DOI QR코드

DOI QR Code

Reviewer Recommendation Algorithms in Journal Manuscript Submission and Review Systems

저널 논문 투고 및 심사 시스템에서 심사위원 추천 알고리즘

  • 정용진 (한국기술교육대학교 컴퓨터공학과) ;
  • 김경한 (한국기술교육대학교 컴퓨터공학과) ;
  • 임현교 (한국기술교육대학교 컴퓨터공학과) ;
  • 김용환 (한국기술교육대학교 컴퓨터공학과) ;
  • 한연희 (한국기술교육대학교)
  • Received : 2015.05.21
  • Accepted : 2015.07.24
  • Published : 2015.08.31

Abstract

In journal manuscript submission and review systems, authors can submit their manuscript at any time and editorial members are struggling to find proper reviewers for the submitted manuscripts and assign them to such reviewers. In order to solve this problem, we propose a greedy algorithm and a genetic algorithm to recommend proper reviewers for the submitted manuscripts. The proposed algorithms evaluate reviewers' speciality for the submitted manuscripts by using the submitted manuscripts' keywords and the reviewers expertises. In addition to that, they take the fairness among the reviewers' speciality and the review frequency for consideration. To verify the proposed algorithms, we apply them to the JIPS manuscript submission and review system that the Korea Information Processing Society has operated, and present the results in this paper. By performing the performance evaluation of the proposed algorithms, we finally show that the genetic algorithm outperforms the greedy algorithm in terms of the recommended reviewers' fitness.

현재 저널 논문 투고 및 심사 시스템에서 저자는 언제든지 논문 투고가 가능하며 그에 따라 저널 편집위원들이 투고된 논문들에 가장 적절한 심사위원들을 찾아 배정하는 데에 어려움을 겪고 있다. 본 논문에서는 편집위원들의 이러한 심사위원 선정의 어려움을 해결하기 위하여, 투고된 논문들에 적절한 심사위원들을 추천하는 탐욕 알고리즘과 유전 알고리즘을 제시한다. 제안하는 두 알고리즘에서는 투고 논문들의 키워드(Keyword)와 심사위원들의 전문지식 태그(Expertise Tag) 정보를 활용하여 심사위원들의 전문성을 평가하고, 추천되는 심사위원들 간의 공정성 및 심사 참여빈도를 고려하여 심사위원들에게 심사기회가 균등하게 이루어지도록 한다. 제안하는 알고리즘을 검증하기 위하여 본 논문에서는 한국정보처리학회에서 운영하고 있는 JIPS 논문 투고 및 심사 시스템에 추천 알고리즘을 적용해보고 이의 결과를 제시한다. 마지막으로, 제안하는 두 알고리즘의 성능 분석을 수행하여 유전 알고리즘이 탐욕 알고리즘에 비해 추천 심사위원들의 적합도 측면에서 더 좋은 성능을 나타냄을 제시한다.

Keywords

References

  1. C. Long, R. C. Wong, Y. Peng, and L. Ye, "On Good and Fair Paper-Reviewer Assignment," IEEE 13th International Conference on Data Mining, 2013.
  2. X. Liu, T. Suel, and N. Memon, "A Robust Model for Paper-Reviewer Assignment," the 8th ACM Conference on Recommender systems: 25-32, 2014.
  3. X. Yun-hong, G. Xi-tong, X. Liang, C. Yu, Z. and Yong-yao, "Research Analytics for Reviewer Recommendation," International Conference on Management Science & Engineering (19th), 2012.
  4. J. Lee, J. Lee, H. Jung, I. Kang, S. Shin "Automatic Recommendation of Panel Pool Using a Probabilistic Ontology and Researcher Networks" Journal of the Korean Society for Information Management, Vol.24, No.3, pp.43-65, 2007. https://doi.org/10.3743/KOSIM.2007.24.3.043
  5. [Internet] http://www.manuscriptlink.com/journals/jips.
  6. P. Kim, S. Lee, I. Kang, H. Jung, J. Lee, W. Sung "The Academic Information Analysis Service using OntoFrame-Recommendation of Reviewers and Analysis of Researchers' Accomplishments" Journal of KIISE : Computer Systems and Theory, Vol.35, No.7, pp.431-441, 2008.
  7. J. Lee, K. Lee, and J. G. Kim, "Personalized Academic Research Paper Recommendation System," arXiv preprint arXiv:1304.5457, 2013.
  8. C. Basu, H. Hirsh, W. W. Cohen, and C. Nevill-Maning, "Technical Paper Recommendation: A Study in Combining Multiple Information Sources," Journal of Artificial Intelligence Research, Vol.14, pp.231-252, 2001.
  9. 김진권 "KFMA Online 논문투고/심사 시스템 안내" Journal of fluid machinery, Vol.8, No.1, pp.81-85, 2005.
  10. W. W. Cohen, P. Ravikumar, and S. E. Fienberg, "A comparison of string metrics for matching names and records" KDD Workshop on Data Cleaning and Object Consolidation, Vol.3, pp.73-78, 2003.
  11. D. C. Conry, "Recommender Systems for the Conference Paper Assignment Problem," the ACM Conference on Recommender Systems, 2009.
  12. J. Goldsmith and R. H. Sloan, "The AI Conference Paper Assignment Problem," In Pref. Handling for AI, Papers from the AAAI Workshop, 2007.
  13. T. Kolasa and D. Kro,l "A Survey of Algorithms for Paperreviewer Assignment Problem," IETE Technical Review (Medknow Publications & media Pvt. Ltd.), 2011.
  14. [Internet] https://www.manuscriptlink.com/journals/jips.
  15. J. Park, Y. Cho "Social Network Analysis for the Effective Adoption of Recommender Systems" Journal of Intelligence and Information Systems, Vol.17, No.4, pp.305-316, 2011.
  16. S. Lee "Personalized Contents Recommendation System Based on Social Network" Journal of Broadcast Engineering, Vol.18, No.1, pp.98-105, 2013. https://doi.org/10.5909/JBE.2013.18.1.98

Cited by

  1. A conceptual peer review model for arXiv and other preprint databases pp.1741-4857, 2019, https://doi.org/10.1002/leap.1229