ABSTRACT
Advanced music recommendation systems are being introduced along with the development of machine learning. However, it is essential to design a music recommendation system that can increase user satisfaction by understanding users’ music tastes, not by the complexity of models. Although several studies related to music recommendation systems exploiting negative preferences have shown performance improvements, there was a lack of explanation on how they led to better recommendations. In this work, we analyze the role of negative preference in users’ music tastes by comparing music recommendation models with contrastive learning exploiting preference (CLEP) but with three different training strategies - exploiting preferences of both positive and negative (CLEP-PN), positive only (CLEP-P), and negative only (CLEP-N). We evaluate the effectiveness of the negative preference by validating each system with a small amount of personalized data obtained via survey and further illuminate the possibility of exploiting negative preference in music recommendations. Our experimental results show that CLEP-N outperforms the other two in accuracy and false positive rate. Furthermore, the proposed training strategies produced a consistent tendency regardless of different types of front-end musical feature extractors, proving the stability of the proposed method.
Supplemental Material
- Alejandro Bellogin, Pablo Castells, and Ivan Cantador. 2011. Precision-oriented evaluation of recommender systems: an algorithmic comparison. In Proceedings of the fifth ACM conference on Recommender systems. 333–336.Google ScholarDigital Library
- Dmitry Bogdanov, Minz Won, Philip Tovstogan, Alastair Porter, and Xavier Serra. 2019. The MTG-Jamendo dataset for automatic music tagging. (2019).Google Scholar
- Sungkyun Chang, Seungjin Lee, and Kyogu Lee. 2019. Sequential skip prediction with few-shot in streamed music contents. arXiv preprint arXiv:1901.08203(2019).Google Scholar
- Dennis L Chao, Justin Balthrop, and Stephanie Forrest. 2005. Adaptive radio: achieving consensus using negative preferences. In Proceedings of the 2005 international ACM SIGGROUP conference on Supporting group work. 120–123.Google ScholarDigital Library
- Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A simple framework for contrastive learning of visual representations. In International conference on machine learning. PMLR, 1597–1607.Google Scholar
- Yu-Chih Chen, Yu-Shi Lin, Yu-Chun Shen, and Shou-De Lin. 2013. A modified random walk framework for handling negative ratings and generating explanations. ACM transactions on Intelligent Systems and technology (tISt) 4, 1(2013), 1–21.Google Scholar
- Yen-Liang Chen, Yi-Hsin Yeh, and Man-Rong Ma. 2021. A movie recommendation method based on users’ positive and negative profiles. Information Processing & Management 58, 3 (2021), 102531.Google ScholarDigital Library
- Keunwoo Choi, György Fazekas, Mark Sandler, and Kyunghyun Cho. 2017. Convolutional recurrent neural networks for music classification. In 2017 IEEE International conference on acoustics, speech and signal processing (ICASSP). IEEE, 2392–2396.Google ScholarDigital Library
- Maarten Clements, Arjen P de Vries, and Marcel JT Reinders. 2009. Exploiting positive and negative graded relevance assessments for content recommendation. In International Workshop on Algorithms and Models for the Web-Graph. Springer, 155–166.Google ScholarDigital Library
- Yashar Deldjoo, Markus Schedl, and Peter Knees. 2021. Content-driven music recommendation: Evolution, state of the art, and challenges. arXiv preprint arXiv:2107.11803(2021).Google Scholar
- Prafulla Dhariwal, Heewoo Jun, Christine Payne, Jong Wook Kim, Alec Radford, and Ilya Sutskever. 2020. Jukebox: A generative model for music. arXiv preprint arXiv:2005.00341(2020).Google Scholar
- Andres Ferraro, Dmitry Bogdanov, and Xavier Serra. 2019. Skip prediction using boosting trees based on acoustic features of tracks in sessions. arXiv preprint arXiv:1903.11833(2019).Google Scholar
- Susan Gauch, Mirco Speretta, Aravind Chandramouli, and Alessandro Micarelli. 2007. User profiles for personalized information access. The adaptive web (2007), 54–89.Google Scholar
- Jonathan L Herlocker, Joseph A Konstan, Loren G Terveen, and John T Riedl. 2004. Evaluating collaborative filtering recommender systems. ACM Transactions on Information Systems (TOIS) 22, 1 (2004), 5–53.Google ScholarDigital Library
- Yifan Hu, Yehuda Koren, and Chris Volinsky. 2008. Collaborative filtering for implicit feedback datasets. In 2008 Eighth IEEE international conference on data mining. Ieee, 263–272.Google ScholarDigital Library
- Gawesh Jawaheer, Martin Szomszor, and Patty Kostkova. 2010. Comparison of implicit and explicit feedback from an online music recommendation service. In proceedings of the 1st international workshop on information heterogeneity and fusion in recommender systems. 47–51.Google ScholarDigital Library
- Marius Kaminskas and Francesco Ricci. 2012. Contextual music information retrieval and recommendation: State of the art and challenges. Computer Science Review 6, 2-3 (2012), 89–119.Google ScholarCross Ref
- Diane Kelly and Jaime Teevan. 2003. Implicit feedback for inferring user preference: a bibliography. In Acm Sigir Forum, Vol. 37. ACM New York, NY, USA, 18–28.Google Scholar
