pith. machine review for the scientific record. sign in

arxiv: 2604.08385 · v1 · submitted 2026-04-09 · 💻 cs.HC

Recognition: no theorem link

Let Me Introduce You: Stimulating Taste-Broadening Serendipity Through Song Introductions

Brett Binst , Ulysse Maes , Martijn C. Willemsen , Annelien Smets
Authors on Pith no claims yet

Pith reviewed 2026-05-10 17:34 UTC · model grok-4.3

classification 💻 cs.HC
keywords music recommender systemsserendipityuser studytransportationsong introductionstaste broadeningexplorationlistening diversity
0
0 comments X

The pith

Song introductions that absorb listeners into narratives most strongly spark interest in unfamiliar music.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper tests whether short introductions to songs can encourage users to engage with music beyond their typical preferences, an effect called taste-broadening serendipity. A user study identifies two mechanisms at work: transportation, or absorption into a story about the music, and cognitive elaboration, or picking up new facts about the artist or context. Transportation proves the stronger driver of interest, while cognitive elaboration is weaker but easier to create with simple information. This matters because music streaming platforms frequently recommend novel tracks yet fail to turn those suggestions into actual listening. The research shows how crafted introductions can address that gap by triggering specific psychological responses.

Core claim

The authors establish that immersive and informative song introductions stimulate taste-broadening serendipity, with transportation into a narrative world serving as the primary mechanism and cognitive elaboration about the artist or social context serving as a secondary one that is easier to induce.

What carries the argument

Transportation (absorption into a narrative world) and cognitive elaboration (learning new information about the artist or context) as mechanisms triggered by song introductions.

If this is right

  • Narrative introductions should produce higher engagement with out-of-preference songs than purely factual ones.
  • Cognitive elaboration can still be used when narrative elements are hard to create, though with smaller gains.
  • Widespread use of such introductions could raise the overall diversity of listening on streaming platforms.
  • The relative strength of transportation implies that story-like elements should be prioritized in introduction design.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same introduction techniques could be adapted to encourage exploration in other recommendation domains such as books or podcasts.
  • Real deployment would require testing how user context and attention levels alter the observed effects.
  • Optimal introductions might combine transportation and elaboration rather than using either mechanism alone.

Load-bearing premise

The effects measured in a controlled user study will produce comparable increases in interest when users encounter song recommendations amid the distractions and motivations of everyday music streaming.

What would settle it

A live A/B test on a music platform in which users who receive song introductions show no higher rate of playing or saving unfamiliar recommended tracks than users who receive no introductions.

Figures

Figures reproduced from arXiv: 2604.08385 by Annelien Smets, Brett Binst, Martijn C. Willemsen, Ulysse Maes.

Figure 1
Figure 1. Figure 1: Path diagram illustrating the two pathways hypothesized to stimulate Taste-Broadening Serendipity. [PITH_FULL_IMAGE:figures/full_fig_p005_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Left: An immersive intro for “Smoke on the Water”. Right: an informative intro for “Folsom Prison Blues”. [PITH_FULL_IMAGE:figures/full_fig_p006_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: TBS rates by song and intro method. a 5-point Likert scale) into a low (< 3), medium (2-4), and high (> 3) condition. We find that informative introductions that were not perceived as interesting actually have a negative effect on Taste-Broadening Serendipity compared to no introduction (for low quality immersive introductions, there was no significant difference). Conversely, when introductions were perce… view at source ↗
Figure 4
Figure 4. Figure 4: Path diagram of standardized (latent and observed) MLR estimates of the tested model. Constructs: latent (circles), observed [PITH_FULL_IMAGE:figures/full_fig_p011_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Path diagram of standardized (both latent and observed) estimates of the tested model through SEM. Latent constructs are [PITH_FULL_IMAGE:figures/full_fig_p012_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Predicted score on “Desire to listen to more music from this genre”. [PITH_FULL_IMAGE:figures/full_fig_p013_6.png] view at source ↗
read the original abstract

