Multi Criteria Recommender System for Music using K-Nearest Neighbors and Weighted Product Method
Abstract views: 285
,
575 downloads: 210
Abstract
Currently, the music industry has grown rapidly which has led to an information overload that hinders users from finding the music they want, because everyone has their own unique characteristics. In a previous study, the Recommender System converted music lyrics into digital values using Lexicon's Non-Commercial Research (NRC) and K Nearest Neighbors (KNN) to look for similarities between music. However, this system only uses lyrics to recommend music, so it doesn't pay more attention to user preferences. Therefore, in this study adds criteria from users using the Weighted Product Method (WPM) to weight the music criteria with the input criteria from users. In this study uses a music dataset from 2000 to 2019 taken from the Kaggle website. The purpose of this study was to measure user satisfaction using the System Usability Scale (SUS). In this case, the user is free to answer 10 questions regarding the results of the recommendations provided by the system. Based on the results of the questionnaire, the SUS score was 83.65. This score is included in the EXCELLENT category with grade A scale
Downloads
References
[2] G. Dror, N. Koenigstein, and Y. Koren, “Yahoo! music recommendations: Modeling music ratings with temporal dynamics and item taxonomy,†2011, doi: 10.1145/2043932.2043964.
[3] F. Hdioud, B. Frikh, and B. Ouhbi, “Bootstrapping recommender systems based on a multi-criteria decision making approach,†2014, doi: 10.1109/NGNS.2014.6990254.
[4] J. Choi, J. H. Song, and Y. Kim, “An analysis of music lyrics by measuring the distance of emotion and sentiment,†2018, doi: 10.1109/SNPD.2018.8441085.
[5] D. M. Khairina, M. R. Asrian, and H. R. Hatta, “Decision support system for new employee recruitment using weighted product method,†2017, doi: 10.1109/ICITACEE.2016.7892459.
[6] F. Alyari and N. Jafari Navimipour, “Recommender systems: A systematic review of the state of the art literature and suggestions for future research,†Kybernetes. 2018, doi: 10.1108/K-06-2017-0196.
[7] G. Adomavicius and Y. Kwon, “Multi-criteria recommender systems,†in Recommender Systems Handbook, Second Edition, 2015.
[8] “A Multi-Criteria Collaborative Filtering Recommender System Using Clustering and Regression Techniques,†J. Soft Comput. Decis. Support Syst., 2016.
[9] J. R. S. C. Mateo, “Multi-Criteria Analysis in the Renewable Energy Industry,†2012, doi: 10.1007/978-1-4471-2346-0.
[10] F. Hdioud, B. Frikh, B. Ouhbi, and I. Khalil, “Multi-criteria recommender systems: A survey and a method to learn new user’s profile,†Int. J. Mob. Comput. Multimed. Commun., 2017, doi: 10.4018/IJMCMC.2017100102.
[11] R. R. Padovani, L. N. Ferreira, and L. H. S. Lelis, “Bardo: Emotion-based music recommendation for tabletop role-playing games,†2017.
[12] R. Ahuja, A. Solanki, and A. Nayyar, “Movie recommender system using k-means clustering and k-nearest neighbor,†2019, doi: 10.1109/CONFLUENCE.2019.8776969.
[13] V. Subramaniyaswamy and R. Logesh, “Adaptive KNN based Recommender System through Mining of User Preferences,†Wirel. Pers. Commun., 2017, doi: 10.1007/s11277-017-4605-5.
[14] J. R. Lewis Senior HF Engineer and J. Sauro, “Revisiting the Factor Structure of the System Usability Scale,†2017.
[15] A. Novelty Octaviani Faomasi Daeli, “Sentiment Analysis on Movie Reviews Using Information Gain and K-Nearest Neighbor,†J. Data Sci. Its Appl., vol. 3, no. 1, 2020.
[16] H. Supriyono and C. P. Sari, “Developing decision support systems using the weighted product method for house selection,†2018, doi: 10.1063/1.5042905.
[17] M. Braunhofer, M. Elahi, and F. Ricci, “Usability assessment of a context-aware and personality-based mobile recommender system,†in Lecture Notes in Business Information Processing, 2014, vol. 188, pp. 77–88, doi: 10.1007/978-3-319-10491-1_9.
Copyright (c) 2021 Muhamad Hafidh Nofal, zk abdurahman baizal, Ramanti Dharayani
This work is licensed under a Creative Commons Attribution 4.0 International License.
- Manuscript submitted to IndoJC has to be an original work of the author(s), contains no element of plagiarism, and has never been published or is not being considered for publication in other journals.Â
- Copyright on any article is retained by the author(s). Regarding copyright transfers please see below.
- Authors grant IndoJC a license to publish the article and identify itself as the original publisher.
- Authors grant IndoJC commercial rights to produce hardcopy volumes of the journal for sale to libraries and individuals.
- Authors grant any third party the right to use the article freely as long as its original authors and citation details are identified.
- The article and any associated published material is distributed under the Creative Commons Attribution 4.0License