- Gregory Koch, Richard Zemel, Ruslan Salakhutdinov, 2015. Siamese neural networks for one-shot image recognition. In ICML deep learning workshop, Vol. 2. Lille, 0.Google Scholar
- Noam Koenigstein. 2017. Rethinking Collaborative Filtering: A Practical Perspective on State-of-the-art Research Based on Real World Insights. In Proceedings of the Eleventh ACM Conference on Recommender Systems. 336–337.Google ScholarDigital Library
- Junghyun Koo, Seungryeol Paik, and Kyogu Lee. 2022. End-to-end Music Remastering System Using Self-supervised and Adversarial Training. arXiv preprint arXiv:2202.08520(2022).Google Scholar
- Denis Kotkov, Shuaiqiang Wang, and Jari Veijalainen. 2016. A survey of serendipity in recommender systems. Knowledge-Based Systems 111 (2016), 180–192.Google ScholarDigital Library
- Edith Law, Kris West, Michael I Mandel, Mert Bay, and J Stephen Downie. 2009. Evaluation of algorithms using games: The case of music tagging.. In ISMIR. 387–392.Google Scholar
- Danielle H Lee and Peter Brusilovsky. 2009. Reinforcing recommendation using implicit negative feedback. In International conference on user modeling, adaptation, and personalization. Springer, 422–427.Google ScholarDigital Library
- Ning-Han Liu. 2013. Comparison of content-based music recommendation using different distance estimation methods. Applied intelligence 38, 2 (2013), 160–174.Google Scholar
- Hongyu Lu, Min Zhang, and Shaoping Ma. 2018. Between clicks and satisfaction: Study on multi-phase user preferences and satisfaction for online news reading. In The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval. 435–444.Google ScholarDigital Library
- Elisa Mena-Maldonado, Rocío Cañamares, Pablo Castells, Yongli Ren, and Mark Sanderson. 2020. Agreement and disagreement between true and false-positive metrics in recommender systems evaluation. In Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. 841–850.Google ScholarDigital Library
- Nicola Montecchio, Pierre Roy, and François Pachet. 2020. The skipping behavior of users of music streaming services and its relation to musical structure. Plos one 15, 9 (2020), e0239418.Google ScholarCross Ref
- Elias Pampalk, Tim Pohle, and Gerhard Widmer. 2005. Dynamic Playlist Generation Based on Skipping Behavior.. In ISMIR, Vol. 5. 634–637.Google Scholar
- Isabelle Peretz, Danielle Gaudreau, and Anne-Marie Bonnel. 1998. Exposure effects on music preference and recognition. Memory & cognition 26, 5 (1998), 884–902.Google Scholar
- Jordi Pons and Xavier Serra. 2019. musicnn: Pre-trained convolutional neural networks for music audio tagging. arXiv preprint arXiv:1909.06654(2019).Google Scholar
- Ali Razavi, Aaron Van den Oord, and Oriol Vinyals. 2019. Generating diverse high-fidelity images with vq-vae-2. Advances in neural information processing systems 32 (2019).Google Scholar
- Pablo Sánchez and Alejandro Bellogín. 2018. Measuring anti-relevance: a study on when recommendation algorithms produce bad suggestions. In Proceedings of the 12th ACM Conference on Recommender Systems. 367–371.Google ScholarDigital Library
- Markus Schedl. 2019. Deep learning in music recommendation systems. Frontiers in Applied Mathematics and Statistics (2019), 44.Google Scholar
- Guy Shani and Asela Gunawardana. 2011. Evaluating recommendation systems. In Recommender systems handbook. Springer, 257–297.Google Scholar
- Janne Spijkervet and John Ashley Burgoyne. 2021. Contrastive learning of musical representations. arXiv preprint arXiv:2103.09410(2021).Google Scholar
- Aaron Van den Oord, Sander Dieleman, and Benjamin Schrauwen. 2013. Deep content-based music recommendation. Advances in neural information processing systems 26 (2013).Google Scholar
- Aaron Van Den Oord, Oriol Vinyals, 2017. Neural discrete representation learning. Advances in neural information processing systems 30 (2017).Google Scholar
- Yongfeng Zhang, Xu Chen, 2020. Explainable recommendation: A survey and new perspectives. Foundations and Trends® in Information Retrieval 14, 1(2020), 1–101.Google Scholar
Index Terms
- Exploiting Negative Preference in Content-based Music Recommendation with Contrastive Learning
Recommendations
Personalized Recommendations for Music Genre Exploration
UMAP '19: Proceedings of the 27th ACM Conference on User Modeling, Adaptation and PersonalizationMost recommender systems generate recommendations to match the user's current preference. However, users sometimes might have the goal to develop new preferences away from their current preference and use the recommender to guide them towards it. In ...
Contrastive Learning for Cold-Start Recommendation
MM '21: Proceedings of the 29th ACM International Conference on MultimediaRecommending purely cold-start items is a long-standing and fundamental challenge in the recommender systems. Without any historical interaction on cold-start items, the collaborative filtering (CF) scheme fails to leverage collaborative signals to ...
Exploiting non-content preference attributes through hybrid recommendation method
RecSys '13: Proceedings of the 7th ACM conference on Recommender systemsThis paper explores a method for incorporating into a recommender system explicit representations of user's preferences over non-content attributes such as popularity, recency, and similarity of recommended items. We show how such attributes can be ...
Comments