DOI QR코드

DOI QR Code

문서 중요도를 고려한 토픽 기반의 논문 교정자 매칭 방법론

A Proofreader Matching Method Based on Topic Modeling Using the Importance of Documents

  • Son, Yeonbin (Industrial and Management Engineering, Kyonggi University) ;
  • An, Hyeontae (Industrial and Management Engineering, Kyonggi University) ;
  • Choi, Yerim (Industrial and Management Engineering, Kyonggi University)
  • 투고 : 2018.04.04
  • 심사 : 2018.07.06
  • 발행 : 2018.08.31

초록

최근 국내외 연구기관에서는 논문을 저널에 제출하는 과정에서 연구결과를 효과적으로 전달하기 위해 외부 기관을 통해 논문의 문맥, 전문 용어의 쓰임, 스타일 등에 대한 논문 교정을 진행하는 경우가 증가하고 있다. 하지만 대다수의 논문 교정 회사에서는 매니저의 주관적 판단에 따라 수동으로 논문 교정자를 할당하는 시스템이며, 이에 따라 논문의 주제에 대한 전문성이 부족한 교정자를 할당하여 논문 교정 의뢰인의 만족도가 떨어지는 사례가 발생하고 있다. 따라서 본 논문에서는 효과적인 논문 교정자 할당을 위해 논문의 토픽을 고려한 논문 교정자 매칭 방법론을 제안한다. Latent Dirichlet Allocation을 이용하여 문서의 토픽 모델링을 진행하고, 그 결과를 이용하여 코사인 유사도 기반으로 사용자간 유사도를 계산하였다. 특히, 논문 교정자의 토픽 모델링 과정에서, 대표 문서로 간주되는 문서의 중요도에 따라 가중치를 부여하여 빈도수에 차별을 둬 정밀한 토픽 추정을 가능하게 한다. 실제 서비스의 데이터를 이용한 실험에서 제안 방법론의 성능이 비교 방법론보다 우수함을 확인하였으며, 정성적 평가를 통해 논문 교정자 매칭 결과의 유효성을 검증하였다.

In the process of submitting a manuscript to a journal in order to present the results of the research at the research institution, researchers often proofread the manuscript because it can manuscripts to communicate the results more effectively. Currently, most of the manuscript proofreading companies use the manual proofreader assignment method according to the subjective judgment of the matching manager. Therefore, in this paper, we propose a topic-based proofreader matching method for effective proofreading results. The proposed method is categorized into two steps. First, a topic modeling is performed by using Latent Dirichlet Allocation. In this process, the frequency of each document constituting the representative document of a user is determined according to the importance of the document. Second, the user similarity is calculated based on the cosine similarity method. In addition, we confirmed through experiments by using real-world dataset. The performance of the proposed method is superior to the comparative method, and the validity of the matching results was verified using qualitative evaluation.

키워드

참고문헌

  1. Wordvice Inc., https://essayreview.co.kr/intro/.
  2. Hyun, Y., Shun, W. W. X., & Kim, N., "Methodology for Issue-related R&D Keywords Packaging Using Text Mining.", Journal of Internet Computing and Services, Vol.16, No.02, pp.57-66, 2015. https://doi.org/10.7472/jksii.2015.16.2.57
  3. Yu, Y., Mo, L., & Wang, J., "Identifying Topic- Specific Experts on Microblog.", Transactions on Internet & Information Systems, Vol.10, No.06, 2016. https://doi.org/10.3837/tiis.2016.06.010
  4. Hofmann, T., "Probabilistic Latent Semantic Analysis.", In Proceedings of the conference on Uncertainty in Artificial Intelligence, pp.289-296, 1999. https://dl.acm.org/citation.cfm?id=-2073829
  5. Blei, D. M., Ng, A. Y., & M. I., "Latent Dirichlet Allocation.", Journal of Machine Learning Research, pp.993-1022, 2003. http://www.jmlr.org/papers/v3/blei03a.html
  6. Pang, N. T., Michael, S., and Vipin, K., "Introduction to Data Mining.", Addison-Wesley, 2007.
  7. Kim, M., Song, E., & Kim, Y., "A Design of Satisfaction Analysis System for Content Using Opinion Mining of Online Review Data.", Journal of Internet Computing and Services, Vol.17, No.03, pp.107-113, 2016. https://doi.org/10.7472/jksii.2016.17.3.107
  8. Jung, S., Lee, H., & Suh, Y., "The Influence of Negative Emotions on Customer Contribution to Organizational Innovation in an Online Brand Community.", Journal of Internet Computing and Services, Vol.14, No.04, pp.91-100, 2013. https://doi.org/10.7472/jksii.2013.14.4.91
  9. Yoo, S. Y., & Jeong, O. R., "Social Category Based Recommendation Method.", Journal of Internet Computing and Services, Vol.15, No.05, pp.73-82, 2014. https://doi.org/10.7472/jksii.2014.15.5.73
  10. Wallach, H. M., "Topic Modeling: Beyond Bagof-words.", In Proceedings of the 23rd International Conference on Machine Learning, pp.977-984, 2006. https://doi.org/10.1145/1143844.1143967
  11. Karnik, A., Goswami, S., & Guha, R., "Detecting Obfuscated Viruses Using Cosine Similarity Analysis.", Modelling & Simulation, pp.165-170, 2007. https://doi.org/10.1109/ams.2007.31
  12. Koren, Y., Bell, R., & Volinsky, C., "Matrix Factorization Techniques for Recommender Systems.", Computer, Vol.42, No.08, 2009. https://doi.org/10.1109/mc.2009.263
  13. Baltrunas, L., Ludwig, B., & Ricci, F., "Matrix Factorization Techniques for Context Aware Recommendation.", In Proceedings of the fifth ACM conference on Recommender systems., pp.301-304, 2011. https://doi.org/10.1145/2043932.2043988

피인용 문헌

  1. Dessert Ateliers Recommendation Methods for Dessert E-commerce Services vol.21, pp.1, 2018, https://doi.org/10.7472/jksii.2020.21.1.111