[논문]딥러닝 자동 분류 모델을 위한 공황장애 소셜미디어 코퍼스 구축 및 분석

이수빈; 김성덕; 이주희; 고영수; 송민

doi:10.3743/kosim.2021.38.2.153

[국내논문] 딥러닝 자동 분류 모델을 위한 공황장애 소셜미디어 코퍼스 구축 및 분석
Building and Analyzing Panic Disorder Social Media Corpus for Automatic Deep Learning Classification Model 원문보기

정보관리학회지 = Journal of the Korean society for information management, v.38 no.2, 2021년, pp.153 - 172

이수빈 (연세대학교 문헌정보학과) , 김성덕 (연세대학교 문헌정보학과) , 이주희 (연세대학교 문헌정보학과) , 고영수 (연세대학교 문헌정보학과) , 송민 (연세대학교 문헌정보학과)

초록
AI-Helper

본 연구는 공황장애 말뭉치 구축과 분석을 통해 공황장애의 특성을 살펴보고 공황장애 경향 문헌을 분류할 수 있는 딥러닝 자동 분류 모델을 만들고자 하였다. 이를 위해 소셜미디어에서 수집한 공황장애 관련 문헌 5,884개를 정신 질환 진단 매뉴얼 기준으로 직접 주석 처리하여 공황장애 경향 문헌과 비 경향 문헌으로 분류하였다. 이 중 공황장애 경향 문헌에 나타난 어휘적 특성 및 어휘의 관계성을 분석하기 위해 TF-IDF값을 산출하고 단어 동시출현 분석을 실시하였다. 공황장애의 특성 및 증상 간의 관련성을 분석하기 위해 증상 빈도수와 주석 처리된 증상 번호 간의 동시출현 빈도수를 산출하였다. 또한, 구축한 말뭉치를 활용하여 딥러닝 자동 분류 모델 학습 및 성능 평가를 하였다. 이를 위하여 최신 딥러닝 언어 모델 BERT 중 세 가지 모델을 활용하였고 이 중 KcBERT가 가장 우수한 성능을 보였다. 본 연구는 공황장애 관련 증상을 겪는 사람들의 조기 진단 및 치료를 돕고 소셜미디어 말뭉치를 활용한 정신 질환 연구의 영역을 확장하고자 시도한 점에서 의의가 있다.

Abstract ▼ AI-Helper

This study is to create a deep learning based classification model to examine the characteristics of panic disorder and to classify the panic disorder tendency literature by the panic disorder corpus constructed for the present study. For this purpose, 5,884 documents of the panic disorder corpus collected from social media were directly annotated based on the mental disease diagnosis manual and were classified into panic disorder-prone and non-panic-disorder documents. Then, TF-IDF scores were calculated and word co-occurrence analysis was performed to analyze the lexical characteristics of the corpus. In addition, the co-occurrence between the symptom frequency measurement and the annotated symptom was calculated to analyze the characteristics of panic disorder symptoms and the relationship between symptoms. We also conducted the performance evaluation for a deep learning based classification model. Three pre-trained models, BERT multi-lingual, KoBERT, and KcBERT, were adopted for classification model, and KcBERT showed the best performance among them. This study demonstrated that it can help early diagnosis and treatment of people suffering from related symptoms by examining the characteristics of panic disorder and expand the field of mental illness research to social media.

주제어

참고문헌 (33)

ETRI (2019). KorBERT. Available: https://aiopen.etri.re.kr/service_dataset.php
Kim, Gyeong-Min, Kim, Kue-kyeng, Jo, Jae-choon, & Lim, Heui-Seok (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.

원문보기 상세보기
Kim, Hyun-Ji, Park, Seo-Jeong, Song, Chae-Min, & Song, Min (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.
Ko, Eun-Jung, Choi, Young-Hee, Park, Gi-Hwan, & Lee, Jung-Heum (2000). Clinical characteristics of panic disorder. Journal of the Korean Society of Biological Therapies in Psychiatry, 6(2), 188-198.
Lee, Hyun-Joo, Gim, Min-Sook, Kim, Se-Joo, Park, Seon-Cheol, Yang, Jong-Chul, Lee, Kyoung-Uk, Lee, Sang-Hyuk, Lee, Seung-Jae, Lim, Se-Won, Chae, Jeong-Ho, Han, Sang-Woo, Hong, Jin-Pyo, & Seo, Ho-Jun (2019). The bodily panic symptoms and predisposing stressors in Korean patients with panic disorder. Korean Neuropsychiatric Association, 58(4), 339-345. https://doi.org/10.4306/jknpa.2019.58.4.339

