Social Network Optimization to Reduce Opinion Polarization Using a Graph Pooling Policy Network
Abstract/Contents
- Abstract
- In recent years there has been a substantial increase in sociopolitical polarization—it is clear that our society does not agree on issues in politics, healthcare, education, and beyond. Evidence of polarization in politics has been found in the increasingly partisan voting patterns of the members of Congress (Poole and Rosenthal (1984), Poole and Rosenthal (1991)) and widespread partisan sorting (Baldassarri and Gelman (2008)). Indeed, McCarty et al. (2016) claim via rigorous analysis that America is polarized in terms of political attitudes and beliefs.Drawing on the computational sociology approach presented by Macy and Willer (2002), this research operationalizes a sociotechnical perspective where agent-based modeling assists in simulating the social dynamics underpinning observed trends. The study incorporates the interplay of individual actors within the social network structure, moving beyond conventional statistical analyses to an agent-centered understanding of polarization phenomena.Empirical studies have argued that that homophily, i.e., greater interaction between like-minded individuals, results in polarization (Gilbert et al. (2009), Baron et al. (1996), Sunstein (2002)). Butas Dandekar et al. (2013) show, homophily alone, without biased assimilation, is not sufficient to polarize society. Indeed, research has shown that biases lead to more network homophily and, overtime, more homophily leads to actions that put more weight on biases and less weight on expert opinion (Hakobyan and Koulovatianos (2019)). This interplay between homophily plus confirmation and assimilation bias result in opinion polarization.Counterintuitively, the increase polarization has been accompanied by the growth of social media platforms where individuals are sharing more information more than ever before and are able to connect with others across a wider range of communities (Silver et al. (2019)). Despite the ability to connect with a greater diversity of people, individual’s beliefs have become more ideologically constrained and extreme in some areas (Kozlowski and Murphy (2021)). Research into social networks and the role of bias, as well as “echo chambers,” have indicated that the structure of social networks can make consensus harder to reach, potentially preventing exposure to other opinions,even despite increases in the total number of connections in a network. As such, modifications to asocial network through purposeful addition of edges may enable less polarization.
Description
| Type of resource | text |
|---|---|
| Publication date | July 19, 2023 |
Creators/Contributors
| Author | Schaider, Isaac | |
|---|---|---|
| Advisor | Willer, Robb |
Subjects
| Subject | sociopolitical polarization, polarization, computational sociology, social networks |
|---|---|
| Genre | Text |
| Genre | Thesis |
Bibliographic information
Access conditions
- Use and reproduction
- User agrees that, where applicable, content will not be used to identify or to otherwise infringe the privacy or confidentiality rights of individuals. Content distributed via the Stanford Digital Repository may be subject to additional license and use restrictions applied by the depositor.
- License
- This work is licensed under a Creative Commons Attribution Non Commercial No Derivatives 4.0 International license (CC BY-NC-ND).
Preferred citation
- Preferred citation
- Schaider, I. (2023). Social Network Optimization to Reduce Opinion Polarization Using a Graph Pooling Policy Network. Stanford Digital Repository. Available at https://purl.stanford.edu/vy483bt6545.
Collection
Stanford University, Department of Sociology, Co-terminal Master's thesis collection.
View other items in this collection in SearchWorksContact information
- Contact
- ischaider@hotmail.com
Also listed in
Loading usage metrics...