작문 평가를 위한 잠재의미분석 방법론 탐색
Utility of Latent Semantic Analysis Methods for Writing Assessment
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
본 연구에서는 텍스트마이닝과 정보검색 분야에서 그 기량을 인정받고 있는 인공지능-기반 잠재의미분석 방법인 LDA와 CTM을 한글로 쓰여진 문서들에 적용해 보고 그 기능을 임상적으로 검증해 보았다. 연구 결과, Gibbs sampling 추정 방식을 사용하는 LDA는 높은 정확도로 한글 말뭉치의 심층적인 의미구조를 찾아 유사한 의미구조를 가진 문서들을 동일한 주제군으로 분류할 수 있었다. 한편 본 연구는 확률적 잠재의미분석 방법들이 어떻게 국작문 평가를 위한 효과적인 분석 툴이 될 수 있는지에 대하여 논의하였다.
Abstract
LDA and CTM are artificial intelligence-powered latent semantic analysis methods that are recognized for their prowess in the fields of text mining and information retrieval. In this study, these methods were applied to documents written in Korean, and their functionality was tested empirically. The LDA with the Gibbs sampling approach for parameter estimation was useful for identifying the deep semantic structure of the Korean language corpus and for classifying documents with similar semantic structures into common topic clusters with very high accuracy. This paper discusses how these probabilistic latent semantic analysis models could be utilized as an effective tool for Korean writing assessment.
참고문헌 (33)
- 교육부, "2015 개정 국어과 교육과정", 교육부, ~ (2015)
- 김승주, "인지진단모형을 활용한 논증적 글쓰기 평가를 위한 Q행렬 타당화 연구", 작문연구, (45), pp.181~222 (2020), 한국작문학회[DOI]
- 박헤영, "초·중등학생 글쓰기 능력 평가를 위한 평가틀 구안", 한국리터러시학회 & 한국작문학회 공동학술대회, pp.18~32 (2020)
- 박혜영, "미국의 초·중등 작문 평가의 특징과 시사점 탐색 - 국가 및 주 수준 표준화 작문 평가를 중심으로 -", 작문연구, (44), pp.73~107 (2020), 한국작문학회[DOI]
- 신선희, "미국의 작문평가", 작문연구, (13), pp.117~141 (2011), 한국작문학회
- 옥철영, "UTagger 반자동 태깅 툴 TCM 매뉴얼", 울산대학교 한국어처리연구실, ~ (2019)
- 한국리터러시학회, "한국리터러시학회 & 한국작문학회 공동학술대회 2020년 10월 17일 자료집", ~ (2020)
- Akaike, H., "Second international symposium on information theory", pp.267~281 (1973), Akademiai Kiado
- Blei, D. M., "A correlated topic model of science", The Annals of Applied Statistics, 1(1), pp.17~35 (2007)[DOI]
- Blei, D. M., "Latent dirichlet allocation", Journal of Machine Learning Research, 3, pp.993~1022 (2003)
- Burstein, J., "Benefits of modularity in an automated scoring system", Proceedings of the workshop on using toolsets and architectures to build NLP systems, 18th international conference on computational linguistics (2000)
- Cao, J., "A density-based method for adaptive LDA model selection", Neurocomputing, 72, pp.1775~1781 (2009)
- Chang, "Relational topic models for document networks", Proceedings of the 12th International Conference on Artificial Intelligence and Statistics, pp.81~88 (2009)
- Collins, L. M., "Latent class and latent transition analysis" (2010), John Wiley & Sons
- Deerwester, S., "Indexing by latent semantic analysis", Journal of the American Society for Information Science, 41, pp.391~407 (1990)
- Griffiths, T. L., "Finding scientific topics", Proceedings of the National Academy of Sciences of the United States of America, 101(suppl. 1), pp.5228~5235 (2004)
- Grün, B., "Topicmodels : An R package for fitting topic models", Journal of Statistical Software, 40(13), pp.1~30 (2011)[DOI]
- Hofmann, T., "Probabilistic latent semantic indexing", Proceedings of the Twenty-Second Annual International SIGIR Conference (1999)
- Jordan, M., "Learning in graphical models" (1999), MIT Press
- Kakkonen, T., "Automatic essay grading with probabilistic latent semantic analysis", Proceedings of the 2nd Workshop on Building Educational Application Using NLP, pp.29~36 (2005)
- Kintsch, E., "Developing summarization skills through the use of LSA-based feedback", Interactive Learning Environments, 8(2), pp.87~109 (2000)[DOI]
- Kline, R. B., "Principles and practice of structural equation modeling" (2011), Guilford Press
- Kuzi, S., "Automatic assessment of complex assignments using topic models", Association for Computing Machinery (2019)[DOI]
- Landauer, T. K., "An introduction to latent semantic analysis", Discourse Processes, 25(2&3), pp.259~284 (1998)
- Landauer, T. K., "Automatic essay assessment", Assessment in Education: Principles, Policy & Practice, 10(3), pp.295~308 (2003)[DOI]
- Miller, T., "Essay assessment with latent semantic analysis", Journal of Educational Computing Research, 29(4), pp.495~512 (2003)
- OECD, "Education policy outlook 2015: Making reforms happen" (2015), OECD Publishing
- "Latent Dirichlet allocation in R. Diploma thesis" (2012)[URL]
- Schwarz, G., "Estimating the dimension of a model", The Annals of Statistics, 6(2), pp.461~464 (1978)[DOI]
- Shin, S., "Effectiveness of Latent Class Analysis (LCA) Techniques to Handle Count Data with Excessive Zeros in Topic Analysis", The 32nd Florida Artificial Intelligence Research Society (2019)
- Tein, J-Y., "Statistical poser to detect the correct number of classes in latent profile analysis", Structural Equation Modeling, 20(4), pp.640~657 (2013)[DOI]
- Wallach, H. M., "Evaluation methods for topic models", Proceedings of the 26th Annual International Conference on Machine Learning (ICML '09), pp.1105~1112 (2009)
- Zhai, C, "Text data management and analysis: A practical introduction to information retrieval and text mining" (2016), Association for Computing Machinery and Morgan & Claypool Publishers
