=Paper=
{{Paper
|id=Vol-3908/paper_41
|storemode=property
|title=Algorithmic Collective Action in Recommender Systems: Promoting Songs by Reordering
Playlists
|pdfUrl=https://ceur-ws.org/Vol-3908/paper_41.pdf
|volume=Vol-3908
|authors=Joachim Baumann,Celestine Mendler-Dünner
|dblpUrl=https://dblp.org/rec/conf/ewaf/0002M24
}}
==Algorithmic Collective Action in Recommender Systems: Promoting Songs by Reordering
Playlists==
https://ceur-ws.org/Vol-3908/paper_41.pdf
Algorithmic Collective Action in Recommender
Systems: Promoting Songs by Reordering Playlists
Joachim Baumann1,* , Celestine Mendler-Dünner2
1
University of Zurich, Zurich University of Applied Sciences
2
ELLIS Institute, Tübingen, Max Planck Institute for Intelligent Systems, Tübingen and Tübingen AI Center
Abstract
We investigate algorithmic collective action in transformer-based recommender systems. Our use case is
a collective of fans aiming to promote the visibility of an artist by strategically placing one of their songs
in the existing playlists they control. The success of the collective is measured by the increase in test-time
recommendations of the targeted song. We introduce an easily implementable strategy towards this goal
and test its efficacy on a publicly available recommender system model used in production by a major
music streaming platform. Our findings reveal that even small collectives (controlling less than 0.01% of
the training data) can achieve up to 25× amplification of recommendations by strategically choosing
the position at which to insert the song. Further, we find that the strategy only minimally impairs user
experience; recommendations of other songs are largely preserved, and newly gained recommendations
are taken from diverse songs of varying popularity levels. Taken together, our findings demonstrate
how algorithmic collective action can be effective while not necessarily being adversarial, raising new
questions around fairness, incentives, and social dynamics in recommender systems.
Keywords
music recommendation, collective action, power dynamics, transformer models, participatory AI
1. Motivation
In the ever-evolving landscape of music discovery, the challenge of sifting through the over-
whelming number of tracks released daily has become increasingly difficult for both platforms
and streamers. This has resulted in a strong dependence on platforms like Spotify, Deezer,
or Apple Music, which distribute and promote music through song recommendations. These
systems rely on historical data to learn user preferences and predict future content consump-
tion [1, 2, 3, 4, 5].
It has been widely documented that music recommendation systems suffer from popularity
bias as they tend to concentrate recommendation exposure on a limited fraction of artists, often
overlooking new and emerging talent [6, 7, 8, 9, 10, 11]. As the success and visibility of artists
are deeply influenced by the algorithms of these platforms, this can lead to a considerable
imbalance in the music industry [12, 13] and reinforce existing inequalities [14, 15]. As a result,
artists have started to fight for more transparency and fairer payments for online streaming
EWAF’24: European Workshop on Algorithmic Fairness, July 01–03, 2024, Mainz, Germany
*
Work conducted during a research internship at the Max-Planck Institute for Intelligent Systems, Tübingen.
$ baumann@ifi.uzh.ch (J. Baumann); celestine@tue.ellis.eu (C. Mendler-Dünner)
0000-0002-0877-7063 (J. Baumann); 0000-0002-9880-7173 (C. Mendler-Dünner)
© 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
CEUR
Workshop
Proceedings
http://ceur-ws.org
ISSN 1613-0073
CEUR Workshop Proceedings (CEUR-WS.org)
CEUR
ceur-ws.org
Workshop ISSN 1613-0073
Proceedings
Figure 1: By strategically choosing the position at which to insert a song in a playlist, collectives can
achieve a disproportional amplification in recommendation frequency relative to training set occurrences,
compared to other songs.
services. The “Justice at Spotify” campaign, launched by the Union of Musicians and Allied
Workers [16], has been signed by more than 28,000 artists. At the same time, the International
Society for Music Information Retrieval has been arguing for promoting the discovery of less
popular artists by recommending ‘long-tail’ items [17], as have other researchers [18, 19, 20].
2. Proposed strategy
We explore algorithmic collective action as a means for emerging artists to gain exposure
in ML-powered recommender systems by mobilizing their fan base. Algorithmic collective
action [21] describes the coordinated effort of a group of individuals to strategically report the
part of the training data they control in order to impact the outcomes of a learning algorithm.
In music recommender systems the training data consists of user-generated playlists 𝑝. Each
playlist is composed of an ordered list of songs. We want collective action to preserve user
experience. Thus, we design collective action strategies under an authenticity constraint:
A strategy ℎ : 𝑝 → 𝑝′ is authentic iff: Lev(𝑝, ℎ(𝑝)) ≤ 1
where Lev denotes the Levenshtein distance [22], also known as edit distance in information
theory, counting the number of operations needed to transform one sequence into another.
