プライミング効果を用いた音楽の印象変容に関する基礎調査

全文

(1)Vol.2018-HCI-177 No.13 2018/3/16. IPSJ SIG Technical Report. †1. †1. †1. †1. †1. ) ). 1. PC. [5]. Web 1. ) 2016 ). 42.7%. [1]. YouTube. ) ). Web. ) ). ) [2]. ). ). ) [6] Web [3]. [7] ). [4] †1 Meiji University. 2018 Information Processing Society of Japan. 1.

(2) Vol.2018-HCI-177 No.13 2018/3/16. IPSJ SIG Technical Report. [5]. ) [11] ) ) [12] ). ). [6]. 2. [2] ) ). Morris Bogdanov Levy. [7]. Web. [8]. [9] Koren. [10]. ). ) ). ). 3. Herlocker. [3]. ) 4 5 3.1. ). [4] ) ). 2018 Information Processing Society of Japan. Web. 2.

(3) Vol.2018-HCI-177 No.13 2018/3/16. IPSJ SIG Technical Report 1, 2. 1. 1 C6. ). -2 Valence. ). C1 +2. ). ). -2. +2. Arousal. -2. +2. ) 4. 5. 5 30. 2. ) -2. ) 1. ). +2. 5. ) 1. 8. C1. C2. C3. 1. C4. C5. C6. ,. Valence. Arousal. 3.3. 2 [15] http://nkmr.io/mood/. 3.2 8 VOCALOID. ) 8. 8 MIREX[13] Valence-Arousal. 5. ). 2012. 500. Russel [14]. [15]. ) 8. 2018 Information Processing Society of Japan. 3.

(4) Vol.2018-HCI-177 No.13 2018/3/16. IPSJ SIG Technical Report BPM. Songle http://songle.jp/. ) 500. 8. [16]. k-means. 500. 50. 2 100 Songle 30 30 VOCALOID. 4. 3. 50 ) ). 4.1 1. ) API ) ). 1. ). 4.3 4.2. 4 3 4. ) ) 5. 3 20. 15. 1. 100. 4 ) 4.4 3. 15. 100 1,500. 5 300 4 2. 3. 0.1 V. 2018 Information Processing Society of Japan. 4. Valence. A. Arousal. 4.

(5) Vol.2018-HCI-177 No.13 2018/3/16. IPSJ SIG Technical Report. 5. 4. 5.1 4. 4 2. C1. C2. C3. C4. C5. C6. V. 2. A. -0.050 0.007 0.053 0.017 -0.023 0.057 0.000 -0.103 0.000 -0.067 -0.043 0.020 0.067 0.033 -0.043 -0.027 -0.130 -0.077 -0.007 -0.080 0.143 -0.090 0.020 0.107 -0.003 -0.153 -0.010 0.013 0.100 -0.030 0.000 0.007 0.050 0.037 -0.117 0.000. 2. ) 5.2 2. t. 5. 5% C3. C6. C2. 4 Arousal 0.1 4.5. 5. 4 0.1. Arousal. 100 100 5 S A B C D. 2018 Information Processing Society of Japan. 5.

(6) Vol.2018-HCI-177 No.13 2018/3/16. IPSJ SIG Technical Report Valence-Arousal. [14] Valence. Arousal 5 Valence-Arousal. 5.3 3 3 ) 3. 6 4 20. 18. 1. 200. 3. C1. C2. C3. C4. C5. C6. V. A. 0.044 0.083 -0.057 0.081 -0.022 0.038 0.063 0.037 0.033 0.039 0.097 -0.126 0.133 -0.036 0.097 0.061 0.077 -0.013. 5.4. 0.036 0.022 0.003 0.068 -0.007 0.059 0.049 0.076 0.092. 18. 200 3,600. 5. 4 900 6 3. 3. ) S A B C D. 0.1 0.1. A. C. t. ). 100. 5% V. Valence. A. ). Arousal. ). 40 4. 6. t. 3 C3. 5%. C4 4 0.175 Valence. 2018 Information Processing Society of Japan. C2 0.219. 0.206. 6.

