Skip to main content
SpringerLink
Log in
Book cover

International Workshop on Algorithmic Bias in Search and Recommendation

BIAS 2022: Advances in Bias and Fairness in Information Retrieval pp 82–90Cite as

Mitigating Popularity Bias in Recommendation: Potential and Limits of Calibration Approaches

Part of the Communications in Computer and Information Science book series (CCIS,volume 1610)

Abstract

While recommender systems are highly successful at helping users find relevant information online, they may also exhibit a certain undesired bias of mostly promoting only already popular items. Various approaches of quantifying and mitigating such biases were put forward in the literature. Most recently, calibration methods were proposed that aim to match the popularity of the recommended items with popularity preferences of individual users. In this paper, we show that while such methods are efficient in avoiding the recommendation of too popular items for some users, other techniques may be more effective in reducing the popularity bias on the platform level. Overall, our work highlights that in practice choices regarding metrics and algorithms have to be made with caution to ensure the desired effects.

Keywords

  • Recommender Systems
  • Bias
  • Multi-Metric Evaluation

This is a preview of subscription content, access via your institution.

Chapter
USD   29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD   54.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD   69.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Learn about institutional subscriptions

Notes

  1. 1.

    Similar ideas were proposed earlier in [14] and [17], and later independently popularized under the term calibration in [19].

  2. 2.

    Differently from [2], we used the MovieLens dataset with about 100k ratings by 943 users on 1612 items of in our experiments.

  3. 3.

    Interestingly, in [2], CP was favorable over XQ also on the ARP measure. We could not reproduce this finding for both datasets. Unfortunately, the authors of [2] could not reproduce the code of the CP method. The observed discrepancy might therefore be both related to dataset characteristics and differences in the implementation.

References

  1. Abdollahpouri, H., Burke, R., Mobasher, B.: Managing popularity bias in recommender systems with personalized re-ranking. In: FLAIRS 2019, pp. 413–418 (2019)

    Google Scholar 

  2. Abdollahpouri, H., Mansoury, M., Burke, R., Mobasher, B., Malthouse, E.: User-centered evaluation of popularity bias in recommender systems. In: ACM UMAP 2021, pp. 119–129 (2021)

    Google Scholar 

  3. Boratto, L., Fenu, G., Marras, M.: The effect of algorithmic bias on recommender systems for massive open online courses. In: European Conference on Information Retrieval, pp. 457–472 (2019)

    Google Scholar 

  4. Boratto, L., Fenu, G., Marras, M.: Combining mitigation treatments against biases in personalized rankings: use case on item popularity. In: IIR 2021 (2021)

    Google Scholar 

  5. Boratto, L., Fenu, G., Marras, M.: Connecting user and item perspectives in popularity debiasing for collaborative recommendation. IP&M 58(1), 102387 (2021)

    Google Scholar 

  6. Borges, R., Stefanidis, K.: On mitigating popularity bias in recommendations via variational autoencoders. In: ACM/SIGAPP SAC 2021, pp. 1383–1389 (2021)

    Google Scholar 

  7. Castells, P., Hurley, N.J., Vargas, S.: Novelty and diversity in recommender systems. In: Ricci, F., Rokach, L., Shapira, B. (eds.) Recommender Systems Handbook, pp. 881–918. Springer, New York (2015)

    Google Scholar 

  8. Elahi, M., Jannach, D., Skjærven, L., et al.: Towards responsible media recommendation. AI and Ethics (2021)

    Google Scholar 

  9. Elahi, M., Kholgh, D.K., Kiarostami, M.S., Saghari, S., Rad, S.P., Tkalcic, M.: Investigating the impact of recommender systems on user-based and item-based popularity bias. Inf. Process. Manage. 58, 102655 (2021)

    Google Scholar 

  10. Fleder, D., Hosanagar, K.: Blockbuster culture’s next rise or fall: the impact of recommender systems on sales diversity. Manage. Sci. 55, 697–712, 102655 (2009)

    Google Scholar 

  11. Harper, F.M., Konstan, J.A.: The MovieLens datasets: history and context. ACM TIIS 5(4), 1–19, 102655 (2015)

    Google Scholar 

  12. Jannach, D., Jugovac, M.: Measuring the business value of recommender systems. ACM Trans. Manage. Inf. Syst. 10(4) (2019)