상세보기
Lee, Sungjick & Kim, Han-joon (2009). Keyword extraction from news corpus using modified TF-IDF. The Jounal of Society for e-Business Studies, 14(4), 59-73.
Paek, Hye-Jin, Cho, Hye-Jin, & Kim, Jung-Hyun (2017). Content analysis of news coverage on stigma and attribution regarding mental illness. Korean Journal of Journalism & Communication Studies, 61(4), 7-43. https://doi.org/10.20879/kjjcs.2017.61.4.001

상세보기
Park, Chan-Jun, Park, Ki-Nam, Moon, Hyeon-Seok, Eo, Su-Gyeong, & Lim, Heui-Seok (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.
Park, Soo-Hyun (2017). Evidence-based treatment of panic disorder. Korean Journal of Clinical Psychology, 36(4), 458-469. https://doi.org/10.15842/kjcp.2017.36.4.002

상세보기
Seoul Asan Hospital (2014). Disease encyclopedia panic disorder. Available: http://www.amc.seoul.kr/asan/healthinfo/disease/diseaseDetail.do?contentId31583
Seoul National University Hospital (2010). N medical information panic disorder. Available: http://www.snuh.org/health/nMedInfo/nView.do?categoryDIS&medidAA000344
Shin, Seo-Hee (2017). Panic disorder patients in the last 5 years Treatment trend analysis. Health Insurance Review & Assessment Service.
Shin, Yong-Wook (2014). Seoul Asan Hospital. Available: http://psy.amc.seoul.kr/asan/depts/psy/K/bbsDetail.do?menuId862&contentId213922
Song, Min (2017). Textmining. Seoul: Chungram.
Yu, J. (2019). Text mining for identifying topics in internet Q&A about adolescents' sexual concerns. Journal of Health Informatics and Statistics, 44(2), 181-188. https://doi.org/10.21032/jhis.2019.44.2.181

상세보기
American Psychiatric Association. (2013). Diagnostic and Statistical Manual of Mental Disorders (5th ed.). Washington, DC: Author.
Benton, A., Mitchell, M., & Hovy, D. (2017). Multi-task Learning for Mental Health using Social Media Text. arXiv preprint arXiv:1712.03538.
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.
Devlin, J. (2021). Bert multilingual. Available: https://github.com/google-research/bert/blob/master/multilingual.md
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

상세보기
Jeon, Heewon. (2018). KoSpacing: Automatic Korean word spacing. Available: https://github.com/haven-jeon/PyKoSpacing
Jeon, Heewon. (2021). KoBERT. Available: https://github.com/SKTBrain/KoBERT
Ko, Hyunwoong. (2021). Korean Sentence Splitter. Available: https://github.com/hyunwoongko/kss
Lee, Junbum. (2021). KcBERT: Korean Comments BERT. Available: https://github.com/Beomi/KcBERT
Medrouk, L. & Pappa, A. (2017). Deep learning model for sentiment analysis in multi-lingual corpus. In International Conference on Neural Information Processing (pp. 205-212). Springer, Cham. https://doi.org/10.1007/978-3-319-70087-8_22
Moessner, M., Feldhege, J., Wolf, M., & Bauer, S. (2018). Analyzing big data in social media: Text and network analyses of an eating disorder forum. International Journal of Eating Disorders, 51(7), 656-667. https://doi.org/10.1002/eat.22878

상세보기
Mozafari, M., Farahbakhsh, R., & Crespi, N. (2019). A BERT-based transfer learning approach for hate speech detection in online social media. In International Conference on Complex Networks and Their Applications (pp. 928-940). Springer, Cham. https://doi.org/10.1007/978-3-030-36687-2_77
Roy-Byrne, P. P., Craske, M. G., & Stein, M. B. (2006). Panic disorder. The Lancet, 368(9540), 1023-1032. https://doi.org/10.1016/S0140-6736(06)69418-X

상세보기
Salton, G. & M. J. McGill. (1983). Introduction to modern information retrieval.
Sekulic, I. & Strube, M. (2020). Adapting deep learning methods for mental health prediction on social media. arXiv preprint arXiv:2003.07634.
Song, Min. (2021. June 6). treform. Available: https://github.com/MinSong2/treform
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017). Attention is all you need. arXiv preprint arXiv:1706.03762.
Yu, L., Jiang, W., Ren, Z., Xu, S., Zhang, L., & Hu, X. (2021). Detecting changes in attitudes toward depression on Chinese social media: A text analysis. Journal of affective disorders, 280, 354-363. https://doi.org/10.1016/j.jad.2020.11.040

상세보기

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증