Valentina Maccatrozzo
Jacco Van Ossenbruggen
ABSTRACT
In this paper, we study the role of serendipity in music playlists. Serendipity is an important construct in recommendations, and finding an indicator of serendipity in a user-created playlist can facilitate the recommendation task. In particular, we want to know how the serendipity level of playlists is affected by the creator’s ability and by the context they are created. To do so, we (1) measure the serendipity level of music playlists using a previously established Linked Open Data-based approach, (2) assess whether the ability of the creator of the playlists has an effect on the serendipity level, and (3) assess whether different contexts facilitate a higher or lower serendipity level of playlists. The serendipity level of playlists is calculated with the cosine distance between Linked Open Data Paths that connect the songs contained in the playlist. The ability of the creator to generate serendipitous recommendations is estimated by measuring his/her coping potential and assessing the genre diversity of listening history. We instrument a study using a Spotify playlists dataset. Previous results in different contexts suggest that the coping potential is a good proxy for the curiosity level of a person, and, in turn, for the diversified knowledge this person has. Our analyses confirm these findings also in the music context: we find that playlist creators with higher coping potential have a more diversified knowledge. They create a higher number of playlists that span across multiple contexts and genres. Conversely, a lower copying potential implies a lower number of less coherent playlists.
- Pedro Álvarez, Jorge García de Quirós, and Sandra Baldassarri. 2020. A Web System Based on Spotify for the automatic generation of affective playlists. In Cloud Computing, Big Data & Emerging Topics. Springer, Cham, 124–137.Google Scholar
- Ian Anderson, Santiago Gil, Clay Gibson, Scott Wolf, Will Shapiro, Oguz Semerci, and David M. Greenberg. 2021. “Just the Way You Are": Linking Music Listening on Spotify and Personality. Social Psychological and Personality Science 12, 4 (2021), 561–572.Google ScholarCross Ref
- Willian G. Assuncao, Lara S.G. Piccolo, and Luciana A.M. Zaina. 2022. Considering emotions and contextual factors in music recommendation: a systematic literature review. Multimedia Tools Applications 81 (2022), 8367–8407.Google ScholarDigital Library
- Mahta Bakhshizadeh, Ali Moeini, Mina Latifi, and Maryam T. Mahmoudi. 2019. Automated Mood Based Music Playlist Generation By Clustering The Audio Features. In 9th International Conference on Computer and Knowledge Engineering. IEEE, 231–237.Google Scholar
- Shay Ben-Elazar, Gal Lavee, Noam Koenigstein, Oren Barkan, Hilik Berezin, Ulrich Paquet, and Tal Zaccai. 2017. Groove Radio: A Bayesian Hierarchical Model for Personalized Playlist Generation. In Tenth ACM International Conference on Web Search and Data Mining (Cambridge, United Kingdom). ACM, New York, USA, 445–453.Google ScholarDigital Library
- Daniel E. Berlyne. 1954. A theory of human curiosity. British Journal of Psychology. General Section 45, 3 (1954), 180–191.Google ScholarCross Ref
- Jeong Choi, Anis Khlif, and Elena Epure. 2020. Prediction of user listening contexts for music playlists. In The 1st Workshop on NLP for Music and Audio. ACL, 23–27.Google Scholar
- Mark de Rond. 2014. The structure of serendipity. Culture and Organization 20, 5 (2014), 342–358.Google ScholarCross Ref
- Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In 2019 Conference of the North American Chapter of the ACL: Human Language Technologies. ACL, Minneapolis, USA, 4171–4186.Google Scholar
- Ricardo Dias, Daniel Gonçalves, and Manuel J. Fonseca. 2017. From manual to assisted playlist creation: a survey. Multimedia Tools Applications 76 (2017), 14375–14403.Google ScholarDigital Library
