DEIM Forum 2016 E1-4 525-8577 1 1-1 E-mail: is0111rs@ed.ritsumei.ac.jp, oku@fc.ritsumei.ac.jp, kawagoe@is.ritsumei.ac.jp 373 1.,, itunes Store 1, Web,., 4,300., [1], [2] [3],,, [4], ( ) [3], [5].,,.,,,, [6]. [6],. EXILE EXILE 1https://www.apple.com/jp/itunes/ EXILE EXILE (a) (b) (c) 2 2
2 3, 4, 5 6 2. [1] [2] [3]., [4], () [3], [5]. Mel Frequency Cepstral Coefficients (MFCC) [9] Logan [4] MFCC MFCC Flexer [10] Bogdanov2010 [3] [14],,,,,, (a) (b) (c) [11] [11] 3. Tada [14] WAV 909 Punk ClassicsPopEasy Listening 15 217 79 909 909 itunes Search API 2 373 3. 1 (1) 373 1 (2) 1 {TT, TF, FT, FF} 2 5 (3) (1)(2) 1 3. 2 2016 12 16 26 373 1 30 11,190 155 1 4 5 1 2 3, 727 4, 031 2https://www.apple.com/itunes/affiliates/resources/documentation/itunesstore-web-service-search-api.html
1 TT TF FT FF TT (1,125) TF (148) FT (1,131) FF (8,786) 2 5 4 3 2 1 4. 3. 4. 1-3. - - (1) u i U a j A TT k ij (2) k ij i j (3) 1 (4) 1 (5) - K K 77 55 - (1) u i U a j A 4 5 r ij (2) r ij i j (3) 1 (4) 1 (5) - R R 107 121 4. 2 - K R 2 1 (1) [13] K -- 20 (2) - a j 20 (3) a j a l sim(a j, a l ) (4) sim(a j, a l ) j l AK (5) AK 2 (v 1, v 2) (6) a j (v 1j, v 2j) v 1j v 1 j 2 1 R 2 5. 4. 5. 1
2 3 u i P i (1) P i (2) a j A 1 u i TT4 5 a j P i (3) (2) 5. 2 5. 1 u i S i (1) S i (2) a j A 1 u i TF FT FF4 5 a j S i (3) S i P i (4) (2) (3) 5. 3 u i 3 P i S i u i TT TF FT FF One-Class SVM u i 4 u i 4 51 2 One-Class SVM u i 3 4 3 FictionJunction YUUKA, KOTOKO, Silent Point 4 u i 6.
4, 2. [1] F. Ricci, L. Rokach, B. Shapira, P.B. Kantor (Eds.), Recommender Systems Handbook, Springer, 2011. [2] Y. Koren, R. Bell, C. Volinsky, Matrix factorization techniques for recommender systems, IEEE Computer 42 (8) (2009) 30 37. [3] D. Bogdanov, M. Haro, F. Fuhrmann, E. Gomez, and P. Herrera, Content-based music recommendation based on user preference examples Categories and Subject Descriptors, in Womrad 2010: The 4th ACM Conference on Recommender Systems. Workshop on Music Recommendation and Discovery, 2010. [4] B. Logan and A. Salomon, A Content-Based Music Similarity Function, 2001. [5] M. Levy and M. Sandler. Music information retrieval using social tags and audio. IEEE Transactions on Multimedia, 11(3):383 395, 2009. [6] :, - Web II -, Vol.25, No.1, pp.2 10, 2013. [7],, and,, in, 2012, vol. 11, no. 2, pp. 23 29. [8] : Vol. 68. No. 1, pp. 16 21, 2012. [9] B. Logan, Mel Frequency Cepstral Coefficients for Music Modeling, in ISMIR 2000:Proceedings of International Symposium on Music Information Retrieval, 2000. [10] A. Flexer, D. Schnitzer, M. Gasser, and G. Widmer, Playlist Generation Using Start and End Songs,in Ninth International Conference on Music Information Retrieval, 2008, pp. 2 7. [11] Y. Hijikata, T. Shimizu, and S. Nishida,Discovery-oriented collaborative filtering for improving user satisfaction, in IUI 2009:Proceedings of the 14th international conference on Intelligent user interfaces, 2009, p. 67 76. [12] Yehuda Koren, Robert Bell, Chris Volinsky, Matrix Factorization Techniques for Recommender Systems, Computer, vol.42, no. 8, pp. 30-37, August 2009, doi:10.1109/mc.2009.263 [13],, 51, 9, 2012 9 [14] Keigo Tada, Ryosuke Yamanishi, Shohei Kato:Interactive Music Recommendation System for Adapting Personal Affection, 11th International Conference on Entertainment Computing, Lecture Notes in Computer Science Vol.7522, pp.417?510, 2012 JSPS 15K12151 (2015-19)