Journal of Digital Convergence (디지털융복합연구)

The Society of Digital Policy and Management (한국디지털정책학회)
권호 표지
DOI QR코드

DOI QR Code

A Movie Recommendation System based on Fuzzy-AHP and Word2vec

Fuzzy-AHP와 Word2Vec 학습 기법을 이용한 영화 추천 시스템

  • Oh, Jae-Taek (Department of Computer Science & Engineering, Kongju National University) ;
  • Lee, Sang-Yong (Division of Computer Science & Engineering, Kongju National University)
  • 오재택 (공주대학교 컴퓨터공학과) ;
  • 이상용 (공주대학교 컴퓨터공학부)
  • Received : 2019.11.08
  • Accepted : 2020.01.20
  • Published : 2020.01.28
Download PDF
⟨ Previous Next ⟩

Abstract

In recent years, a recommendation system is introduced in many different fields with the beginning of the 5G era and making a considerably prominent appearance mainly in books, movies, and music. In such a recommendation system, however, the preference degrees of users are subjective and uncertain, which means that it is difficult to provide accurate recommendation service. There should be huge amounts of learning data and more accurate estimation technologies in order to improve the performance of a recommendation system. Trying to solve this problem, this study proposed a movie recommendation system based on Fuzzy-AHP and Word2vec. The proposed system used Fuzzy-AHP to make objective predictions about user preference and Word2vec to classify scraped data. The performance of the system was assessed by measuring the accuracy of Word2vec outcomes based on grid search and comparing movie ratings predicted by the system with those by the audience. The results show that the optimal accuracy of cross validation was 91.4%, which means excellent performance. The differences in move ratings between the system and the audience were compared with the Fuzzy-AHP system, and it was superior at approximately 10%.

최근 추천 시스템은 5G 시대의 시작과 동시에 여러 분야에서 도입하고 있으며, 주로 도서나 영화, 음악 분야의 서비스에서 크게 두각을 나타내고 있다. 그러나 이러한 추천 시스템에서 사용자마다 선호하는 정도가 주관적이고, 불확실하여 정확한 추천 서비스를 제공하기가 어렵다. 추천 시스템의 성능을 향상시키기 위해서는 많은 양의 학습 데이터가 필요하며, 추론 기술이 보다 정확해야 한다. 이러한 문제점을 해결하기 위하여 본 연구에서는 Fuzzy-AHP와 Word2Vec 학습 기법을 이용한 영화 추천 시스템을 제안하였다. 본 시스템에서는 사용자의 선호도를 객관적으로 예측하기 위해 Fuzzy-AHP를 사용하였으며, 스크레이핑한 데이터를 분류하기 위해 Word2Vec 학습 기법을 사용하였다. 본 시스템의 성능을 평가하기 위해 그리드 서치를 이용하여 Word2Vec 학습 결과의 정확도를 측정하였고, 그 후 본 시스템이 예측한 평점과 관객들이 평가한 영화의 평점 간 차이를 비교하였다. 그 결과 최적의 교차 검증 정확도가 91.4%로 우수한 성능을 나타내었으며, 예측한 평점과 관객들이 평가한 영화의 평점 간 차이를 Fuzzy-AHP 시스템과 비교한 결과 10% 정도 우수함을 확인할 수 있었다.

