한국산업정보학회논문지 (Journal of Korea Society of Industrial Information Systems)

한국산업정보학회 (Korea Society of Industrial Information Systems)
권호 표지
DOI QR코드

DOI QR Code

소셜네트워크에서 분위기 벡터를 이용한 멀티미디어 콘텐츠 추천 방법

Multimedia Contents Recommendation Method using Mood Vector in Social Networks

  • 문창배 (금오공과대학교 ICT융합특성화연구센터) ;
  • 이종열 (금오공과대학교 컴퓨터소프트웨어공학과) ;
  • 김병만 (금오공과대학교 컴퓨터소프트웨어공학과)
  • 투고 : 2019.08.20
  • 심사 : 2019.10.08
  • 발행 : 2019.12.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

웹에서 정보 구매자들의 성향은 가성비에서 가심비 형태로 변해가는 추세이다. 멀티미디어 콘텐츠 추천에도 그러한 흐름이 있는데, 바로 폭소노미 (Folksonomy) 기반의 분위기를 이용한 추천 방법이다. 하지만 이런 방법의 경우 동의어를 고려하지 못한다는 문제점이 존재한다. 이 문제를 해결하기 위해 일부 연구에서는 Thayer모델의 12 분위기를 AV(Arousal and Valence)값으로 정의하여 그 문제점을 해결하였지만, 추천 성능이 재현 수준 0.1에서 키워드 기반 검색 방법보다 떨어지는 문제점을 보였다. 본 논문에서는 재현 수준 0.1에서도 키워드 기반 검색 방법과 동일한 추천 성능을 유지하면서 동의어 문제를 해결할 수 있도록 멀티미디어 콘텐츠의 분위기 벡터를 이용하는 방법을 제안하였다. 또한, 추천 성능 분석을 위해 기존 AV값 기반 방법과 키워드 기반 방법과 비교 분석하였다. 추천 성능 분석결과, 본 논문에서 제안한 방법이 전체적으로 기존 방법들 보다 우수한 추천 성능을 보였다.

The tendency of buyers of web information is changing from the cost-effectiveness to the cost-satisfaction. There is such tendency in the recommendation of multimedia contents, some of which are folksonomy-based recommendation services using mood. However, there is a problem that they does not consider synonyms. In order to solve this problem, some studies have solved the problem by defining 12 moods of Thayer model as AV values (Arousal and Valence), but the recommendation performance is lower than that of a keyword-based method at the recall level 0.1. In this paper, we propose a method based on using mood vector of multimedia contents. The method can solve the synonym problem while maintaining the same performance as the keyword-based method even at the recall level 0.1. Also, for performance analysis, we compare the proposed method with an existing method based on AV value and a keyword-based method. The result shows that the proposed method outperform the existing methods.

