1
|
Bellina A, Castellano C, Pineau P, Iannelli G, De Marzo G. Effect of collaborative-filtering-based recommendation algorithms on opinion polarization. Phys Rev E 2023; 108:054304. [PMID: 38115540 DOI: 10.1103/physreve.108.054304] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/03/2023] [Accepted: 09/11/2023] [Indexed: 12/21/2023]
Abstract
A central role in shaping the experience of users online is played by recommendation algorithms. On the one hand they help retrieving content that best suits users taste, but on the other hand they may give rise to the so-called "filter bubble" effect, favoring the rise of polarization. In the present paper we study how a user-user collaborative-filtering algorithm affects the behavior of a group of agents repeatedly exposed to it. By means of analytical and numerical techniques we show how the system stationary state depends on the strength of the similarity and popularity biases, quantifying respectively the weight given to the most similar users and to the best rated items. In particular, we derive a phase diagram of the model, where we observe three distinct phases: disorder, consensus, and polarization. In the last users spontaneously split into different groups, each focused on a single item. We identify, at the boundary between the disorder and polarization phases, a region where recommendations are nontrivially personalized without leading to filter bubbles. Finally, we show that our model well reproduces the behavior of users on the online music platform last.fm. This analysis paves the way to a systematic analysis of recommendation algorithms by means of statistical physics methods and opens the possibility of devising less polarizing recommendation algorithms.
Collapse
Affiliation(s)
- Alessandro Bellina
- Dipartimento di Fisica Università "Sapienza," P. le A. Moro, 2, I-00185 Rome, Italy
- Centro Ricerche Enrico Fermi, Piazza del Viminale, 1, I-00184 Rome, Italy
| | - Claudio Castellano
- Centro Ricerche Enrico Fermi, Piazza del Viminale, 1, I-00184 Rome, Italy
- Istituto dei Sistemi Complessi (ISC-CNR), Via dei Taurini 19, I-00185 Rome, Italy
| | - Paul Pineau
- École Normale Supérieure Paris-Saclay, 4 Avenue des Sciences, 91190 Gif-sur-Yvette, France
| | - Giulio Iannelli
- Centro Ricerche Enrico Fermi, Piazza del Viminale, 1, I-00184 Rome, Italy
- Dipartimento di Fisica, Università di Roma "Tor Vergata," 00133 Rome, Italy
| | - Giordano De Marzo
- Dipartimento di Fisica Università "Sapienza," P. le A. Moro, 2, I-00185 Rome, Italy
- Centro Ricerche Enrico Fermi, Piazza del Viminale, 1, I-00184 Rome, Italy
- Complexity Science Hub Vienna, Josefstädter Strasse 39, 1080, Vienna, Austria
- Sapienza School for Advanced Studies, "Sapienza," P. le A. Moro, 2, I-00185 Rome, Italy
| |
Collapse
|
2
|
Zimmaro F, Contucci P, Kertész J. Voter-like Dynamics with Conflicting Preferences on Modular Networks. ENTROPY (BASEL, SWITZERLAND) 2023; 25:838. [PMID: 37372182 DOI: 10.3390/e25060838] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/06/2023] [Revised: 05/08/2023] [Accepted: 05/12/2023] [Indexed: 06/29/2023]
Abstract
Two of the main factors shaping an individual's opinion are social coordination and personal preferences, or personal biases. To understand the role of those and that of the topology of the network of interactions, we study an extension of the voter model proposed by Masuda and Redner (2011), where the agents are divided into two populations with opposite preferences. We consider a modular graph with two communities that reflect the bias assignment, modeling the phenomenon of epistemic bubbles. We analyze the models by approximate analytical methods and by simulations. Depending on the network and the biases' strengths, the system can either reach a consensus or a polarized state, in which the two populations stabilize to different average opinions. The modular structure generally has the effect of increasing both the degree of polarization and its range in the space of parameters. When the difference in the bias strengths between the populations is large, the success of the very committed group in imposing its preferred opinion onto the other one depends largely on the level of segregation of the latter population, while the dependency on the topological structure of the former is negligible. We compare the simple mean-field approach with the pair approximation and test the goodness of the mean-field predictions on a real network.
Collapse
Affiliation(s)
- Filippo Zimmaro
- Department of Computer Science, University of Pisa, 56126 Pisa, Italy
- Department of Mathematics, University of Bologna, 40126 Bologna, Italy
- Department of Network and Data Science, Central European University, 1100 Vienna, Austria
| | | | - János Kertész
- Department of Network and Data Science, Central European University, 1100 Vienna, Austria
| |
Collapse
|
4
|
Iannelli G, De Marzo G, Castellano C. Filter bubble effect in the multistate voter model. CHAOS (WOODBURY, N.Y.) 2022; 32:043103. [PMID: 35489842 DOI: 10.1063/5.0079135] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 11/18/2021] [Accepted: 03/15/2022] [Indexed: 06/14/2023]
Abstract
Social media influence online activity by recommending to users content strongly correlated with what they have preferred in the past. In this way, they constrain users within filter bubbles strongly limiting their exposure to new or alternative content. We investigate this type of dynamics by considering a multistate voter model where, with a given probability λ, a user interacts with "personalized information," suggesting the opinion most frequently held in the past. By means of theoretical arguments and numerical simulations, we show the existence of a nontrivial transition between a region (for small λ) where a consensus is reached and a region (above a threshold λc) where the system gets polarized and clusters of users with different opinions persist indefinitely. The threshold always vanishes for large system size N, showing that a consensus becomes impossible for a large number of users. This finding opens new questions about the side effects of the widespread use of personalized recommendation algorithms.
Collapse
Affiliation(s)
- Giulio Iannelli
- Centro Ricerche Enrico Fermi, Piazza del Viminale, 1, I-00184 Rome, Italy
| | - Giordano De Marzo
- Centro Ricerche Enrico Fermi, Piazza del Viminale, 1, I-00184 Rome, Italy
| | - Claudio Castellano
- Centro Ricerche Enrico Fermi, Piazza del Viminale, 1, I-00184 Rome, Italy
| |
Collapse
|