Keywords

References

  1. Domo, Inc. (2019). Data Never Sleeps 6.0. https://www.domo.com/learn/data-never-sleeps-6
  2. F. T. S. Chan & N. Kumar. (2007). Global Supplier Development Considering Risk Factors using Fuzzy Extended AHP-based Approach. Original Research Article Omega, 35(4), 417-431.
  3. C. Lin & P. J. Hsieh. (2004). A Fuzzy Decision Support System for Strategic Portfolio Management. Decision Support Systems, 38(2004), 383-398. https://doi.org/10.1016/S0167-9236(03)00118-0
  4. B. Kaluza. (2016). Machine Learning in Java. Seoul: Acorn.
  5. C. M. Kwon. (2019). Python Machine Learning Perfect Guide. Paju: Wikibooks.
  6. S. K. Gorakala. (2017). Building Recommendation Engines. Seoul: Acorn.
  7. S. H. Park, D. H. Kim, H. J. Cho & J. W. Kim. (2019). Music Therapy Counseling Recommendation Model Based on Collaborative Filtering. Journal of the Korea Convergence Society, 10(9), 31-36.
  8. S. J. Park, Y. M. Kim & J. J. Ahn. (2019). Development of Product Recommender System using Collaborative Filtering and Stacking Model. Journal of Convergence for Information Technology, 9(6), 83-90. https://doi.org/10.22156/CS4SMB.2019.9.6.083
  9. B. S. Kim. (2017). How does Naver AI Recommended System 'AiRs' Operate? Collaborative Filtering?. Chosunbiz. http://biz.chosun.com/site/data/html_dir/2017/04/08/2017040800549
  10. S. J. Lee. (2019). Since I introduced AI to Naver news, page views have increased. Business Watch. https://m.post.naver.com/viewer/postView.nhn?volumeNo=18935104&memberNo=997329&vType=VERTICAL
  11. S. Wang, C. Li, K. Zhao & H. Chen. (2017). Learning to Context-aware Recommend with Hierarchical Factorization Machines. Information Sciences, 409-410(2017), 121-138. https://doi.org/10.1016/j.ins.2017.05.015
  12. M. Ahmed, M. T. Imtiaz & R. Khan. (2018). Movie Recommendation System using Clustering and Pattern Recognition Network. 2018 IEEE 8th Annual Computing and Communication Workshop and Conference, 1-5.
  13. Y. S. Jeong. (2019). Machine Learning Based Domain Classification for Korean Dialog System. Journal of Convergence for Information Technology, 9(8), 1-8. https://doi.org/10.22156/CS4SMB.2019.9.8.001
  14. X. H. Ding, Q. Xie, Y. J. Jang & T. S. Yun. (2019). Usability Evaluation Model for Locomotion Technology in VR Space. Journal of the Korea Convergence Society, 10(9), 1-9. https://doi.org/10.15207/JKCS.2019.10.9.001
  15. E. Kinoshita & T. Oya. (2012). Strategic Decision-making Technique AHP. Seoul: Cheongram.
  16. R. S. Chaulagain, S. Pandey, S. R. Basnet & S. Shakya. (2017). Cloud based Web Scraping for Big Data Applications. 2017 IEEE International Conference on Smart Cloud, 1-6.
  17. K. Kato. (2018). Web Crawling and Scraping with Python. Paju: Wikibooks.
  18. K. Hikodukue. (2017). Introduction to the Practical Development of Machine Learning and Deep Learning using Python. Paju: Wikibooks.
  19. T. Hope, Y. S. Resheff & I. Lieder. (2018). Learning TensorFlow. Seoul: Hanbit Media.
  20. S. Y. Kim & Y. J. Jung. (2017). Machine Learning for the First Time. Seoul: Hanbit Media.
  21. N. Buduma. (2018). Fundamentals of Deep Learning. Seoul: Hanbit Media.
  22. F. Yin, Y. Wang, X. Pan & P. Su. (2018). A Word based Review Vector Method for Sentiment Analysis of Movie Reviews Exploring the Applicability of the Movie Reviews. 2018 3rd International Conference on Computational Intelligence and Applications, 1-6.
  23. Y. C. Yoon & J. W. Lee. (2018). Movie Recommendation using Metadata based Word2vec Algorithm. 2018 International Conference on Platform Technology and Service, 1-5.
  24. S. K. Reddy, V. Swaminathan & C. M. Motley. (1998). Exploring the Determinants of Broadway Show Success. Journal of Marketing Research, 17(6), 296-315.
  25. Kakao Corp. (2019). Daum Movie. https://movie.daum.net
  26. A. C. Muller, S. Guido. (2019). Introduction to Machine Learning with Python. Seoul: Hanbit Media.
  27. T. Okatani. (2017). Getting started with Deep Learning. Paju: Jpub.