[논문]자연어 처리 기법을 활용한 산업재해 위험요인 구조화

강성식; 장성록; 이종빈; 서용윤

doi:10.14346/jkosos.2021.36.1.56

자연어 처리 기법을 활용한 산업재해 위험요인 구조화
Structuring Risk Factors of Industrial Incidents Using Natural Language Process 원문보기

한국안전학회지 = Journal of the Korean Society of Safety, v.36 no.1, 2021년, pp.56 - 63

강성식 (부경대학교 안전공학과) , 장성록 (부경대학교 안전공학과) , 이종빈 (부경대학교 방재연구소) , 서용윤 (부경대학교 안전공학과)

Abstract ▼ AI-Helper

The narrative texts of industrial accident reports help to identify accident risk factors. They relate the accident triggers to the sequence of events and the outcomes of an accident. Particularly, a set of related keywords in the context of the narrative can represent how the accident proceeded. Previous studies on text analytics for structuring accident reports have been limited to extracting individual keywords without context. We proposed a context-based analysis using a Natural Language Processing (NLP) algorithm to remedy this shortcoming. This study aims to apply Word2Vec of the NLP algorithm to extract adjacent keywords, known as word embedding, conducted by the neural network algorithm based on supervised learning. During processing, Word2Vec is conducted by adjacent keywords in narrative texts as inputs to achieve its supervised learning; keyword weights emerge as the vectors representing the degree of neighboring among keywords. Similar keyword weights mean that the keywords are closely arranged within sentences in the narrative text. Consequently, a set of keywords that have similar weights presents similar accidents. We extracted ten accident processes containing related keywords and used them to understand the risk factors determining how an accident proceeds. This information helps identify how a checklist for an accident report should be structured.

주제어

표/그림 (8)

그림 Fig. 1. Flowchart for the methodology.
그림 Fig. 2. Sliding window process (window=2).
그림 Fig. 3. Example of weight calculation.
그림 Fig. 4. Neural network diagram in Word2Vec.
그림 Fig. 5. Weight matrix using Word2Vec.
그림 Fig. 6. Visualization of keyword vectors using t-SNE algorithm.
표 Table 1. Keywords driven by k-means clustering
표 Table 2. Accident process and keywords by category

참고문헌 (18)

KOSHA, "Statistical Survey and Analysis of Industrial Disasters", 2018.
Y. Suh, "Data Analytics for Social Risk Forecasting and Assessment of New Technology", J. Korean Soc. Saf., Vol. 32, No. 3, pp. 83-89, 2017.

원문보기 상세보기
C. D. Manning and H. Schutze, "Foundations of Statistical Natural Language Processing", MIT Press, 1999.
B. Kim, S. Chang and Y. Suh, "Text Analytics for Classifying Types of Accident Occurrence Using Accident Report Documents", J. Korean Soc. Saf., Vol. 33, No.3, pp. 58-64, 2018.

원문보기 상세보기
S. Kang and Y. Suh, "On the Development of Risk Factor Map for Accident Analysis using Textmining and SelfOrganizing Map(SOM) Algorithms", J. Korean Soc. Saf., Vol. 33, No. 6, pp. 77-84, 2018.

원문보기 상세보기
G. Ahn, M. Seo and S. Hur, "Development of Accident Classification Model and Ontology for Effective Industrial Accident Analysis based on Textmining", J. Korean Soc. Saf., Vol. 32, No. 5, pp. 179-185, 2017.

원문보기 상세보기
T. L. Bunn, S. Slavova and L. Hall, "Narrative Text Analysis of Kentucky Tractor Fatality Reports", Accid. Anal. Prev., Vol. 40, No. 2, pp. 419-425, 2008.

상세보기
T. Mikolov, K. Chen, G. Corrado and J. Dean, "Efficient Estimation of Word Representations in Vector Space", arXiv preprint, arXiv:1301.3781, 2013.
X. He, D. Cai, S. Yan and H. Zhang, "Neighborhood Preserving Embedding", Tenth IEEE International Conference on Computer Vision, 2005.
K. Toutanova, D. Chen, P. Pantel, H. Poon, P. Choudhury and M. Gamon, "Representing Text for Joint Embedding of Text and Knowledge Bases", Conference on Empirical Methods in Natural Language Processing, pp. 1499-1509, 2015.
J. H. Jo, "A study on the Causes Analysis and Preventive Measures by Disaster types in Construction Fields", KSMS, Vol. 14, No. 1, pp. 7-13, 2012.
S. K. Kang, H. Yu and Y. J. Lee, "Analyzing Disaster Response Terminologies by Text Mining and Social Network Analysis", Information Systems Review, Vaol. 18, No. 1, pp. 141-155, 2016.

원문보기 상세보기
W. Jang and Y. Suh, "Identifying Abnormal Accidents Using Local Outlier Factor and Decision Tree Algorithms", Journal of the Korean Institute of Industrial Engineers, Vol. 45, No. 4, pp. 329-340, 2019.

상세보기
Y. Goldberg and O. Levy, "Word2vec Explained: Deriving Mikolov et al.'s Negative-sampling Word-embedding Method", arXiv preprint, arXiv:1402.3722, 2014.
L. Ma and Y. Zhang, "Using Word2Vec to Process Big Text Data", IEEE International Conference on Big Data, 2015.
Sanghyuk Choi, Jinseok Seol and Sang-goo Lee, "On Word Embedding Models and Parameters Optimized for Korean", Korean Language information Science Society, pp. 252-256, 2016.
L. Van Der Maaten and G. Hinton, "Visualizing Data using t-SNE", J Mach Learn Res, Vol. 9, pp. 2579-2605, 2008.

상세보기
A. Likas, N. Vlassis and J. J. Verbeek, "The Global k-means Clustering Algorithm", Pattern Recognition, Vol. 36, No. 2, pp. 451-461, 2003.

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