Research on how people experience music emphasizes the importance of exploration and diversity in listening. However, music recommender systems struggle with facilitating exploration. Even when music recommender systems are able to recommend something valuable to users that is outside their typical preferences, it still remains difficult to spark their interest. This paper presents a user study examining the efficacy of immersive and informative introductions in stimulating interest in songs that are beyond one's usual preferences, an experience called Taste-Broadening Serendipity. We uncover two important mechanisms behind the effect of introductions: transportation and cognitive elaboration. Our findings indicate that transportation (i.e., being absorbed into a narrative world) is the strongest predictor of Taste-Broadening Serendipity, while cognitive elaboration (i.e., learning something new about the artist or social context in which the music emerged) has a weaker effect but is easier to stimulate. We propose that song introductions can play an important role in facilitating exploration and increasing diversity of listening on music streaming platforms.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The paper presents a user study examining how immersive and informative song introductions can stimulate 'Taste-Broadening Serendipity' (interest in songs outside typical preferences). It identifies transportation (absorption into a narrative world) as the strongest predictor of this serendipity and cognitive elaboration (learning new artist or contextual information) as a weaker but more easily stimulated factor, proposing implications for music recommender systems to promote exploration and listening diversity.

Significance. If the empirical relationships hold after addressing methodological gaps, the work could meaningfully advance HCI research on music recommendation by providing actionable mechanisms for overcoming user resistance to unfamiliar content. The focus on testable psychological processes (transportation and cognitive elaboration) and the explicit link to platform design represent a constructive contribution to addressing the exploration challenge in recommender systems.

major comments (2)
  1. [User Study / Results] User Study section (and abstract): The manuscript reports regression-based findings on predictors of Taste-Broadening Serendipity but provides no information on sample size, experimental controls, statistical analysis procedures, or validation of the transportation and cognitive elaboration measures. This absence makes it impossible to evaluate whether the claim that transportation is the 'strongest predictor' is supported by reliable data or merely reflects unaccounted variance.
  2. [User Study] Stimuli selection (User Study section): The operationalization of songs 'beyond one's usual preferences' is not described as relying on individualized checks such as pre-exposure familiarity/liking ratings or analysis of each participant's listening history. If selection used only generic genre labels or 'unfamiliar' tracks, the measured effects of transportation versus cognitive elaboration on serendipity could conflate general engagement with actual taste-broadening, rendering the comparative predictor claim non-diagnostic for the intended mechanism.
minor comments (2)
  1. [Abstract] The abstract introduces 'Taste-Broadening Serendipity' without a concise operational definition or citation to prior serendipity literature, which would help readers immediately grasp the construct.
  2. [Results] Ensure any tables reporting regression coefficients or predictor comparisons include standard errors, p-values, and effect sizes to allow direct assessment of the 'strongest' and 'weaker' claims.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback. We address each major comment below and indicate the revisions planned for the next version of the manuscript.

read point-by-point responses

  1. Referee: [User Study / Results] User Study section (and abstract): The manuscript reports regression-based findings on predictors of Taste-Broadening Serendipity but provides no information on sample size, experimental controls, statistical analysis procedures, or validation of the transportation and cognitive elaboration measures. This absence makes it impossible to evaluate whether the claim that transportation is the 'strongest predictor' is supported by reliable data or merely reflects unaccounted variance.

    Authors: We acknowledge the omission of these methodological details in the User Study section. In the revised manuscript we will add a dedicated methods subsection that reports the exact sample size and participant demographics, describes all experimental controls (including counterbalancing and attention checks), specifies the regression procedures (model specification, predictors entered, and diagnostics performed), and provides validation evidence for the transportation and cognitive elaboration scales (e.g., reliability coefficients and factor structure). These additions will allow readers to assess the robustness of the finding that transportation is the strongest predictor. revision: yes

  2. Referee: [User Study] Stimuli selection (User Study section): The operationalization of songs 'beyond one's usual preferences' is not described as relying on individualized checks such as pre-exposure familiarity/liking ratings or analysis of each participant's listening history. If selection used only generic genre labels or 'unfamiliar' tracks, the measured effects of transportation versus cognitive elaboration on serendipity could conflate general engagement with actual taste-broadening, rendering the comparative predictor claim non-diagnostic for the intended mechanism.