    Google Scholar 

  13. Jannach, D., Lerche, L., Kamehkhosh, I., Jugovac, M.: What recommenders recommend: an analysis of recommendation biases and possible countermeasures. User Model. User-Adap. Inter. 25(5), 427–491 (2015). https://doi.org/10.1007/s11257-015-9165-3

    CrossRef  Google Scholar 

  14. Jugovac, M., Jannach, D., Lerche, L.: Efficient optimization of multiple recommendation quality factors according to individual user tendencies. Expert Syst. Appl. 81, 321–331 (2017)

    CrossRef  Google Scholar 

  15. Kowald, D., Schedl, M., Lex, E.: The unfairness of popularity bias in music recommendation: a reproducibility study. In: European Conference on Information Retrieval, pp. 35–42 (2020)

    Google Scholar 

  16. Lin, J.: Divergence measures based on the Shannon entropy. IEEE Trans. Inf. Theory 37(1), 145–151 (1991)

    CrossRef  MathSciNet  Google Scholar 

  17. Oh, J., Park, S., Yu, H., Song, M., Park, S.T.: Novel recommendation based on personal popularity tendency. In: ICDM 2011, pp. 507–516 (2011)

    Google Scholar 

  18. Santos, R.L., Macdonald, C., Ounis, I.: Exploiting query reformulations for web search result diversification. In: WWW 2010, pp. 881–890 (2010)

    Google Scholar 

  19. Steck, H.: Calibrated recommendations. In: ACM RecSys 2018, pp. 154–162 (2018)

    Google Scholar 

  20. Takács, G., Tikk, D.: Alternating least squares for personalized ranking. In: ACM RecSys 2012, pp. 83–90 (2012)

    Google Scholar 

  21. Trattner, C., Elsweiler, D.: Investigating the healthiness of internet-sourced recipes: implications for meal planning and recommender systems. In: WWW 2017, pp. 489–498 (2017)

    Google Scholar 

  22. Trattner, C., et al.: Responsible media technology and AI: challenges and research directions. AI and Ethics, pp. 1–10 (2021)

    Google Scholar 

  23. Yin, H., Cui, B., Li, J., Yao, J., Chen, C.: Challenging the long tail recommendation. Proc. VLDB Endow. 5(9), 896–907 (2012)

    CrossRef  Google Scholar 

  24. Zehlike, M., Bonchi, F., Castillo, C., Hajian, S., Megahed, M., Baeza-Yates, R.: FA*IR: a Fair Top-k ranking algorithm. In: CIKM 2017, pp. 1569–1578 (2017)

    Google Scholar 

Download references

Acknowledgement

This work was supported by industry partners and the Research Council of Norway with funding to MediaFutures: Research Centre for Responsible Media Technology and Innovation, through The Centres for Research-based Innovation scheme, project number 309339.

Author information

Authors and Affiliations

  1. University of Bergen, Bergen, Norway

    Anastasiia Klimashevskaia, Mehdi Elahi & Christoph Trattner

  2. University of Klagenfurt, Klagenfurt, Austria

    Dietmar Jannach

  3. TV 2, Bergen, Norway

    Lars Skjærven

Authors
  1. Anastasiia Klimashevskaia
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mehdi Elahi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Dietmar Jannach
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Christoph Trattner
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Lars Skjærven
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Anastasiia Klimashevskaia .

Editor information

Editors and Affiliations

  1. University of Cagliari, Cagliari, Italy

    Ludovico Boratto

  2. Sapienza University of Rome, Rome, Italy

    Stefano Faralli

  3. University of Cagliari, Cagliari, Italy

    Mirko Marras

  4. University of L’Aquila, L’Aquila, Italy

    Dr. Giovanni Stilo

Rights and permissions

Reprints and Permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Klimashevskaia, A., Elahi, M., Jannach, D., Trattner, C., Skjærven, L. (2022). Mitigating Popularity Bias in Recommendation: Potential and Limits of Calibration Approaches. In: Boratto, L., Faralli, S., Marras, M., Stilo, G. (eds) Advances in Bias and Fairness in Information Retrieval. BIAS 2022. Communications in Computer and Information Science, vol 1610. Springer, Cham. https://doi.org/10.1007/978-3-031-09316-6_8

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-09316-6_8

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-09315-9

  • Online ISBN: 978-3-031-09316-6

  • eBook Packages: Computer ScienceComputer Science (R0)

search

Navigation