DOI QR코드

DOI QR Code

다차원 메타데이터 공간을 활용한 학술 문헌 추천기법 연구

A Study on the Method of Scholarly Paper Recommendation Using Multidimensional Metadata Space

  • 감미아 (연세대학교 문헌정보학과 ) ;
  • 이지연 (연세대학교 문헌정보학과)
  • 투고 : 2023.02.15
  • 심사 : 2023.03.13
  • 발행 : 2023.03.30

초록

본 연구는 '우수한 성능의 메타데이터 속성 유사도 기반의 학술 문헌추천시스템'을 제안하는 데에 목적을 두고 있다. 본 연구에서는 정보조직에서 다루는 메타데이터의 활용과 계량정보학에서 다루고 있는 동시인용, 저자-서지결합법, 동시출현 빈도, 코사인 유사도의 개념을 활용한 문헌정보학 기반의 학술 문헌 추천기법을 제안하고자 하였다. 실험을 위해 수집한 '불평등', '격차' 관련 총 9,643개의 논문 메타데이터를 정제하여 코사인 유사도를 활용한 저자, 키워드, 제목 속성 간의 상대적 좌표 수치를 도출하였고, 성능 좋은 가중치 조건 및 차원의 수를 선정하기 위해 실험을 수행하였다. 실험 결과를 제시하여 이용자의 평가를 거쳤으며, 이를 이용해 기준노드와 추천조합 특성 분석 및 컨조인트 분석, 결과 비교 분석을 수행하여 연구질문 중심의 논의를 수행하였다. 그 결과 전반적으로는 저자 관련 속성을 제한 조합 혹은 제목 관련 속성만 사용하는 경우 성능이 뛰어난 것으로 나타났다. 본 연구에서 제시한 기법을 활용하고 광범위한 표본의 확보를 이룬다면, 향후 정보서비스의 문헌 추천 분야뿐 아니라 사회의 다양한 분야에 대한 추천기법 성능 향상에 도움을 줄 수 있을 것이다.

The purpose of this study is to propose a scholarly paper recommendation system based on metadata attribute similarity with excellent performance. This study suggests a scholarly paper recommendation method that combines techniques from two sub-fields of Library and Information Science, namely metadata use in Information Organization and co-citation analysis, author bibliographic coupling, co-occurrence frequency, and cosine similarity in Bibliometrics. To conduct experiments, a total of 9,643 paper metadata related to "inequality" and "divide" were collected and refined to derive relative coordinate values between author, keyword, and title attributes using cosine similarity. The study then conducted experiments to select weight conditions and dimension numbers that resulted in a good performance. The results were presented and evaluated by users, and based on this, the study conducted discussions centered on the research questions through reference node and recommendation combination characteristic analysis, conjoint analysis, and results from comparative analysis. Overall, the study showed that the performance was excellent when author-related attributes were used alone or in combination with title-related attributes. If the technique proposed in this study is utilized and a wide range of samples are secured, it could help improve the performance of recommendation techniques not only in the field of literature recommendation in information services but also in various other fields in society.

키워드

과제정보

이 논문은 2022년 대한민국 교육부와 한국연구재단의 지원을 받아 수행된 연구임 (NRF-2022S1A5C2A0309359721)