    Authors: We agree that the current description of stimuli selection is insufficiently precise. In the revision we will expand the Stimuli subsection to detail exactly how songs were chosen to lie outside participants' typical preferences, including whether pre-exposure familiarity and liking ratings were collected for each participant or whether selection relied on genre labels and general unfamiliarity. If individualized checks were not performed, we will explicitly discuss this as a limitation and clarify the scope of the taste-broadening claim. This will strengthen the interpretability of the comparative predictor results. revision: yes

Circularity Check

0 steps flagged

Empirical user study with no mathematical derivations or self-referential predictions

full rationale

The paper reports results from a controlled user study measuring transportation, cognitive elaboration, and Taste-Broadening Serendipity via participant responses. No equations, fitted parameters, or predictions are derived; claims rest directly on observed data and statistical comparisons. No self-citations are invoked as load-bearing uniqueness theorems or ansatzes. The derivation chain is absent, rendering the work self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 1 invented entities

This is an empirical HCI user study. No free parameters or physical entities are introduced. The term Taste-Broadening Serendipity is newly defined for the paper.

axioms (1)
  • domain assumption Self-reported measures in user studies accurately capture subjective experiences such as transportation and interest
    Standard assumption in HCI research but subject to social desirability and recall biases.
invented entities (1)
  • Taste-Broadening Serendipity no independent evidence
    purpose: To label the specific experience of increased interest in out-of-preference songs triggered by introductions
    Newly coined term in the abstract with no external validation or prior usage cited.

pith-pipeline@v0.9.0 · 5484 in / 1283 out tokens · 83803 ms · 2026-05-10T17:34:31.299155+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

45 extracted references · 31 canonical work pages

  1. [1]

    Himan Abdollahpouri and Steve Essinger. 2018. Towards Effective Exploration/Exploitation in Sequential Music Recommendation. doi:10.48550/ arXiv.1812.03226 arXiv:1812.03226 [cs]

    work page arXiv 2018

  2. [2]

    Ashton Anderson, Lucas Maystre, Ian Anderson, Rishabh Mehrotra, and Mounia Lalmas. 2020. Algorithmic Effects on the Diversity of Consumption on Spotify. InProceedings of The Web Conference 2020. ACM, Taipei Taiwan, 2155–2165. doi:10.1145/3366423.3380281

    work page doi:10.1145/3366423.3380281 2020

  3. [3]

    Markus Appel, Timo Gnambs, Tobias Richter, and Melanie C. Green. 2015. The Transportation Scale–Short Form (TS–SF).Media Psychology18, 2 (April 2015), 243–266. doi:10.1080/15213269.2014.987400

    work page doi:10.1080/15213269.2014.987400 2015

  4. [4]

    Morteza Behrooz, Sarah Mennicken, Jennifer Thom, Rohit Kumar, and Henriette Cramer. 2019. Augmenting Music Listening Experiences on Voice Assistants.. InISMIR. 303–310

    2019

  5. [5]

    Brett Binst, Lien Michiels, and Annelien Smets. 2025. What is Serendipity? An Interview Study to Conceptualize Experienced Serendipity in Recommender Systems. InProceedings of the 33rd ACM Conference on User Modeling, Adaptation and Personalization

    2025

  6. [6]

    1984.Distinction: A social critique of the judgement of taste

    Pierre Bourdieu. 1984.Distinction: A social critique of the judgement of taste. Routledge

    1984

  7. [7]

    2017.brms: AnRPackage for Bayesian Multilevel Models UsingStan.Journal of Statistical Software80, 1 (2017)

    Paul-Christian Bürkner. 2017.brms: AnRPackage for Bayesian Multilevel Models UsingStan.Journal of Statistical Software80, 1 (2017). doi:10.18637/jss.v080.i01

    work page doi:10.18637/jss.v080.i01 2017

  8. [8]

