The Closed Loop Between Opinion Formation and Personalized Recommendations

Rossi, Wilbert Samuel; Polderman, Jan Willem; Frasca, Paolo

doi:10.1109/tcns.2021.3105616

Cited by 26 publications

(18 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given that such polarization is also evident in real world social networks, in this section we examine potential methods to counter, prevent, or even reverse extreme polarization. Recent research on polarisation mitigation and opinion control suggests various approaches, for example, Musco et al studied ways to minimise polarisation and disagreement in social networks 27 , Garimella et al suggests controversy can be reduced by connecting opposing views 28 , Rossi et al studied closed loops between opinion formation and personalised recommendations 29 , while Matakos et al proposed a recommender-based approach to break filter bubbles in social media 30 . Here we examine two techniques in use today by social networks to see their effectiveness in our model.…”

Section: Countering Extreme Polarizationmentioning

confidence: 99%

Opinion amplification causes extreme polarization in social networks

Lim

Bentley

2022

Sci Rep

View full text Add to dashboard Cite

Extreme polarization of opinions fuels many of the problems facing our societies today, from issues on human rights to the environment. Social media provides the vehicle for these opinions and enables the spread of ideas faster than ever before. Previous computational models have suggested that significant external events can induce extreme polarization. We introduce the Social Opinion Amplification Model (SOAM) to investigate an alternative hypothesis: that opinion amplification can result in extreme polarization. SOAM models effects such as sensationalism, hype, or “fake news” as people express amplified versions of their actual opinions, motivated by the desire to gain a greater following. We show for the first time that this simple idea results in extreme polarization, especially when the degree of amplification is small. We further show that such extreme polarization can be prevented by two methods: preventing individuals from amplifying more than five times, or through consistent dissemination of balanced opinions to the population. It is natural to try and have the loudest voice in a crowd when we seek attention; this work suggests that instead of shouting to be heard and generating an uproar, it is better for all if we speak with moderation.

show abstract

Section: Countering Extreme Polarizationmentioning

confidence: 99%

Opinion amplification causes extreme polarization in social networks

Lim

Bentley

2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…For this advanced model, the authors obtained a mean-field approximation and derived conditions under which a consensus state can be achieved. In (Rossi et al, 2021), the authors developed a model in which an agent communicates with an online news aggregator. They showed that ranking algorithms, while pursuing their commercial purposes, make users' opinions more extreme.…”

Section: Literaturementioning

confidence: 99%

“…(when new information is perceived in a form that aligns existing belief systems) (Haghtalab et al, 2021). Next, the online domain is subject to moderation by ranking algorithms that may push people into closed information loops with no access to challenging content (Rossi et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

“…To the best of our knowledge, there are no studies that capture all the points raised above. Some papers have already concerned the issue of users' interactions in the online domain subject to moderation by personalization systems (Maes & Bischofberger, 2015;Perra & Rocha, 2019;Rossi et al, 2021). However, all these studies were drawn from minimal models of online interactions, ignoring the rich nature of online communication tools.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Opinion Formation in Online Public Debates Structured in Information Cascades: A System-Theoretic Viewpoint

Kozitsin¹

2023

Preprint

View full text Add to dashboard Cite

Information cascades (tree-like structures formed by posts, comments, likes, replies, etc.) constitute the spine of the public online information environment, reflecting its various trends, evolving with it and, importantly, affecting its development. While users participate in online discussions, they display their views and thus contribute to the growth of cascades. At the same time, users’ opinions are influenced by cascades’ elements. The current paper aims to advance our knowledge regarding this social phenomenon by developing an agent-based model in which agents participate in a discussion around a post on the Internet. Agents display their opinions by writing comments on the post and liking them (i.e., leaving positive assessments). The result of these processes is dual: on the one hand, agents develop an information cascade; on the other hand, they update their views. Our purpose is to understand how agents’ activity, openness to influence, and cognitive constraints (that condition the amount of information individuals are able to proceed with) affect opinion dynamics. We also control for social contagions (when people’ perception of a message may depend not only on the message’s opinion, but also on how other individuals perceive this object, with more positive evaluations increasing the probability of adoption) and ranking algorithms that steer the order in which agents learn new messages. Among other things, we demonstrated that replies to disagreeable opinions are extremely effective for promoting your own position. In contrast, likes have a tiny effect on this issue.

show abstract

“…Groups of individuals with no access to challenging content are called echo chambers (Jasny et al, 2015). The proliferation of OSN usage may facilitate the formation of echo chambers as OSNs are supposed to accelerate the strength of confirmation bias due to personalization systems -algorithms that determine which content a user will be exposed to (Bakshy et al, 2015;Geschke et al, 2019;Kozyreva et al, 2020;Maes & Bischofberger, 2015;Perra & Rocha, 2019;Rossi et al, 2019). However, some studies have demonstrated that confirmation bias may not be a key mechanism in information consumption: for example, in (Feldman, 2011), it was argued that direct persuasion (Mäs & Flache, 2013) plays an essential role when individuals consume opinionated information.…”

Section: Radicalization Of Opinionsmentioning

confidence: 99%

Opinion dynamics of online social network users: a micro-level analysis

Kozitsin

2021

The Journal of Mathematical Sociology

View full text Add to dashboard Cite

In this paper, we present an empirical study of the opinion dynamics of a large-scale sample of online social network users. Opinions of users are estimated based on their subscriptions to information sources and we analyze how friendship connections affect the dynamics of these estimations. Our analysis has revealed traces of both positive (assimilative) and negative (repulsive) influence in how users decide whether to change their opinions, while magnitudes of changed opinions appear to obey a positive influence. We also found that individuals with networks that include many ideologically opposite users are less prone to radicalization than those with homogenous ones. Our results indicate that the opinion dynamics of online social network users cannot be described solely by any concrete theoretical opinion formation model; rather, they include patterns of multiple models simultaneously.

show abstract

The Closed Loop Between Opinion Formation and Personalized Recommendations

Cited by 26 publications

References 47 publications

Opinion amplification causes extreme polarization in social networks

Opinion amplification causes extreme polarization in social networks

Opinion Formation in Online Public Debates Structured in Information Cascades: A System-Theoretic Viewpoint

Opinion dynamics of online social network users: a micro-level analysis

Contact Info

Product

Resources

About