- Ricardo Dias, Joana Pinto, and Manuel J. Fonseca. 2014. Interactive Visualization for Music Rediscovery and Serendipity. In 28th International BCS Human Computer Interaction Conference on HCI (Southport, UK). BCS, UK, 183–188.Google Scholar
- Marco Furini, Jessica Martini, and Manuela Montangero. 2019. Automated Generation of User-Tailored and Time-Sensitive Music Playlists. In 16th Annual Consumer Communications Networking Conference. IEEE, Las Vegas, USA, 1–6.Google Scholar
- Anna Gatzioura, João Vinagre, Alípio M. Jorge, and Miquel Sànchez-Marrè. 2019. A Hybrid Recommender System for Improving Automatic Playlist Continuation. Transactions on Knowledge and Data Engineering 33 (2019), 1819–1830.Google Scholar
- Anja Nylund Hagen. 2015. The Playlist Experience: Personal Playlists in Music Streaming Services. Popular Music and Society 38, 5 (2015), 625–645.Google ScholarCross Ref
- Leo Iaquinta, Marco De Gemmis, Pasquale Lops, Giovanni Semeraro, Michele Filannino, and Piero Molino. 2008. Introducing serendipity in a content-based recommender system. In Proceedgins of the 8th International Conference on Hybrid Intelligent Systems. IEEE, Barcelona, Spain, 168–173.Google ScholarDigital Library
- Rosilde T. Irene, Clara Borrelli, Massimiliano Zanoni, Michele Buccoli, and Augusto Sarti. 2019. Automatic playlist generation using Convolutional Neural Networks and Recurrent Neural Networks. In 27th European Signal Processing Conference. IEEE, Coruña, Spain, 1–5.Google ScholarCross Ref
- Dietmar Jannach, Iman Kamehkhosh, and Geoffray Bonnin. 2014. Analyzing the characteristics of shared playlists for music recommendation. In RSWeb Workshop at ACM RecSys ’14, Vol. 1271. CEUR, Silicon Valley, USA.Google Scholar
- Dietmar Jannach, Lukas Lerche, and Iman Kamehkhosh. 2015. Beyond Hitting the Hits: Generating Coherent Music Playlist Continuations with the Right Tracks. In 9th Conference on Recommender Systems (Vienna, Austria). ACM, New York, USA, 187–194.Google ScholarDigital Library
- Dan Jurafsky and James H. Martin. 2009. Speech and language processing : an introduction to natural language processing, computational linguistics, and speech recognition. Pearson Prentice Hall, Upper Saddle River, N.J.Google Scholar
- Peter Knees and Markus Schedl. 2013. A Survey of Music Similarity and Recommendation from Music Context Data. ACM Trans. Multimedia Comput. Commun. Appl. 10, 1, Article 2 (Dec. 2013), 21 pages.Google ScholarDigital Library
- Peter Knees, Markus Schedl, Bruce Ferwerda, and Audrey Laplante. 2019. 9. User awareness in music recommender systems. De Gruyter Oldenbourg, Berlin, 223–252.Google Scholar
- Amanda E. Krause and Adrian C. North. 2014. Contextualized music listening: playlists and the Mehrabian and Russell model. Psychology of Well-Being 4, 1 (2014), 22–38.Google ScholarCross Ref
- Tuck W. Leong, Frank Vetere, and Steve Howard. 2005. The Serendipity Shuffle. In 17th Australia Conference on Computer-Human Interaction: Citizens Online (Canberra, Australia). CHISIG Australia, Narrabundah, AUS, 1–4.Google Scholar
- Elad Liebman, Maytal Saar-Tsechansky, and Peter Stone. 2015. DJ-MC: A Reinforcement-Learning Agent for Music Playlist Recommendation. In 2015 International Conference on Autonomous Agents and Multiagent Systems (Istanbul, Turkey). IFAAMAS, Richland, SC, 591–599.Google Scholar
- George Loewenstein. 1994. The psychology of curiosity: A review and reinterpretation. Psychological Bulletin 116, 1 (1994), 75–98.Google ScholarCross Ref
- Valentina Maccatrozzo, Lora Aroyo, and Willem Robert Van Hage. 2013. Crowdsourced Evaluation of Semantic Patterns for Recommendation. In UMAP Workshops, Vol. 997. CEUR, Rome, Italy, 15–21.Google Scholar
- Valentina Maccatrozzo, Manon Terstall, Lora Aroyo, and Guus Schreiber. 2017. SIRUP: Serendipity In Recommendations via User Perceptions. In 22nd Intelligent User Interfaces Conference. ACM, Limassol, Cyprus, 35–44.Google ScholarDigital Library