    Dahlstrom

    Michael F. Dahlstrom. 2014. Using narratives and storytelling to communicate science with nonexpert audiences.Proceedings of the National Academy of Sciences111, supplement_4 (Sept. 2014), 13614–13620. doi:10.1073/pnas.1320645111

    work page doi:10.1073/pnas.1320645111 2014

  9. [9]

    Darda and Anjan Chatterjee

    Kohinoor M. Darda and Anjan Chatterjee. 2023. The impact of contextual information on aesthetic engagement of artworks.Scientific Reports13, 1 (March 2023), 4273. doi:10.1038/s41598-023-30768-9

    work page doi:10.1038/s41598-023-30768-9 2023

  10. [10]

    William P Eveland. 2001. The cognitive mediation model of learning from the news: Evidence from nonelection, off-year election, and presidential election contexts.Communication research28, 5 (2001), 571–601

    2001

  11. [11]

    Arthur Flexer, Dominik Schnitzer, Martin Gasser, and Gerhard Widmer. 2008. Playlist generation using start and end songs. InProceedings of the 9th International Conference of Music. ISMIR, Philadelphia

    2008

  12. [12]

    Luna T Frauhammer and Jana H Dreston. 2025. How cognitive elaboration fosters knowledge acquisition on social media—a field experiment. Journal of Computer-Mediated Communication30, 5 (July 2025), zmaf014. doi:10.1093/jcmc/zmaf014

    work page doi:10.1093/jcmc/zmaf014 2025

  13. [13]

    Giovanni Gabbolini and Derek Bridge. 2021. Generating interesting song-to-song segues with Dave. InProceedings of the 29th ACM Conference on User Modeling, Adaptation and Personalization. 98–107

    2021

  14. [14]

    Giovanni Gabbolini and Derek Bridge. 2022. A User-Centered Investigation of Personal Music Tours. InProceedings of the 16th ACM Conference on Recommender Systems. ACM, Seattle WA USA, 25–34. doi:10.1145/3523227.3546776

    work page doi:10.1145/3523227.3546776 2022

  15. [15]

    Alinka Greasley and Alexandra Lamont. 2016. Keeping it fresh: How listeners regulate their own exposure to familiar music. InMusic and Familiarity. Routledge, 13–31

    2016

  16. [16]

    Melanie C Green and Markus Appel. 2024. Narrative transportation: How stories shape how we see ourselves and the world. InAdvances in Experimental Social Psychology. Vol. 70. Elsevier, 1–82. doi:10.1016/bs.aesp.2024.03.002

    work page doi:10.1016/bs.aesp.2024.03.002 2024

  17. [17]

    Green and Timothy C

    Melanie C. Green and Timothy C. Brock. 2000. The role of transportation in the persuasiveness of public narratives.Journal of Personality and Social Psychology79, 5 (Nov. 2000), 701–721. doi:10.1037/0022-3514.79.5.701

    work page doi:10.1037/0022-3514.79.5.701 2000

  18. [18]

    Greenberg, Simon Baron-Cohen, David J

    David M. Greenberg, Simon Baron-Cohen, David J. Stillwell, Michal Kosinski, and Peter J. Rentfrow. 2015. Musical Preferences are Linked to Cognitive Styles.PLOS ONE10, 7 (July 2015), e0131151. doi:10.1371/journal.pone.0131151

    work page doi:10.1371/journal.pone.0131151 2015

  19. [19]

    Elizabeth Hellmuth Margulis. 2010. When program notes don’t help: Music descriptions and enjoyment.Psychology of Music38, 3 (July 2010), 285–302. doi:10.1177/0305735609351921

    work page doi:10.1177/0305735609351921 2010

  20. [20]

    Bart P Knijnenburg and Martijn C Willemsen. 2015. Evaluating recommender systems with user experiments. InRecommender systems handbook. Springer, 309–352

    2015

  21. [21]

    Denis Kotkov, Shuaiqiang Wang, and Jari Veijalainen. 2016. A survey of serendipity in recommender systems.Knowledge-Based Systems111 (Nov. 2016), 180–192. doi:10.1016/j.knosys.2016.08.014

    work page doi:10.1016/j.knosys.2016.08.014 2016

  22. [22]