We propose a concrete strategy that satisfies this constraint. Our strategy consists of inserting
an agreed-upon target song 𝑠* at a specific position in the playlist, as shown in Figure 2. The
position 𝑖 to insert the song 𝑠* is chosen by identifying the least likely song 𝑠0 among the songs
in the playlist 𝑝 and placing 𝑠* right after 𝑠0 .
!∗
… !"%& !! !"#$ … !!
*
" the target song 𝑠 #right after 𝑠0 in a playlist of length 𝐿.
Figure 2: Song insertion strategy: placing
"! ∗ "! ∗
Intuition for the strategy. Sequential recommenders are trained to approximate the condi-
tional distributions of songs. For a given context window, the model then recommends one of
the top 𝐾 most likely songs to follow this context. Our strategy aims to exploit contexts that are
overrepresented in the data the collective controls to increase the chance of meeting the top 𝐾
threshold. To this end, it selects contexts that end on a low-frequency song (for small collectives,
these typically appear only once in the controlled playlists). To find these low-frequency songs
participants of the collective can share information about the playlists they own, gather stream
counts by scraping Spotify playlists, or use public APIs to gather external song statistics.
Notice that the probabilistic assumption on the sequence model is not specific to the model ar-
chitecture or the training algorithm used. This makes the strategy robust and easy to implement
in practice.
3. Success of collective action
We empirically test the success of our strategy against a recent transformer-based automatic
playlist continuation model [4]. The model has been deployed and made publicly available by
Deezer—one of the biggest streaming platforms in the world. To train the model we use the
Spotify million playlist dataset [23], treating each playlist as a user, and randomly sampling a
small 𝛼-fraction to compose the collective. We find that by strategically placing the target song,
small collectives can achieve disproportional representation at test time, see Figure 1. The star
shows that a collective of size 1% can achieve that the target song is recommended in 6% of
the playlist continuations at test time. This corresponds to a factor 6 amplification comparing
training time and test time occurrences. In contrast, placing the song at the end of every playlist
is largely ineffective. Also interesting to observe in Figure 1 is that a similar strategy does not
seem to be implemented by any artist in the investigated data.
We further experiment with collective sizes from 0.03% to 3%, and show amplification in
Figure 3. Interestingly, even tiny user collectives, controlling as few as 60 out of 1 million
playlists can achieve an amplification of 25×. This is 40× more than an average song occurring
at the same frequency in the training data. Notably, this can be achieved by choosing the position
at which to insert one song strategically, while leaving the rest of the playlist untouched.
4. Externalities
As we have seen, collective action offers an effective lever for platform participants to promote
their interests on algorithm-driven platforms. However, strategies can only be effective if they
are not creating equally strong incentives for other players in the system to counter them. In
25
20
Amplification
Collective Strategy
15 Full information
10% train data
10 scraped stream counts
Random
5 AtTheEnd
0
10−4 10−3 10−2
α (log scale)
Figure 3: Empirical amplification of our proposed strategy with different levels of information (compared
to two baselines Random and AtTheEnd).
Change in recommendations
Collectively promoted
600
Other songs
due to collective action
400
200
0
−200
0.0 α 0.02 0.03 0.04
Song frequency in train
Figure 4: Impact of collective action on other songs when controlling 1% of training data (𝛼 = 1%).
Songs are sorted by their training set frequency and aggregated into 50 evenly spaced bins with 95% CI.
Table 1
Effect on recommendation performance—measured using standard metrics [24]: Normalized Discounted
Cumulative Gain (NDCG), R-precision, and number of clicks to find relevant song (#C).
Performance Performance loss Strategy Performance loss
No strategy all only participants replace relevant
NDCG 0.29 ± 0.15 0.01 ± 0.01 0.00 ± 0.0 0.03 ± 0.04
R-precision 0.22 ± 0.11 0.01 ± 0.01 0.00 ± 0.0 0.03 ± 0.04
#C 2.52 ± 1.34 0.01 ± 0.01 −0.01 ± 0.1 0.03 ± 0.04
the following we study the externalities of our strategy, choosing 𝛼 = 1%.
First, we focus on the effect of our strategy on other artists. In Figure 4, we visualize the
change in total recommendation counts for individual songs, binned according to their training
set frequency. The purple star indicates the song promoted by the collective. We find that
the gained recommendations are taken from songs of varying popularity levels, and no artist
appears to be affected disproportionally.
