DOI QR코드

DOI QR Code

Interactive Morphological Analysis to Improve Accuracy of Keyword Extraction Based on Cohesion Scoring

  • Yu, Yang Woo (Dept. of Digital Contents Design, Ulsan College) ;
  • Kim, Hyeon Gyu (Div. of Computer Science and Engineering, Sahmyook University)
  • Received : 2020.10.26
  • Accepted : 2020.11.24
  • Published : 2020.12.31

Abstract

Recently, keyword extraction from social big data has been widely used for the purpose of extracting opinions or complaints from the user's perspective. Regarding this, our previous work suggested a method to improve accuracy of keyword extraction based on the notion of cohesion scoring, but its accuracy can be degraded when the number of input reviews is relatively small. This paper presents a method to resolve this issue by applying simplified morphological analysis as a postprocessing step to extracted keywords generated from the algorithm discussed in the previous work. The proposed method enables to add analysis rules necessary to process input data incrementally whenever new data arrives, which leads to reduction of a dictionary size and improvement of analysis efficiency. In addition, an interactive rule adder is provided to minimize efforts to add new rules. To verify performance of the proposed method, experiments were conducted based on real social reviews collected from online, where the results showed that error ratio was reduced from 10% to 1% by applying our method and it took 450 milliseconds to process 5,000 reviews, which means that keyword extraction can be performed in a timely manner in the proposed method.

최근 소셜 빅데이터를 대상으로 한 키워드 분석은 고객 관점의 의견이나 불만 사항을 추출하기 위한 목적으로 광범위하게 활용되고 있다. 이와 관련하여, 이전 연구에서는 키워드 분석의 정확도를 높이기 위해 응집도 점수를 활용한 방법을 제안하였으나, 리뷰의 수가 적을 경우 오류율이 증가하는 문제가 있었다. 본 논문에서는 응집도 점수 기반 알고리즘으로부터 추출된 키워드에 대해 간소화된 형태소 분석 단계를 후처리 형태로 적용함으로써 키워드 추출의 정확도를 개선하고자 하였다. 제안 방법은 입력 데이터가 주어질 때마다 필요한 형태소 분석 규칙을 점증적으로 추가할 수 있도록 지원함으로써, 사전의 크기를 최소화하고 분석의 효율을 높이고자 하였다. 또한 대화형 규칙 입력 시스템을 제공하여 분석 규칙 추가에 드는 노력을 최소화하고자 하였다. 제안 방법을 검증하기 위해 온라인에서 수집된 실제 리뷰를 대상으로 실험을 수행하였으며, 제안 방법을 적용할 경우 오류율이 기존 10%에서 1%로 개선되는 동시에, 5,000개의 리뷰 처리에 450ms가 소요되어 실시간 처리가 가능한 수준임을 확인하였다.

Keywords

References

  1. H. G. Kim, "Developing a Big Data Analysis Platform for Small and Medium-Sized Enterprises," Journal of the Korea Society of Computer and Information, Vol. 25, No. 8, Aug. 2020.
  2. W. L. Kang, H. G. Kim, and Y, J. Lee, "Reducing IO Cost in OLAP Query Processing with MapReduce," IEICE Trans. Inf. & Syst, Vol. E98-D, No. 2, pp. 444-447, Feb. 2015. https://doi.org/10.1587/transinf.2014EDL8143
  3. Naver Open API, https://developers.naver.com/docs/common/ open apiguide/
  4. Google Developer API, https://developers.google.com/
  5. Kokoma, http://kkma.snu.ac.kr/documents/index.jsp
  6. H. G. Kim, "Efficient Keyword Extraction from Social Big Data Based on Cohesion Scoring," Journal of the Korea Society of Computer and Information, Vol. 25, No. 10, Oct. 2020.
  7. H. Lim, B. Yoon, and H. Lim, "An Efficient Korean Morphological Analyzer using Exclusive Information," Journal of KIISE, Vol. 22, No. 6, pp. 957-964, 1995.
  8. Y. Kim, M. Park, J. Choi, and H. Kwon, "Improvement of Analysis Speed in Korean Morphologlcal Analyzer Using Ameliorated Dictionary," Proc. of the 11th Hangul and Korean Information Processing, pp. 479-483, 1999.
  9. S. H. Yang and Y. S. Kim, "A High-Speed Korean Morphological Analysis Method based on Pre-Analyzed Partial Words," Journal of KIISE, Vol. 27, No. 3, pp. 290-301, 2000.
  10. H. G. Seo and H. W. Park, "Design and Implementation of Potential Advertisement Keyword Extraction System Using SNS," Journal of the Korea Convergence Society, Vol. 9, No. 7, pp. 14-24, 2018.
  11. O. J. Lee, S. B. Park, D. Chung, and E. S. You, "Movie Box-Office Analysis Using Social Big Data," Journal of the Korea Contents Society, Vol. 14, No. 10, pp. 527-538, 2014.
  12. C. Lee, D. Choi, S. Kim, and J. Kang, "Classification and Analysis of Emotion in Korean Microblog Texts," Journal of KIISE, Vol. 40, No. 3, pp. 159-167, Jun. 2013.
  13. J. Y. Chang, "A Sentiment Analysis Algorithm for Automatic Product Reviews Classification in Online Shop ping Mall," Vol. 14, No. 4, pp. 19-32, 2009.
  14. Hannanum, http://semanticweb.kaist.ac.kr/hannanum/index.html
  15. Z. Jin and K Tanaka-Ishii, "Unsupervised Segmentatino of Chinese Text by Use of Branching Entropy," The Journal of Korea Navigation Institute, pp. 428-435, Jul. 2006.
  16. H. J. Kim and S. J. Cho, "Cleansing Noisy Text Using Corpus Extraction and String Match," MS. Thesis, Seoul National University, 2013.
  17. Cohesion Score, https://lovit.github.io/nlp/2018/04/09/cohesion_ltokenizer/
  18. Soynlp, https://github.com/lovit/soynlp
  19. E. Kim, "The Unsupervised Learning-based Language Modeling of Word Comprehension in Korean," Journal of the Korea Society of Computer and Information, Vol. 24, No. 11, pp. 41-49, Nov. 2019.