ABSTRACT
Recommender systems in social platforms attract attention in part because of their potential impact over political phenomena, such as polarization or fragmentation of online communities. These research topics are also important because of the need for understanding systemic effects in view of upcoming risk-oriented AI regulation in the EU and the US. A common approach leverages outcomes of recommendations to audit recommender systems. A different approach is that of explainability, seeking to render recommendation mechanisms intelligible to humans, potentially enabling both auditing and actionable design tools. This second approach is particularly challenging in the context of online systems of political opinions because of the intrinsic unobservability of opinions. In this article we leverage multi-dimensional political opinion estimation of large online populations (along a left-right dimension but also along other political dimensions) to investigate latent spaces in representation learning computed by recommender systems. We train a recommender based on ubiquitous collaborative filtering principles using data on content sharing on Twitter by a large population, evaluating accuracy and extracting a latent space representation leveraged by the recommender. On the other hand, we leverage multi-dimensional political opinion inference to position users in political spaces representing their opinions. We then show for the first time the relation between latent representations leveraged by a recommender system and the spatial representation of users. We show that some dimensions learned by the recommender capture ideological positions of users, bridging politics and algorithmics in our social and algorithmic system, opening a path towards political explainability of AI.
- N. Gaumont, M. Panahi, and D. Chavalarias, "Reconstruction of the socio-semantic dynamics of political activist Twitter networks---Method and application to the 2017 French presidential election," PLOS ONE, vol. 13, no. 9, p. e0201879, Sep. 2018.Google ScholarCross Ref
- S. Messing and S. J. Westwood, "Selective Exposure in the Age of Social Media: Endorsements Trump Partisan Source Affiliation When Selecting News Online," Communication Research, vol. 41, no. 8, pp. 1042--1063, Dec. 2014.Google ScholarCross Ref
- W. L. Bennett and S. Iyengar, "A New Era of Minimal Effects? the Changing Foundations of Political Communication," Journal of Communication, vol. 58, no. 4, pp. 707--731, Dec. 2008.Google ScholarCross Ref
- C. A. Gomez-Uribe and N. Hunt, "The Netflix Recommender System: Algorithms, Business Value, and Innovation," ACM Transactions on Management Information Systems, vol. 6, no. 4, pp. 13:1--13:19, Dec. 2016.Google ScholarDigital Library
- D. Jannach and M. Jugovac, "Measuring the Business Value of Recommender Systems," ACM Transactions on Management Information Systems, vol. 10, no. 4, pp. 16:1--16:23, Dec. 2019.Google ScholarDigital Library
- D. O'Callaghan, D. Greene, M. Conway, J. Carthy, and P. Cunningham, "Down the (White) Rabbit Hole: The Extreme Right and Online Recommender Systems," Social Science Computer Review, vol. 33, no. 4, pp. 459--478, Aug. 2015.Google ScholarDigital Library
- A. J. B. Chaney, B. M. Stewart, and B. E. Engelhardt, "How algorithmic confounding in recommendation systems increases homogeneity and decreases utility," in Proceedings of the 12th ACM Conference on Recommender Systems, ser. RecSys '18. New York, NY, USA: Association for Computing Machinery, Sep. 2018, pp. 224--232.Google ScholarDigital Library
- M. Haim, A. Graefe, and H.-B. Brosius, "Burst of the Filter Bubble?" Digital Journalism, vol. 6, no. 3, pp. 330--343, Mar. 2018.Google ScholarCross Ref
- Y. Benkler, R. Faris, and H. Roberts, Network propaganda: Manipulation, disinformation, and radicalization in American politics. Oxford University Press, 2018.Google ScholarCross Ref
- E. Bakshy, S. Messing, and L. A. Adamic, "Exposure to ideologically diverse news and opinion on facebook," Science, vol. 348, no. 6239, pp. 1130--1132, 2015.Google ScholarCross Ref
- P. Ramaciotti, R. Lamarche-Perrin, R. Fournier-S'Niehotta, R. Poulain, L. Tabourier, and F. Tarissan, "Measuring diversity in heterogeneous information networks," Theoretical computer science, vol. 859, pp. 80--115, 2021.Google ScholarCross Ref