- Valentina Maccatrozzo, Eveleine van Everdingen, Lora Aroyo, and Guus Schreiber. 2017. Everybody, More or Less, Likes Serendipity. In Adjunct Publication of the 25th Conference on User Modeling, Adaptation and Personalization (Bratislava, Slovakia). ACM, New York, USA, 29–34.Google ScholarDigital Library
- John McCarthy and Peter Wright. 2004. Technology as Experience. MIT Press, Cambridge, MA.Google ScholarDigital Library
- Xi Niu, Fakhri Abbas, Mary Lou Maher, and Kazjon Grace. 2018. Surprise Me If You Can: Serendipity in Health Information. In 2018 CHI Conference on Human Factors in Computing Systems (Montreal QC, Canada). ACM, New York, USA, 1–12.Google ScholarDigital Library
- Emily C. Nusbaum and Paul J. Silvia. 2011. Shivers and Timbres: Personality and the Experience of Chills From Music. Social Psychological and Personality Science 2, 2 (2011), 199–204.Google ScholarCross Ref
- Savvas Petridis, Nediyana Daskalova, Sarah Mennicken, Samuel F Way, Paul Lamere, and Jennifer Thom. 2022. TastePaths: Enabling Deeper Exploration and Understanding of Personal Preferences in Recommender Systems. In 27th International Conference on Intelligent User Interfaces (Helsinki, Finland). ACM, New York, USA, 120–133.Google ScholarDigital Library
- Martin Pichl and Eva Zangerle. 2018. Latent Feature Combination for Multi-Context Music Recommendation. In International Conference on Content-Based Multimedia Indexing. IEEE, La Rochelle, France, 1–6.Google Scholar
- Martin Pichl and Eva Zangerle. 2021. User models for multi-context-aware music recommendation. Multimedia Tools Applications 80 (2021), 22509–22531.Google ScholarDigital Library
- Martin Pichl, Eva Zangerle, and Gunther Specht. 2015. Towards a Context-Aware Music Recommendation Approach: What is Hidden in the Playlist Name?. In International Conference on Data Mining Workshop. IEEE, USA, 1360–1365.Google ScholarDigital Library
- Martin Pichl, Eva Zangerle, and Gunther Specht. 2015. Towards a Context-Aware Music Recommendation Approach: What is Hidden in the Playlist Name?. In International Conference on Data Mining Workshop. IEEE, WashingtonUSA, 1360–1365.Google ScholarDigital Library
- Martin Pichl, Eva Zangerle, and Gunther Specht. 2016. Understanding Playlist Creation on Music Streaming Platforms. In International Symposium on Multimedia. IEEE, San Jose, CA, 475–480.Google Scholar
- Lorenzo Porcaro and Emilia Gómez. 2019. 20 Years of Playlists: A Statistical Analysis on Popularity and Diversity. In 20th Conference of the International Society for Music Information Retrieval (ISMIR 2019). ISMIR, Delft, The Netherlands.Google Scholar
- Royston M. Roberts. 1989. Serendipity: Accidental Discoveries in Science. John Wiley & Sons, Inc., Hoboken, New Jersey, U.S.Google Scholar
- Markus Schedl, David Hauger, and Dominik Schnitzer. 2012. A Model for Serendipitous Music Retrieval. In 2nd Workshop on Context-Awareness in Retrieval and Recommendation (Lisbon, Portugal). ACM, New York, USA, 10–13.Google ScholarDigital Library
- Markus Schedl, Hamed Zamani, Ching-Wei Chen, Yashar Deldjoo, and Mehdi Elahi. 2018. Current challenges and visions in music recommender systems research. International Journal of Multimedia Information Retrieval 7 (2018), 95–116.Google ScholarCross Ref
- Paul J. Silvia. 2005. Cognitive Appraisals and Interest in Visual Art: Exploring an Appraisal Theory of Aesthetic Emotions. Empirical Studies of the Arts 23, 2 (2005), 119–133.Google ScholarCross Ref
- Paul J. Silvia. 2008. Interest - The curious emotion. Current Directions in Psychological Science 17, 1 (2008), 57–60.Google ScholarCross Ref
- Tao Sun, Ming Zhang, and Qiaozhu Mei. 2013. Unexpected Relevance: An Empirical Study of Serendipity in Retweets. In Seventh International Conference on Weblogs and Social Media. The AAAI Press, WashingtonUSA, 592–601.Google Scholar
