Journal of Korea Society of Industrial Information Systems (한국산업정보학회논문지)

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

DOI QR Code

Analysis of Mood Tags For Music Recommendation

음악추천을 위한 분위기 태그 분석

  • 문창배 (금오공과대학교 ICT융합특성화연구센터) ;
  • 이종열 (금오공과대학교 컴퓨터소프트웨어공학과) ;
  • 김동성 (금오공과대학교 IT 융복합공학과) ;
  • 김병만 (금오공과대학교 컴퓨터소프트웨어공학과)
  • Received : 2018.11.08
  • Accepted : 2018.12.28
  • Published : 2019.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

The tendency of buyers of web information is changing from the cost-effectiveness which emphasizes the performance over the price to the cost-satisfaction which emphasizes the psychological satisfaction of the buyer. In music recommendation, one of the methods to increase psychological satisfaction is to use the music mood. In this paper, a music recommendation method considering the mood tag and the synonyms tag is proposed and, as an intermediate result of the proposed method, mood tags and music pieces are expressed in Thayer's AV space and then their distribution are analyzed. The analysis result shows the distributions of mood tags and the ones of music pieces are similar, which implies that the proposed recommendation method can provide significant results. In the future, the music recommendation performance will be analyzed.

웹 정보 구매자들의 성향은 가격대 성능을 중요시하는 가성비에서 구매자의 심리적 만족감을 높이는 가심비 형태로 변해가는 추세이다. 음악 추천에 있어 심리적 만족감을 높이는 방법 중 한 가지는 음악의 분위기를 이용하는 것이다. 본 논문에서는 가심비를 높이기 위한 방법으로 분위기 태그와 태그의 동의어를 고려한 음악 추천 방법을 제안하고, 제안한 방법의 중간 결과로 분위기 태그와 음악을 Thayer의 AV 공간으로 표현한 후 그 분포 특성을 분석하였다. 분석결과, 분위기 태그의 분포와 음악의 분위기 분포가 크게 다르지 않음을 알 수 있었는데, 이는 제안한 추천 방법이 유의한 결과를 도출할 수 있을 것으로 보인다. 향후 분석된 결과를 바탕으로 추천 성능을 도출할 계획이다.

Keywords

SOJBB3_2019_v24n1_13_f0001.png 이미지

Fig. 1 Thayer’s Two-Dimensional Model

SOJBB3_2019_v24n1_13_f0002.png 이미지

Fig. 2 Music Recommendation Structure

SOJBB3_2019_v24n1_13_f0003.png 이미지

Fig. 3 Music Information Construction Process

SOJBB3_2019_v24n1_13_f0004.png 이미지

Fig. 4 Request and Response for Music List of Mood Tag

SOJBB3_2019_v24n1_13_f0005.png 이미지

Fig. 5 Request and Response for Music Tag and Tag Count

SOJBB3_2019_v24n1_13_f0006.png 이미지

Fig. 6 An Example of 12-Mood Distribution of a Music Piece

SOJBB3_2019_v24n1_13_f0007.png 이미지

Fig. 7 Tag-AV Table Creation Process

SOJBB3_2019_v24n1_13_f0008.png 이미지

Fig. 8 Music Recommendation Method using Music-AV Table and Tag-AV Table

SOJBB3_2019_v24n1_13_f0009.png 이미지

Fig. 9 Tag-AV Table Analysis

SOJBB3_2019_v24n1_13_f0010.png 이미지

Fig. 10 Music-AV Table Analysis (MIHT :Musics Including Happy Tag)

Table 1 Synonym Mapping Table

SOJBB3_2019_v24n1_13_t0001.png 이미지

References

  1. Moon, C. B., Yi, J. Y., Kim, D.-S., Kim, B. M., "Analysis of Overlapping Mood Tags Based on Synonyms," Korea Computer Congress 2018 (KCC 2018), KIISE, (2018) June 20-22; ICC JEJU, Korea, Vol. 2018, No. 6, pp. 667-669, 2018.
  2. Russel, J. A., "A Circumplex Model of Affect," Journal of Personality and Social Psychology, Vol. 39, No. 6, pp. 1161-1178, 1980. https://doi.org/10.1037/h0077714
  3. Hevner, K., "Experimental Studies of the Elements of Expression in Music," The American Journal of Psychology, Vol. 48, No. 2, pp. 246-268, 1936. https://doi.org/10.2307/1415746
  4. Thayer, R. E., "The Biopsychology of Mood and Arousal," Oxford University Press, 1990.
  5. Moon, C. B., Kim, H. S., Kim, B. M., "Music Retrieval Method using Mood Tag and Music AV Tag based on Folksonomy," Journal of KIISE, Vol. 40, No. 9, pp. 526-543, 2013.
  6. Moon, C. B., Kim, H.S., Lee, H. A., Kim, B. M., "Analysis of Relationships Between Mood and Color for Different Musical Preferences," Color Research and Application, Vol. 39, No. 4, pp. 413-423, 2014. https://doi.org/10.1002/col.21806
  7. Moon, C. B., Kim, H.S., Lee, D. W., Kim, B. M., "Mood Lighting System Reflecting Music Mood," COLOR Research and Application, Vol. 40, No. 2, pp. 201-212, 2015. https://doi.org/10.1002/col.21864
  8. Cha, J. Y., Moon, J. Y., "A Meta-Analysis of the Music Therapy Research to Reduces Depression," The Korean Journal of Arts Studies, No. 11, pp. 193-224, 2015.
  9. Kim, J.A., "THE CURRENT TRENDS OF BRITISH MUSIC THERAPY & TWO CASE STUDIES OF AUTISTIC CHILDREN," Korean J Child & Adol Psychiatr, Vol. 8, No. 1, pp. 123-132, 1997.
  10. Han, B.J., Hwang, E.J., "Emotion Transition Model based Music Classification Scheme for Music Recommendation," Journal of IKEEE, Vol. 13. No. 2, pp. 59-66, 2017.
  11. Ness, S. R., Theocharis, A., Tzanetakis, G. and Martins, L. G., "Improving Automatic Music Tag Annotation using Stacked Generalization of Probabilistic Svm Outputs," Proc. of the 17th ACM International Conference on Multimedia, pp. 705-708, 2009.
  12. Laurier, C., Sordo, M., Serra, J. and Herrera, P., "Music Mood Representations from Social Tags," Proc. of the 10th International Society for Music Information Conference, Kobe, Japan, pp. 381-386, 2009.
  13. Kim, J., Lee, S., Kim, S. and Yoo, W. Y., "Music Mood Classification Model Based on Arousal-valence Values," Proc. of 13th International Conference on Advanced Communication Technology (ICACT), pp. 292-295, 2011.

Cited by

  1. 소셜네트워크에서 분위기 벡터를 이용한 멀티미디어 콘텐츠 추천 방법 vol.24, pp.6, 2019, https://doi.org/10.9723/jksiis.2019.24.6.011