- J. Bobadilla, F. Ortega, A. Hernando, and A. Gutiérrez, "Recommender systems survey," Knowledge-based systems, vol. 46, pp. 109--132, 2013.Google ScholarDigital Library
- P. Ramaciotti Morales and J.-P. Cointet, "Auditing the effect of social network recommendations on polarization in geometrical ideological spaces," in Proceedings of the 15th ACM Conference on Recommender Systems, 2021, pp. 627--632.Google Scholar
- R. Marcinkevičs and J. E. Vogt, "Interpretability and Explainability: A Machine Learning Zoo Mini-tour," Dec. 2020.Google Scholar
- N. Tintarev and J. Masthoff, "A Survey of Explanations in Recommender Systems," in 2007 IEEE 23rd International Conference on Data Engineering Workshop, Apr. 2007, pp. 801--810.Google Scholar
- R. Bakker, S. Jolly, and J. Polk, "Complexity in the European party space: Exploring dimensionality with experts," European Union Politics, vol. 13, no. 2, pp. 219--245, Jun. 2012.Google ScholarCross Ref
- P. Ramaciotti and Z. Vagena, "Embedding social graphs from multiple national settings in common empirical opinion spaces," in 2022 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM). IEEE, 2022, pp. 60--67.Google Scholar
- P. Ramaciotti Morales, J.-P. Cointet, and G. M. Zolotoochin, "Unfolding the dimensionality structure of social networks in ideological embeddings," Aug 2021. [Online]. Available: https://hal.archives-ouvertes.fr/hal-03315759Google Scholar
- P. Ramaciotti Morales, J.-P. Cointet, G. Muñoz Zolotoochin, A. Fernández Peralta, G. Iñiguez, and A. Pournaki, "Inferring attitudinal spaces in social networks," Social Network Analysis and Mining, vol. 13, no. 1, pp. 1--18, 2023.Google Scholar
- R. Bakker, L. Hooghe, S. Jolly, G. Marks, J. Polk, J. Rovny, M. Steenbergen, and M. A. Vachudova, "2019 chapel hill expert survey," Chapel Hill, 2020, www.chesdata.eu.Google Scholar
- Y. Koren, "Factorization meets the neighborhood: a multifaceted collaborative filtering model," in Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining, 2008, pp. 426--434.Google Scholar
- J. Bobadilla, F. Ortega, A. Hernando, and A. Gutiérrez, "Recommender systems survey," Knowledge-Based Systems, vol. 46, pp. 109--132, Jul. 2013.Google ScholarDigital Library
- A. Cichocki and A.-H. Phan, "Fast Local Algorithms for Large Scale Nonnegative Matrix and Tensor Factorizations," IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, vol. E92.A, no. 3, pp. 708--721, 2009.Google Scholar
- D. Lee and H. S. Seung, "Algorithms for Non-negative Matrix Factorization," in Advances in Neural Information Processing Systems, vol. 13. MIT Press, 2000.Google Scholar
- C. Boutsidis and E. Gallopoulos, "SVD based initialization: A head start for nonnegative matrix factorization," Pattern Recognition, vol. 41, no. 4, pp. 1350--1362, Apr. 2008.Google ScholarDigital Library
- J. Kennedy and R. Eberhart, "Particle swarm optimization," in Proceedings of ICNN'95 - International Conference on Neural Networks, vol. 4, Nov. 1995, pp. 1942--1948 vol.4.Google Scholar
- A. Gunawardana and G. Shani, "A Survey of Accuracy Evaluation Metrics of Recommendation Tasks," Journal of Machine Learning Research, pp. 2935--2962, 2009.Google Scholar
- W. Hu, M. Fey, M. Zitnik, Y. Dong, H. Ren, B. Liu, M. Catasta, and J. Leskovec, "Open Graph Benchmark: Datasets for Machine Learning on Graphs," Feb. 2021.Google Scholar
Index Terms
- Discovering ideological structures in representation learning spaces in recommender systems on social media data
Recommendations
Acquiring User Information Needs for Recommender Systems
WI-IAT '13: Proceedings of the 2013 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT) - Volume 03Most recommender systems attempt to use collaborative filtering, content-based filtering or hybrid approach to recommend items to new users. Collaborative filtering recommends items to new users based on their similar neighbours, and content-based ...
A Scalable, Accurate Hybrid Recommender System
WKDD '10: Proceedings of the 2010 Third International Conference on Knowledge Discovery and Data MiningRecommender systems apply machine learning techniques for filtering unseen information and can predict whether a user would like a given resource. There are three main types of recommender systems: collaborative filtering, content-based filtering, and ...
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