Second, we focus on the effect of our strategy on the recommendation performance. Table 4
shows performance along multiple metrics. The loss seems to be very small for the platform. In
comparison, the last column shows an alternative strategy with the same success, but replacing
a relevant song every time 𝑠* is recommended. This shows that the gained recommendations
often replace irrelevant songs causing relatively little harm. Similarly, we see little performance
drop for the platform participants, suggesting that their recommendations are also widely
preserved at test time. If the song were to be actually relevant for individuals in the collective
such a strategy could even help increase recommendation performance.
5. Conclusion
We designed an easy-to-implement collective action strategy under a natural authenticity con-
straint. We demonstrated that it can be effective in promoting a target song even for tiny
collectives, while minimally impairing overall user experience. This suggests a widely unex-
plored design space for effective collective action strategies that differ from typical adversarial
data poisoning attacks [c.f. 25, 26, 27, 28]. They offer a powerful data lever [29, 30], and an
approach to participatory AI [31]. Thus, understanding the role of economic power [32, 33],
formalizing incentives [34], as well as quantifying long-term payoffs, dynamics and equilibria
under collective action promises to be a fruitful direction for future work.1
Acknowledgments
We would like to thank Moritz Hardt for many insightful and formative discussions throughout
the course of this work. We would also like to thank Mila Gorecki, Ricardo Dominguez-Olmedo,
Ana-Andreea Stoica, and André Cruz for invaluable feedback on the manuscript, and Olawale
Salaudeen, Florian Dorner, Stefania Ionescu, and Tijana Zrnic for helpful feedback on earlier
versions of this work. We would also like to thank the anonymous reviewers for their feedback.
References
[1] C. Hansen, C. Hansen, L. Maystre, R. Mehrotra, B. Brost, F. Tomasi, M. Lalmas, Contextual
and sequential user embeddings for large-scale music recommendation, in: Proceedings
of the 14th ACM Conference on Recommender Systems, 2020, p. 53–62.
[2] F. Tomasi, J. Cauteruccio, S. Kanoria, K. Ciosek, M. Rinaldi, Z. Dai, Automatic music
playlist generation via simulation-based reinforcement learning, in: Proceedings of the
29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD ’23, 2023,
p. 4948–4957.
[3] D. Moor, Y. Yuan, R. Mehrotra, Z. Dai, M. Lalmas, Exploiting sequential music prefer-
ences via optimisation-based sequencing, in: Proceedings of the 32nd ACM International
Conference on Information and Knowledge Management, 2023, p. 4759–4765.
[4] W. Bendada, G. Salha-Galvan, T. Bouabça, T. Cazenave, A Scalable Framework for Au-
tomatic Playlist Continuation on Music Streaming Services, in: Proceedings of the 46th
1
An extended version of the paper can be found on arXiv [35].
International ACM SIGIR Conference on Research and Development in Information Re-
trieval, 2023, pp. 464–474.
[5] W. Bendada, T. Bontempelli, M. Morlon, B. Chapus, T. Cador, T. Bouabça, G. Salha-Galvan,
Track Mix Generation on Music Streaming Services Using Transformers, in: Proceedings
of the 17th ACM Conference on Recommender Systems, 2023, pp. 112–115.
[6] P. M. Napoli, Requiem for the long tail: Towards a political economy of content aggregation
and fragmentation, International Journal of Media & Cultural Politics 12 (2016) 341–356.
[7] C. Bauer, M. Kholodylo, C. Strauss, Music recommender systems: challenges and opportu-
nities for non-superstar artists, in: 30th Bled eConference, 2017, pp. 21–32.
[8] C. Bauer, Allowing for equal opportunities for artists in music recommendation, in:
Proceedings of the 1st Workshop on Human-Centric Music Information Research Systems,
2019, pp. 16–18.
[9] M. P. Coelho, J. Z. Mendes, Digital music and the “death of the long tail”, Journal of
Business Research 101 (2019) 454–460.
[10] E. Blake, Data shows 90 percent of streams go to the top 1 percent of artists, 2020. https:
//www.rollingstone.com/pro/news/top-1-percent-streaming-1055005.
[11] D. Jannach, L. Lerche, F. Gedikli, G. Bonnin, What recommenders recommend – an analysis
of accuracy, popularity, and sales diversity effects, in: User Modeling, Adaptation, and
Personalization, Springer Berlin Heidelberg, 2013, pp. 25–37.
[12] L. Aguiar, J. Waldfogel, Platforms, power, and promotion: Evidence from spotify playlists,
The Journal of Industrial Economics 69 (2021) 653–691.
[13] R. Prey, M. Esteve Del Valle, L. Zwerwer, Platform pop: disentangling spotify’s intermediary
role in the music industry, Information, Communication & Society 25 (2022) 74–92.