(7) Vol.2018-HCI-177 No.13 2018/3/16. IPSJ SIG Technical Report 4. C1. C2. C3. C4. C5. C6. V. A. 0.089 0.175 -0.117 0.133 -0.047 0.075 0.219 0.031 0.206. ). -0.022 0.025 -0.061 0.050 -0.067 0.028 -0.028 0.039 -0.086. ) ). 5 4 100. ). ). ). 2 43. ) 26. 57 6.2. 22 5. C3. 6 C4 C4. Valence C4. t. Arousal. C3. 5% 5. C4. 0.191 Valence. 0.137 C4. C3. C3. 6 0.201 Arousal. ). 0.160 ). 0.185. 5. C1. C2. C3. C4. C5. C6. V. A. 0.106 0.093 -0.137 0.191 -0.021 0.101 0.137 0.119 0.039 -0.030 0.073 0.056 0.030 -0.098 0.184 -0.026 -0.043 0.056. C3. 6. C1. C2. C3. C4. C5. C6. V. A. C4. 6.3. 0.086 0.111 -0.185 0.201 -0.019 0.041 0.092 0.160 -0.025 -0.101 0.051 -0.076 -0.010 -0.020 0.086 0.051 -0.035 -0.061. 7. 6.. 0.5. 6 7. 6.1. C2. Valence. 2018 Information Processing Society of Japan. 7.

(8) Vol.2018-HCI-177 No.13 2018/3/16. IPSJ SIG Technical Report 4.. 7 [5] I hate to love you like this So, I won't lo... [6]. [7] I was dead. ) ). [8]. 7.. [9]. [10]. [11]. [12]. [13]. [14]. 0.2 [15]. ) [16]. ,. ,. .. . , 2013, vol. 25, no. 1, p. 511-123. , . . ARG Web , 2017, vol. 10. Morris R, Dontcheva M and Geber E. Priming for Better Performance in Microtask Crowdsourcing Environments. IEEE Internet Computing, 2012, vol. 16, no. 5, p. 13-19. D. Bogdanov, M. Haro, F. Fuhrmann, E. Gomez, and P.Herrera. Content-based music recommendation based on user preference examples. The 4th ACM Conference on Recommender Systems. Workshop on Music Recommendation and Discovery, 2010. M. Levy and M. Sandler. Music information retrieval using social tags and audio. IEEE Transactions on Multimedia, 2009, vol. 11, no. 3, p. 383-395. Y. Koren, R. Bell, C. Volinsky. Matrix factorization techniques for recommender systems. IEEE Computer, 2009, vol. 42, no. 8, p. 3037. , , , , , , . : . , 2010, vol. 51, no. 8, p. 1452-1468. , , . . DICOMO2016 , 2016, p. 1621-1627. Hu, X., Downie, J., Laurier, C., Bay, M. and Ehmann, A.. The 2007 MIREX audio mood classification task: Lessons learned, Proc. 9th International Conference on Music Information Retrieval, 2008, p. 462-467. Russell, James A. A circumplex model of affect, Journal of Personality and Social Psychology, 1980, vol. 39, no. 6, p. 11611178. , , , . . DEIM Form 2016 E3-5, 2016, p. 1-8. , , . . , 2004, vol. 111, p. 125-130.. ). JST ACCEL JPMJAC1602. [1]. 2016 , http://www.riaj.or.jp/f/report/mediauser/2016.html, (2017/12/09 ). [2] , , , , . . , 2005, vol. 4, no. 2, p. 275-276. [3] Jonathan L. Herlocker, Joseph A. Konstan, Loren G. Terveen, and John T. Riedl. Evaluating collaborative filtering recommender systems. ACM Transactions on Information Systems(TOIS), 2004, vol. 22, no. 1, p. 5-53. [4] , , . . 8 (DEIM 2016), 2016, p. 3-. 2018 Information Processing Society of Japan. 8.

(9)