    Helmut Leder, Benno Belke, Andries Oeberst, and Dorothee Augustin. 2004. A model of aesthetic appreciation and aesthetic judgments.British Journal of Psychology95, 4 (Nov. 2004), 489–508. doi:10.1348/0007126042369811

    work page doi:10.1348/0007126042369811 2004

  23. [23]

    Willemsen

    Yu Liang and Martijn C. Willemsen. 2019. Personalized Recommendations for Music Genre Exploration. InProceedings of the 27th ACM Conference on User Modeling, Adaptation and Personalization. ACM, Larnaca Cyprus, 276–284. doi:10.1145/3320435.3320455

    work page doi:10.1145/3320435.3320455 2019

  24. [24]

    Willemsen

    Yu Liang and Martijn C. Willemsen. 2021. Interactive Music Genre Exploration with Visualization and Mood Control. In26th International Conference on Intelligent User Interfaces. ACM, College Station TX USA, 175–185. doi:10.1145/3397481.3450700

    work page doi:10.1145/3397481.3450700 2021

  25. [25]

    Willemsen

    Yu Liang and Martijn C. Willemsen. 2021. The role of preference consistency, defaults and musical expertise in users’ exploration behavior in a genre exploration recommender. InFifteenth ACM Conference on Recommender Systems. ACM, Amsterdam Netherlands, 230–240. doi:10.1145/ 3460231.3474253

    work page arXiv 2021

  26. [26]

    Willemsen

    Yu Liang and Martijn C. Willemsen. 2022. Exploring the longitudinal effects of nudging on users’ music genre exploration behavior and listening preferences. InProceedings of the 16th ACM Conference on Recommender Systems. ACM, Seattle WA USA, 3–13. doi:10.1145/3523227.3546772

    work page doi:10.1145/3523227.3546772 2022

  27. [27]

    Valentina Maccatrozzo, Tobias Kuhn, Davide Ceolin, and Jacco Van Ossenbruggen. 2023. The Role of Serendipity in User-Curated Music Playlists. InProceedings of the 12th Knowledge Capture Conference 2023. ACM, Pensacola FL USA, 140–147. doi:10.1145/3587259.3627552 Let Me Introduce You: Stimulating Taste-Broadening Serendipity Through Song Introductions 17

    work page doi:10.1145/3587259.3627552 2023

  28. [28]

    Valentina Maccatrozzo, Eveline Van Everdingen, Lora Aroyo, and Guus Schreiber. 2017. Everybody,More or Less, likes Serendipity. InAdjunct Publication of the 25th Conference on User Modeling, Adaptation and Personalization. ACM, Bratislava Slovakia, 29–34. doi:10.1145/3099023.3099064

    work page doi:10.1145/3099023.3099064 2017

  29. [29]

    Rishabh Mehrotra. 2021. Algorithmic Balancing of Familiarity, Similarity, & Discovery in Music Recommendations. InProceedings of the 30th ACM International Conference on Information & Knowledge Management. ACM, Virtual Event Queensland Australia, 3996–4005. doi:10.1145/3459637. 3481893

    work page doi:10.1145/3459637 2021

  30. [30]

    Mark Mulligan. 2025. Music subscriber market shares 2024: Slowdown? What slowdown? https://www.midiaresearch.com/blog/music-subscriber- market-shares-2024-slowdown-what-slowdown

    2025

  31. [31]

    Alec Nonnemaker, Ralvi Isufaj, Zoltán Szlávik, and Cynthia Liem. 2025. Feedback-Driven Gradual Discovery for Expanding Musical Preferences. In Proceedings of the Nineteenth ACM Conference on Recommender Systems. ACM, Prague Czech Republic, 605–609. doi:10.1145/3705328.3748025

    work page doi:10.1145/3705328.3748025 2025

  32. [32]

    Rolf Reber, Norbert Schwarz, and Piotr Winkielman. 2004. Processing fluency and aesthetic pleasure: Is beauty in the perceiver’s processing experience?Personality and social psychology review8, 4 (2004), 364–382

    2004

  33. [33]