[14] L. Porcaro, C. Castillo, E. Gómez, Diversity by design in music recommender systems,
Transactions of the International Society for Music Information Retrieval (2021).
[15] T. Tofalvy, J. Koltai, “Splendid Isolation”: The reproduction of music industry inequalities
in Spotify’s recommendation system, New Media & Society 25 (2023) 1580–1604.
[16] Union of Musicians and Allied Workers, Justice at Spotify, 2021. URL: https://weareumaw.
org/justice-at-spotify.
[17] C. Bauer, Report on the ISMIR 2020 special session: how do we help artists?, ACM SIGIR
Forum 54 (2020).
[18] Ò. Celma, Music Recommendation and Discovery: The Long Tail, Long Fail, and Long
Play in the Digital Music Space, Springer Berlin, Heidelberg, 2010.
[19] D. Turnbull, L. Barrington, G. Lanckriet, Five approaches to collecting tags for music, in:
ISMIR, 2008.
[20] S. Craw, B. Horsburgh, S. Massie, Music recommendation: Audio neighbourhoods to
discover music in the long tail, in: Case-Based Reasoning Research and Development,
Springer International Publishing, 2015, pp. 73–87.
[21] M. Hardt, E. Mazumdar, C. Mendler-Dünner, T. Zrnic, Algorithmic Collective Action in
Machine Learning, in: Proceedings of the 40th International Conference on Machine
Learning, volume 202, PMLR, 2023, pp. 12570–12586.
[22] V. I. Levenshtein, Binary codes capable of correcting deletions, insertions and reversals,
Soviet Physics Doklady 10 (1966) 707.
[23] C.-W. Chen, P. Lamere, M. Schedl, H. Zamani, Recsys Challenge 2018: Automatic Music
Playlist Continuation, in: Proceedings of the 12th ACM Conference on Recommender
Systems, RecSys ’18, 2018, pp. 527–528.
[24] H. Zamani, M. Schedl, P. Lamere, C.-W. Chen, An Analysis of Approaches Taken in the
ACM RecSys Challenge 2018 for Automatic Music Playlist Continuation, ACM Trans.
Intell. Syst. Technol. 10 (2019).
[25] Z. Tian, L. Cui, J. Liang, S. Yu, A comprehensive survey on poisoning attacks and counter-
measures in machine learning, ACM Comput. Surv. 55 (2022).
[26] H. Zhang, Y. Li, B. Ding, J. Gao, Practical data poisoning attack against next-item recom-
mendation, in: Proceedings of The Web Conference 2020, 2020, p. 2458–2464.
[27] Z. Yue, Z. He, H. Zeng, J. McAuley, Black-box attacks on sequential recommenders via
data-free model extraction, in: Proceedings of the 15th ACM Conference on Recommender
Systems, 2021, p. 44–54.
[28] Z. Yue, H. Zeng, Z. Kou, L. Shang, D. Wang, Defending substitution-based profile pollution
attacks on sequential recommenders, in: Proceedings of the 16th ACM Conference on
Recommender Systems, 2022, p. 59–70.
[29] N. Vincent, B. Hecht, S. Sen, “Data Strikes”: Evaluating the Effectiveness of a New Form of
Collective Action Against Technology Companies, in: The World Wide Web Conference,
2019, pp. 1931–1943.
[30] N. Vincent, H. Li, N. Tilly, S. Chancellor, B. Hecht, Data Leverage: A Framework for
Empowering the Public in Its Relationship with Technology Companies, in: Proceedings
of the 2021 ACM Conference on Fairness, Accountability, and Transparency, FAccT ’21,
2021, pp. 215–227.
[31] A. Birhane, W. Isaac, V. Prabhakaran, M. Diaz, M. C. Elish, I. Gabriel, S. Mohamed, Power
to the people? opportunities and challenges for participatory ai, in: Proceedings of the 2nd
ACM Conference on Equity and Access in Algorithms, Mechanisms, and Optimization,
2022.
[32] M. Hardt, M. Jagadeesan, C. Mendler-Dünner, Performative Power, in: Advances in Neural
Information Processing Systems, 2022.
[33] M. Hardt, C. Mendler-Dünner, Performative prediction: Past and future, arXiv preprint
arXiv:2310.16608 (2023).
[34] M. Olson, The logic of collective action: public goods and the theory of groups., Harvard
University Press, 1965.
[35] J. Baumann, C. Mendler-Dünner, Algorithmic collective action in recommender systems:
Promoting songs by reordering playlists, ArXiv preprint arXiv:2404.04269 (2024).