- Maria Taramigkou, Efthimios Bothos, Konstantinos Christidis, Dimitris Apostolou, and Gregoris Mentzas. 2013. Escape the Bubble: Guided Exploration of Music Preferences for Serendipity and Novelty. In 7th Conference on Recommender Systems (Hong Kong, China). ACM, New York, USA, 335–338.Google ScholarDigital Library
- Andreu Vall, Matthias Dorfer, Hamid Eghbal-zadeh, Markus Schedl, Keki Burjorjee, and Gerhard Widmer. 2019. Feature-combination hybrid recommender systems for automated music playlist continuation. User Modeling and User-Adapted Interaction 29, 2 (01 Apr 2019), 527–572.Google Scholar
- Andreu Vall, Massimo Quadrana, Markus Schedl, Gerhard Widmer, and Paolo Cremonesi. 2017. The Importance of Song Context in Music Playlists. In Poster Track of the 11th ACM Conference on Recommender Systems, Vol. 1905. CEUR, Como, Italy.Google Scholar
- Mian Wang, Takahiro Kawamura, Yuichi Sei, Hiroyuki Nakagawa, Yasuyuki Tahara, and Akihiko Ohsuga. 2014. Context-Aware Music Recommendation with Serendipity Using Semantic Relations. In Semantic Technology. Springer, Cham, 17–32.Google Scholar
- Xinxi Wang, David Rosenblum, and Ye Wang. 2012. Context-aware Mobile Music Recommendation for Daily Activities. In 20th ACM International Conference on Multimedia (Nara, Japan). ACM, New York, USA, 99–108.Google Scholar
- Liyang Yu. 2011. Linked Open Data. Springer, Berlin, Heidelberg, 409–466.Google Scholar
- Eva Zangerle and Martin Pichl. 2018. Content-based User Models: Modeling the Many Faces of Musical Preference. In 19th International Society for Music Information Retrieval Conference. ISMIR, Paris, France, 709–716.Google Scholar
- Eva Zangerle, Martin Pichl, and Markus Schedl. 2020. User models for culture-aware music recommendation: fusing acoustic and cultural cues. Transactions of the International Society for Music Information Retrieval 3 (2020), 1–16. Issue 1.Google ScholarCross Ref
- Eva Zangerle, Michael Tschuggnall, Stefan Wurzinger, and Günther Specht. 2018. ALF-200k: Towards Extensive Multimodal Analyses of Music Tracks and Playlists. In Advances in Information Retrieval - 39th European Conference on IR Research, ECIR 2018. Springer, Cham, 584–590.Google Scholar
- Yuan Cao Zhang, Diarmuid Ó Séaghdha, Daniele Quercia, and Tamas Jambor. 2012. Auralist: Introducing Serendipity into Music Recommendation. In 5th International Conference on Web Search and Data Mining (Seattle, Washington, USA). ACM, New York, USA, 13–22.Google ScholarDigital Library
Index Terms
- The Role of Serendipity in User-Curated Music Playlists
Recommendations
Rethinking Serendipity in Recommender Systems
CHIIR '23: Proceedings of the 2023 Conference on Human Information Interaction and RetrievalRecommender systems suggest items, such as movies or books, to users based on their interests. These systems often suggest items that users are either already familiar with or could easily have found on their own without additional assistance. To ...
Correlation analysis among the metadata-based similarity, acoustic-based distance, and serendipity of music
IDEAS '15: Proceedings of the 19th International Database Engineering & Applications SymposiumWith the aim of realizing a serendipity-oriented music recommendation, we analyzed the correlation between music similarity and serendipity. A user may be familiar with the musical piece if its metadata, such as the artist's names, and the title, is ...
Investigating serendipity in recommender systems based on real user feedback
SAC '18: Proceedings of the 33rd Annual ACM Symposium on Applied ComputingOver the past several years, research in recommender systems has emphasized the importance of serendipity, but there is still no consensus on the definition of this concept and whether serendipitous items should be recommended is still not a well-...
Comments