Keybert와 Bertopic을 활용한 텍스트마이닝 연구동향 분석
An Analysis of Academic Research Trends in Text Mining using Keybert and Bertopic
1
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
대량의 텍스트 데이터를 분석하고 활용하는 텍스트 마이닝 기법은 공학 분야뿐만 아니라 사회과학과 교육 등 거의 모든 학문 분야에서 널리 사용되고 있다. 특히 최근 대규모 언어 모델의 급속한발전은 기존 텍스트 마이닝 기법의 한계를 보완하는 혁신적인 방법들을 도입하는 데 기여하고 있다. 본 연구의 목적은 국내 학술 및 학위 논문을 수집하여 최신 텍스트 마이닝 기법을 활용해 분석하는 것이다. 이를 위해 학술연구정보서비스(RISS) 데이터베이스에서 ‘텍스트 마이닝’을 키워드로 논문을 수집하였고, 수집된 논문들에 대해 키워드 분석과 토픽 모델링을 수행하였다. 키워드 분석에서는 TF- IDF를 활용한 빈도 기반 분석과 BERT 기반의 KeyBERT를 활용한 분석을 비교하였다. 또한, 토픽모델링 분석에서는 기존 통계 기반의 LDA 기법과 최신 언어 모델인 BERT 기반의 토픽 모델링 기법인 BERTopic을 비교하였다. 그 결과, BERT 기반의 토픽 분석이 응집도(Coherence Score) 점수에서 보다 우수한 성능을 나타냈다. 특히, Bertopic에서 한국어 임베딩 모델과 Keybert 기반의 토픽추출이 다국어 모델과 문장 기반의 추출보다 더 높은 응집도 점수를 기록하였다. 본 연구는 이러한 결과를 통해 한국어 텍스트 마이닝에서 최신 기법들의 적용과 활용 가능성을 제시하고자 한다.
Abstract
Text mining techniques for analyzing and utilizing large-scale text data are widely used not only in engineering but also in social sciences, education, and almost all academic fields. This study aims to collect and analyze domestic academic and thesis papers on text mining using the latest text mining techniques. For this purpose, papers were collected from the Research Information Sharing Service (RISS) database using the keyword ‘text mining’, and keyword analysis and topic modeling were conducted on the collected papers. In keyword analysis, frequency-based analysis using TF-IDF and analysis using BERT-based KeyBERT were compared. Additionally, in topic modeling analysis, traditional statistical-based LDA techniques were compared with BERTopic, a topic modeling technique based on the latest BERT language model. The results showed that BERT-based topic analysis demonstrated superior performance in terms of coherence score. Particularly, the topic extraction based on Korean embedding models and Keybert recorded higher coherence scores compared to those based on multilingual models and sentence-based extraction. Through these findings, this study aims to present the applicability and potential of the latest techniques in Korean text mining.
참고문헌 (26)
- A. Jadhav, "A survey on text mining - Techniques, application", International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 9(3), pp.338~343 (2023)
- S. Gnanavel, "Rapid text retrieval and analysis supporting latent dirichlet allocation based on probabilistic models", Mobile Information Systems, 2022(1), pp.6028739~ (2022)
- D. Antons, "The application of text mining methods in innovation research: Current state, evolution patterns, and development priorities", R&D Management, 50(3), pp.329~351 (2020)
- A. Aizawa, "An information-theoretic perspective of tf–idf measures", Information Processing & Management, 39(1), pp.45~65 (2003)
- S. Qaiser, "Text mining : Use of TF-IDF to examine the relevance of words to documents", International Journal of Computer Applications, 181(1), pp.25~29 (2018)
- Z. Zhuo, "News text topic clustering optimized method based on TF-IDF Algorithm on Spark", Computers Materials & Continua, 62(1) (2020)
- W. B. Cavnar, "N-gram-based text categorization", Proceedings of SDAIR-94, 3rd annual symposium on document analysis and information retrieval, 161175, pp.14~ (1994)
- R. Lv, "NGram nearest neighbor machine translation", IEEE, 2024, ~
- K. Pooja, "Topic modeling : A comprehensive review", EAI Endorsed transactions on scalable information systems, 7(24) (2019)
- D. M. Blei, "Probabilistic topic models", Communications of the ACM, 55(4), pp.77~84 (2012)
- Y. Zhang, "Understanding bag-of-words model : A statistical framework", International Journal of Machine Learning and Cybernetics, 1, pp.43~52 (2010)
- Y. Kalepalli, "Effective comparison of LDA with LSA for topic modelling", 2020 4th International Conference on Intelligent Computing and Control Systems (ICICCS), pp.1245~1250 (2020)
- D. Lee, "Algorithms for non-negative matrix factorization", Advances in Neural Information Processing Systems, 13 (2020)
- B. Issa, "A comparative study on embedding models for keyword extraction using KeyBERT method", 2023 IEEE 13th International Conference on System Engineering and Technology (ICSET), pp.40~45 (2023)
- D. Deng, "DBSCAN clustering algorithm based on density", 2020 7th international forum on electrical engineering and automation (IFEEA), pp.949~953 (2020)
- "Bertopic Algorithm Hompage image"[URL]
- S. Samsir, "Using BERTopic model for abstracts classification", Jurnal Media Informatika Budidarma, 7(3) (2023)
- S. G. Kim, "The status of using text mining in academic research and analysis methods", Korea Institute of Enterprise Architecture, 13(2), pp.317~329 (2016)
- L. P. Gurdiel, "A comparison study between coherence and perplexity for determining the number of topics in practitioners interviews analysis", IV Iberoamerican Conference of Young Researchers in Economy and Management (2021)
- "Sentence Transformer Model"[URL]
- Z. Wang, "Identifying interdisciplinary topics and their evolution based on BERTopic", Scientometrics, pp.1~26 (2023)