키워드

참고문헌

  1. Chang, E., Kingshy, G., Sychay, G., and Wu, G. (2003). CBSA: Content-Based Soft Annotation for Multimodal Image Retrieval using Bayes Point Machines, IEEE Transactions on Circuits and Systems for Video Technology, 13(1), 26-38. https://doi.org/10.1109/TCSVT.2002.808079
  2. Hevner, K. (1936). Experimental Studies of the Elements of Expression in Music, The American Journal of Psychology, 48(2), 246-268. https://doi.org/10.2307/1415746
  3. Ji, A., Yeon, C., Kim, H., and Jo, G. (2007). Collaborative Tagging in Recommender Systems, Australasian Joint Conference on Artificial Intelligence, pp. 377-386
  4. Kim, J., Lee, S., Kim, S., and Yoo, W. Y. (2011). Music Mood Classification Model based on Arousal-valence Values, Proceedings of 13th International Conference on Advanced Communication Technology (ICACT), pp. 292-295.
  5. Laurier, C., Sordo, M., Serra, J., and Herrera, P. (2009). Music Mood Representations from Social Tags, Proceedings of the 10th International Society for Music Information Conference, Kobe, Japan, pp. 381-386.
  6. Li, J., and Wang, J. Z. (2008). Real-Time Computerized Annotation of Pictures, IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(6), 985-1002. https://doi.org/10.1109/TPAMI.2007.70847
  7. Lindstaedt, S., Morzinger, R., Sorschag, R., Pammer, V., and Thallinger, G. (2009). Automatic Image Annotation using Visual Content and Folksonomies, Multimedia Tools and Applications, 42(1), 97-113. https://doi.org/10.1007/s11042-008-0247-7
  8. Moon, C. B., Kim, H. S., and Kim, B. M. (2013). Music Retrieval Method using Mood Tag and Music AV Tag based on Folksonomy, Journal of The Korean Institute of Information Scientists and Engineers, 40(9), 526-543.
  9. Moon, C. B., Kim, H.S., Lee, H. A., and Kim, B. M., (2014). Analysis of Relationships Between Mood and Color for Different Musical Preferences, Color Research & Application, 39(4), 413-423. https://doi.org/10.1002/col.21806
  10. Moon, C. B., Kim, H.S., Lee, D. W., and Kim, B. M. (2015). Mood Lighting System Reflecting Music Mood, COLOR Research and Application, 40(2), 201-212. https://doi.org/10.1002/col.21864
  11. Moon, C. B., Yi, J. Y., Kim, D.-S., and Kim, B. M. (2018). Analysis of Overlapping Mood Tags Based on Synonyms, Korea Computer Congress 2018 (KCC 2018), June 20-22, Jeju, Korea, pp. 667-669.
  12. Moon, C. B., Lee, J. Y., Kim, D.-S., and Kim, B. M. (2019). Multimedia Content Recommendation in Social Networks using Mood Tags and Synonyms, Multimedia Systems, to be published, 2019.
  13. Moon, C. B., Lee, J. Y., Kim, D.-S., and Kim, B. M. (2019). Analysis of Mood Tags For Music Recommendation, Journal of the Korea Industrial Information Systems Research, 24(1), 13-21. https://doi.org/10.9723/JKSIIS.2019.24.1.013
  14. Ness, S. R., Theocharis, A., Tzanetakis, G., and Martins, L. G. (2019). Improving Automatic Music Tag Annotation using Stacked Generalization of Probabilistic Svm Outputs, Proceedings of the 17th ACM International Conference on Multimedia, pp. 705-708.
  15. Powers, D. (2011). Evaluation: From Precision Recall and f-measure to Roc Informedness Markedness and Correlation, Journal of Machine Learning Technology, 2(1), 37-63.
  16. Russel, J. A. (1980). A Circumplex Model of Affect, Journal of Personality and Social Psychology, 39(6), 1161-1178. https://doi.org/10.1037/h0077714
  17. Thayer, R. E. (1990). The Biopsychology of Mood and Arousal, Oxford University Press.
  18. Tso-Sutter, K., Marinho, L., and Schmidt-Thieme, L. (2008). Tag-aware Recommender Systems by Fusion of Collaborative Filtering Algorithms, ACM Symposium on Applied Computing, pp. 1995-1999.
  19. Vojnovic, M., Cruise, J., Gunawardena, D., and Marbach, P. (2009). Ranking and Suggesting Popular Items, IEEE Transactions on Knowledge and Data Engineering, 21, 1133-1146. https://doi.org/10.1109/TKDE.2009.34
  20. Yang, S., Kim, S., and Ro, Y. M. (2007). Semantic Home Photo Categorization, IEEE Transactions on Circuits and Systems for Video Technology, 17(3), 324-335. https://doi.org/10.1109/TCSVT.2007.890829
  21. Yang, S., Kim, S. K., Seo, K. S., Ro, Y. M., Kim, J., and Seo, Y. S. (2007). Semantic Categorization of Digital Home Photo using Photographic Region Templates, International Journal of Information Processing and Management, 43(2), 503-514. https://doi.org/10.1016/j.ipm.2006.07.009
  22. Yang, S., and Ro, R. M. (2007). Photo Indexing using Person-Based Multi-feature Fusion with Temporal Context, International Conference on Mobile Ubiquitous Computing, Systems, Services and Technologies (UBICOMM'07), pp. 257-262.