, J. (2020). KoELECTRA: Pretrained ELECTRA model for Korean. GitHub. Available: https://github.com/monologg/KoELECTRA
  24. Resnik, P., Armstrong, W., Claudino, L., Nguyen, T., Nguyen, V. A., & Boyd-Graber, J. (2015). Beyond LDA: exploring supervised topic modeling for depression-related language in Twitter. In Proceedings of the 2nd Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality, 99-107.
  25. Resnik, P., Garron, A., & Resnik, R. (2013). Using topic modeling to improve prediction of neuroticism and depression in college students. In Proceedings of the 2013 conference on empirical methods in natural language processing, 1348-1353.
  26. Song, Min (2021, June 6). treform. GitHub. Available: https://github.com/MinSong2/treform
  27. Steyvers, M. & Griffiths, T. (2007). Probabilistic topic models. In Handbook of latent semantic analysis. New Jersey: Psychology Press, 439-460.
  28. Thompson, P., Bryan, C., & Poulin, C. (2014). Predicting military and veteran suicide risk: Cultural aspects. In Proceedings of the Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality, 1-6. http://dx.doi.org/10.3115/v1/W14-3201
  29. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017). Attention is all you need. In Advances in neural information processing systems, 5998-6008. https://dl.acm.org/doi/10.5555/3295222.3295349
  30. Won, H. H., Myung, W., Song, G. Y., Lee, W. H., Kim, J. W., Carroll, B. J., & Kim, D. K. (2013). Predicting national suicide numbers with social media data. PloS one, 8(4), e61809. https://doi.org/10.1371/journal.pone.0061809
  31. World Health Organization (2021, June 6). Suicide prevention. Available: https://www.who.int/health-topics/suicide#tab=tab_1