    Rentfrow and Samuel D

    Peter J. Rentfrow and Samuel D. Gosling. 2003. The do re mi’s of everyday life: The structure and personality correlates of music preferences. Journal of Personality and Social Psychology84, 6 (2003), 1236–1256. doi:10.1037/0022-3514.84.6.1236

    work page doi:10.1037/0022-3514.84.6.1236 2003

  34. [34]

    Yves Rosseel. 2012. lavaan: An R Package for Structural Equation Modeling.Journal of Statistical Software48, 2 (2012), 1–36. doi:10.18637/jss.v048.i02

    work page doi:10.18637/jss.v048.i02 2012

  35. [35]

    Dougal Shakespeare, Victor Chareyron, and Camille Roth. 2025. Reframing the filter bubble through diverse scale effects in online music consumption. Scientific Reports15, 1 (Feb. 2025), 4071. doi:10.1038/s41598-024-75967-0

    work page doi:10.1038/s41598-024-75967-0 2025

  36. [36]

    Paul J. Silvia. 2005. Cognitive Appraisals and Interest in Visual Art: Exploring an Appraisal Theory of Aesthetic Emotions.Empirical Studies of the Arts23, 2 (July 2005), 119–133. doi:10.2190/12AV-AH2P-MCEH-289E

    work page doi:10.2190/12av-ah2p-mceh-289e 2005

  37. [37]

    Paul J. Silvia. 2005. What Is Interesting? Exploring the Appraisal Structure of Interest.Emotion5, 1 (March 2005), 89–102. doi:10.1037/1528-3542.5.1.89

    work page doi:10.1037/1528-3542.5.1.89 2005

  38. [38]

    Paul J. Silvia. 2008. Interest—The Curious Emotion.Current Directions in Psychological Science17, 1 (Feb. 2008), 57–60. doi:10.1111/j.1467- 8721.2008.00548.x

    work page doi:10.1111/j.1467- 2008

  39. [39]

    Annelien Smets. 2025. Intended, afforded, and experienced serendipity: overcoming the paradox of artificial serendipity.Ethics and Information Technology27, 3 (Sept. 2025), 33. doi:10.1007/s10676-025-09841-6

    work page doi:10.1007/s10676-025-09841-6 2025

  40. [40]

    Maria Taramigkou, Efthimios Bothos, Konstantinos Christidis, Dimitris Apostolou, and Gregoris Mentzas. 2013. Escape the bubble: Guided exploration of music preferences for serendipity and novelty. 335–338

    2013

  41. [41]

    Mirjam Thoma, Stefan Ryf, Ulrike Ehlert, and Urs Nater. 2006. Regulation of emotions by listening to music in emotional situations. InProceedings of the 9th International Conference on Music Perception & Cognition. University of Bologna, Bologna, 1088–1093

    2006

  42. [42]

    Visconti, and Martin Wetzels

    Tom Van Laer, Ko De Ruyter, Luca M. Visconti, and Martin Wetzels. 2014. The Extended Transportation-Imagery Model: A Meta-Analysis of the Antecedents and Consequences of Consumers’ Narrative Transportation.Journal of Consumer Research40, 5 (Feb. 2014), 797–817. doi:10.1086/673383

    work page doi:10.1086/673383 2014

  43. [43]

    Yuan Cao Zhang, Diarmuid Ó Séaghdha, Daniele Quercia, and Tamas Jambor. 2012. Auralist: introducing serendipity into music recommendation. InProceedings of the fifth ACM international conference on Web search and data mining. ACM, Seattle Washington USA, 13–22. doi:10.1145/2124295. 2124300

    work page doi:10.1145/2124295 2012

  44. [44]

    Reza Jafari Ziarani and Reza Ravanmehr. 2021. Serendipity in recommender systems: a systematic literature review.Journal of Computer Science and Technology36 (2021), 375–396

    2021

  45. [45]

    Pirkka Åman and Lassi A Liikkanen. 2017. Interacting with context factors in music recommendation and discovery.International Journal of Human–Computer Interaction33, 3 (2017), 165–179

    2017