ABSTRACT
Music recommender systems (RS) aim to aid people with finding relevant enjoyable music without having to sort through the enormous amount of available content. Music RS often rely on collaborative filtering methods, which however limits predicting capabilities in cold-start situations or for users who deviate from main-stream music preferences. Therefore, this paper evaluates various content-based music recommendation methods that may be used in combination with collaborative filtering to overcome such issues. Specifically, the paper focuses on the ability of lyrics-based embedding methods such as tf-idf, word2vec or bert to estimate songs similarity compared to state-of-the-art audio and meta-data based embeddings. Results indicate that both audio and lyrics methods perform similarly, which may favor lyrics-based approaches due to the much simpler processing. We also show that although lyrics-based methods do not outperform meta-data based approaches, they provide much more diverse, yet reasonably relevant recommendations, which is suitable in exploration-oriented music RS.
- Shahin Amiriparian, Michael Freitag, Nicholas Cummins, and Björn Schuller. 2017. Sequence to Sequence Autoencoders for Unsupervised Representation Learning from Audio. In Detection and Classification of Acoustic Scenes and Events 2017 Workshop (DCASE2017). 17--21.Google Scholar
- P. Bedi, A. Gautam, Richa, and C. Sharma. 2014. Using novelty score of unseen items to handle popularity bias in recommender systems. In 2014 International Conference on Contemporary Computing and Informatics (IC3I). 934--939.Google Scholar
- Kyunghyun Cho, Bart van Merrienboer, Çaglar Gülçehre, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. 2014. Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. CoRR abs/1406.1078 (2014).Google Scholar
- Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv:cs.CL/1810.04805Google Scholar
- Sander Dieleman and Benjamin Schrauwen. 2013. Multiscale approaches to music audio feature learning. In 14th international society for music information retrieval conference. Pontifícia Universidade Católica do Paraná, 116--121.Google Scholar
- Derek Gossi and Mehmet Hadi Gunes. 2016. Lyric-Based Music Recommendation. In Complex Networks VII - Proceedings of the 7th Workshop on Complex Networks, CompleNet 2016, Dijon, France, March 23-25, 2016 (Studies in Computational Intelligence), Hocine Cherifi, Bruno Gonçalves, Ronaldo Menezes, and Roberta Sinatra (Eds.), Vol. 644. Springer, 301--310.Google Scholar
- Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long Short-term Memory. Neural computation 9 (12 1997), 1735--80.Google Scholar
- Erich Peter Klement, Radko Mesiar, and Endre Pap. 2013. Triangular norms. Vol. 8. Springer Science & Business Media.Google Scholar
- Beth Logan, Andrew Kositsky, and Pedro Moreno. 2004. Semantic analysis of song lyrics. In 2004 IEEE International Conference on Multimedia and Expo (ICME), Vol. 2. 827--830 Vol.2.Google ScholarCross Ref
- Brian McFee, Luke Barrington, and Gert Lanckriet. 2012. Learning content similarity for music recommendation. IEEE transactions on audio, speech, and language processing 20, 8 (2012), 2207--2218.Google Scholar
- Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient Estimation of Word Representations in Vector Space. CoRR abs/1301.3781 (2013).Google Scholar
- Braja Gopal Patra, Dipankar Das, and Sivaji Bandyopadhyay. 2017. Retrieving Similar Lyrics for Music Recommendation System. In Proceedings of the 14th International Conference on Natural Language Processing (ICON-2017). NLP Association of India, Kolkata, India, 290--297.Google Scholar
- Karl Pearson. 1901. LIII. On lines and planes of closest fit to systems of points in space. (Nov 1901). https://doi.org/10.1080/14786440109462720Google Scholar
- Ladislav Peška and Stepan Balcar. 2019. Fuzzy D'Hondt's Algorithm for On-line Recommendations Aggregation. In ORSUM '19 (Proceedings of Machine Learning Research), Vol. 109. PMLR, 2--11. http://proceedings.mlr.press/v109/peska19a.htmlGoogle Scholar
- Qi Qi, Zhenyu Chen, Jia Liu, Chengfeng Hui, and Qing Wu. 2012. Using Inferred Tag Ratings to Improve User-Based Collaborative Filtering. In 27th Annual ACM Symposium on Applied Computing (SAC '12). Association for Computing Machinery, New York, NY, USA, 2008--2013.Google ScholarDigital Library
- Markus Schedl, Hamed Zamani, Ching-Wei Chen, Yashar Deldjoo, and Mehdi Elahi. 2017. Current challenges and visions in music recommender systems research. Int. J. Multimed. Inf. Retr. 7 (2017), 95--116.Google ScholarCross Ref
- Harald Steck.2018. Calibrated Recommendations. In Proceedings of the 12th ACM Conference on Recommender Systems (RecSys '18). ACM, New York, NY, USA, 154--162. https://doi.org/10.1145/3240323.3240372Google Scholar
- Tsegaye Misikir Tashu and Tomás Horváth. 2019. Semantic-Based Feedback Recommendation for Automatic Essay Evaluation. In Intelligent Systems and Applications - Proceedings of the 2019 Intelligent Systems Conference, IntelliSys 2019, London, UK, September 5-6, 2019, Volume 2 (Advances in Intelligent Systems and Computing), Yaxin Bi, Rahul Bhatia, and Supriya Kapoor (Eds.), Vol. 1038. Springer, 334--346. https://doi.org/10.1007/978-3-030-29513-4_24Google Scholar
- Alexandros Tsaptsinos. 2017. Lyrics-Based Music Genre Classification Using a Hierarchical Attention Network. CoRR abs/1707.04678 (2017).Google Scholar
- Aaron van den Oord, Sander Dieleman, and Benjamin Schrauwen. 2013. Deep content-based music recommendation. In Advances in Neural Information Processing Systems 26. Curran Associates, Inc., 2643--2651.Google Scholar
- Dongjing Wang, Shuiguang Deng, Xin Zhang, and Guandong Xu. 2016. Learning Music Embedding with Metadata for Context Aware Recommendation. In 2016 ACM International Conference on Multimedia Retrieval. 249--253.Google Scholar
- Hamed Zamani, Markus Schedl, Paul Lamere, and Ching-Wei Chen. 2019. An Analysis of Approaches Taken in the ACM RecSys Challenge 2018 for Automatic Music Playlist Continuation. ACM Trans. Intell. Syst. Technol. 10, 5, Article 57 (2019).Google ScholarDigital Library
Index Terms
- Lyrics or Audio for Music Recommendation?
Recommendations
Introducing Global and Regional Mainstreaminess for Improving Personalized Music Recommendation
MoMM2017: Proceedings of the 15th International Conference on Advances in Mobile Computing & MultimediaThe music mainstreaminess of a user reflects how strong a user's listening preferences correspond to those of the larger population. Considering that music mainstream may be defined from different perspectives and on various levels, e.g., geographical (...
Personality Correlates of Music Audio Preferences for Modelling Music Listeners
UMAP '20: Proceedings of the 28th ACM Conference on User Modeling, Adaptation and PersonalizationPast studies have shown that personality has a significant association with user behaviour and preferences, not least towards music. This makes personality information a promising aspect for user modelling in personalised recommender systems and similar ...
Music cold-start and long-tail recommendation: bias in deep representations
RecSys '19: Proceedings of the 13th ACM Conference on Recommender SystemsRecent advances in deep learning have yielded new approaches for music recommendation in the long tail. The new approaches are based on data related to the music content (i.e. the audio signal) and context (i.e. other textual information), from which it ...
Comments