참고문헌

  1. Im, YunJeong, Song, Gyuwon, Cho, MinSang, & Jung, HyunJung (2021). Intelligent export recommendation system based on academic bigdata. Proceedings of the Korean Information Science Society Conference, 111-113.
  2. Ko, Young Man, Song, Min-Sun, & Lee, Seung-Jun (2015). A study on the optimization of semantic relation of author keywords in humanities, social sciences, and art and sport of the Korea Citation Index (KCI). Journal of the Korean Society for Library and Information Science, 49(1), 45-67. http://dx.doi.org/10.4275/KSLIS.2015.49.1.045
  3. Lee, Jae-Yun (2008). Bibliographic author coupling analysis: a new methodological approach for identifying research trends. Journal of the Korea Society for Information Management, 25(1), 173-190. http://dx.doi.org/10.3743/KOSIM.2008.25.1.173
  4. National Research Foundation of Korea (2020). Korea Citation Index(KCI) DB Information. Available: https://www.kci.go.kr/
  5. Park, Dae-Woo, Koh, In Soo, Lee, Nak-Son, & Han, Kyeong-Seok (2020). A study on architecture for bigdata-based book curation system. Jounal of The Korea Society of Information Technology Policy & Management, 12(1), 1559-1565.
  6. Won, Jaesang. (2020). Context-aware recommendation system for literature. Proceedings of the Korean Information Science Society Conference, 1620-1622.
  7. Yeo, Woon-Dong, Park, Hyun-Woo, Kwon, Young-Il, & Park, Young-Wook (2010). Application of research paper recommender system to digital library. The Journal of the Korea Contents Association, 10(11), 10-19. http://dx.doi.org/10.5392/JKCA.2010.10.11.010
  8. Adomavicius, G. & Tuzhilin, A. (2005). Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions. IEEE transactions on knowledge and data engineering, 17(6), 734-749. http://dx.doi.org/10.1109/TKDE.2005.99
  9. Ahmad, S. & Afzal, M. T. (2017). Combining co-citation and metadata for recommending more related papers. 2017 International Conference on Frontiers of Information Technology (FIT). IEEE, 218-222. http://dx.doi.org/10.1109/FIT.2017.00046
  10. Ahmad, S. & Afzal, M. T. (2020). Combining metadata and co-citations for recommending related papers. Turkish Journal of Electrical Engineering & Computer Sciences, 28(3), 1519-1534. https://doi.org/10.3906/elk-1908-19
  11. Alshareef, A. M. (2019). Academic Recommendation System Based on the Similarity Learning of the Citation Network Using Citation Impact. Doctoral dissertation, University of Ottawa. http://dx.doi.org/10.20381/ruor-23359
  12. Beel, J. & Gipp, B. (2009). Google Scholar's ranking algorithm: the impact of citation counts (an empirical study). In 2009 third international conference on research challenges in information science, 439-446. IEEE. http://dx.doi.org/110.1109/RCIS.2009.5089308
  13. Beel, J., Gipp, B., Langer, S., & Breitinger, C. (2016). Paper recommender systems: a literature survey. International Journal on Digital Libraries, 17(4), 305-338. https://doi.org/10.1007/s00799-015-0156-0
  14. Chen, T. T. & Lee, M. (2018). Research paper recommender systems on big scholarly data. In Pacific Rim Knowledge Acquisition Workshop, 251-260. Springer, Cham. https://doi.org/10.1007/978-3-319-97289-3_20
  15. Deldjoo, Y., Dacrema, M. F., Constantin, M. G., Eghbal-Zadeh, H., Cereda, S., Schedl, M., Ionescu, B., & Cremonesi, P. (2019). Movie genome: alleviating new item cold start in movie recommendation. User Modeling and User-Adapted Interaction, 29(2), 291-343. https://doi.org/10.1007/s11257-019-09221-y
  16. Gazni, A. & Didegah, F. (2016). The relationship between authors' bibliographic coupling and citation exchange: analyzing disciplinary differences. Scientometrics, 107(2), 609-626. https://doi.org/10.1007/s11192-016-1856-y
  17. Khan, S., Liu, X., Shakil, K. A., & Alam, M. (2017). A survey on scholarly data: From big data perspective. Information Processing & Management, 53(4), 923-944. https://doi.org/10.1016/j.ipm.2017.03.006
  18. Liling, L. I. U. (2019). Summary of recommendation system development. In Journal of Physics: Conference Series 1187(5), 052044. IOP Publishing. http://dx.doi.org/10.1088/1742-6596/1187/5/052044
  19. Morris, S. A. & Yen, G. G. (2004). Crossmaps: Visualization of overlapping relationships in collections of journal papers. Proceedings of the National Academy of Sciences, 101(Suppl. 1), 5291-5296. https://doi.org/10.1073/pnas.0307604100
  20. Nazir, S., Asif, M., & Ahmad, S. (2020). Exploring the Proportion of Content Represented by the Metadata of Research Articles. In 2020 3rd International Conference on Advancements in Computational Sciences (ICACS), 1-7. IEEE. https://doi.org/10.1109/ICACS47775.2020.9055955
  21. Waheed, W., Imran, M., Raza, B., Malik, A. K., & Khattak, H. A. (2019). A hybrid approach toward research paper recommendation using centrality measures and author ranking. IEEE Access 7, 33145-33158. https://doi.org/10.1109/ACCESS.2019.2900520
  22. Williams, K., Wu, J., Choudhury, S. R., Khabsa, M., & Giles, C. L. (2014). Scholarly big data information extraction and integration in the citeseer χ digital library. In 2014 IEEE 30th International Conference on Data Engineering Workshops, 68-73. IEEE. https://doi.org/10.1109/ICDEW.2014.6818305
  23. Xia, F., Wang, W., Bekele, T. M., & Liu, H. (2017). Big scholarly data: A survey. IEEE Transactions on Big Data, 3(1), 18-35. https://doi.org/10.1109/TBDATA.2016.2641460
  24. Yang, S., Han, R., Wolfram, D., & Zhao, Y. (2016). Visualizing the intellectual structure of information science (2006-2015): Introducing author keyword coupling analysis. Journal of informetrics, 10(1), 132-150. https://doi.org/10.1016/j.joi.2015.12.003