About

Explore research on political communication, media, and public opinion by UCLA Professor Stuart Soroka, focusing on negativity in news and democracy.

Research topics

• Political Science
• Sociology
• Law
• Medicine
• Social Science
• Computer Science
• Psychology
• Economics
• Art
• Advertising
• Epistemology
• Public administration
• World Wide Web
• Data science
• Geography
• Media studies
• Demographic economics
• Business
• Social psychology
• Engineering
• Public relations
• Management science
• Political economy
• Biology

Selected publications

• Fanning the Frames: News Organizations’ versus Individuals’ Online Images of Protest

  Computational Communication Research · 2026-04-20

  articleOpen access

  Recent developments in both mobile technology and social media have produced significant shifts in both the volume and nature of current events images available to the public. Whereas images of current events used to be the sole domain of professional photojournalists, now nearly anyone with a mobile phone can witness and photograph an event, and distribute that photograph to the public at large. This paper explores roughly 9.5 million tweets and nearly 807,000 images about the August 2017 Unite the Right protest in Charlottesville, VA. We assign “frames” to images, and consider variation in framing across news organizations and individuals. We find individuals' accounts engage in more diverse framing than news organizations, and that there is no convergence of framing over time between individuals and the media. These results have important implications for the diversity of perspectives represented in online discourse, and raise questions about the roles – both positive and negative – of “citizen photojournalists.”

  PublisherDOI

• Engaging to Oppose: Cross-Cutting Patterns in Hostile News Commentary

  The International Journal of Press/Politics · 2026-02-18

  articleOpen accessSenior author

  Prior work shows that passive news engagement, such as selection and consumption, exhibits strong news selectivity. Far less attention has been given to more active forms of news engagement, however. News commentary, an active form of engagement, may reflect cross-cutting engagement rather than pro-attitudinal selectivity, given its expressive and often confrontational nature. Using ten years of commenting data from South Korea’s largest news aggregator—amounting to over 250 million comments posted by approximately six million users—and a deep-learning content analysis to classify political attitudes and hostility, we examine whether hostile commentary is indeed characterized by cross-cutting patterns across both content and source levels. We specifically analyze whether users comment on counter-attitudinal news stories and whether hostile commenters are structurally confined within fragmented outlet clusters in co-engagement media networks. Findings show that hostile commenters are more likely to cross boundaries by targeting opposing news stories and exhibit weaker echo chamber structures, reflecting cross-cutting engagement beyond their clusters. This pattern is especially pronounced in political and societal domains. In today’s media environment, hostility and opposition may ironically disrupt, rather than reinforce, echo chambers.

  PublisherDOI

• Political polarization as a co-adaptive process

  Journal of Communication · 2026-01-09

  articleOpen access1st authorCorresponding

  Abstract Political polarization is often characterized as a consequence of changes in media content or technology. We argue, in contrast, for an account that views polarization in media and the public as a co-adaptive process. This paper begins with a brief review of cultural evolution and co-adaptation and then considers the application of similar ideas to changes in media and the public over time. Using formal models, we suggest that—in combination with the human tendency toward in-group bias—a co-adaptive (rather than unidirectional) relationship can best account for real-world dynamics. We consider the implications of these findings for our understanding of media effects and technological innovation in polarization, representative democracy, and mass-mediated communication more broadly.

  PublisherDOI

• How Do Politicians’ Own Opinions Affect Their Information Intake? A Survey Experiment among Belgian and Canadian Elected Representatives

  Representation · 2026-03-08

  article
  PublisherDOI

• Negativity and Misinformation

  Political Communication · 2026-02-25

  article1st authorCorresponding
  PublisherDOI

• Negativity bias

  Edward Elgar Publishing eBooks · 2025-12-16

  book-chapter1st authorCorresponding
  PublisherDOI

• The implications of self-reported and physiologically measured disgust sensitivity for climate change risk perception

  Journal of Science Communication · 2025-12-03

  articleOpen access

  This study examines the relationship between disgust sensitivity and climate change risk perceptions, using both self-reported and psychophysiological measures of disgust sensitivity. We find that disgust sensitivity is connected to climate change risk perception, although results are far weaker with physiological measures than with self-reports. Results consequently suggest that the connection may stem more from cognitive and expressive factors than implicit biological impulses. Given theoretical functions of disgust, these findings offer valuable insights regarding the structure of environmental attitudes and heterogeneity in the effects of science and environmental communication.

  PublisherOA PDFDOI

• Embracing Dialectic Intersubjectivity: Coordination of Differential Perspectives in Content Analysis With LLM Persona Simulation

  Social Science Computer Review · 2025-12-23

  preprintOpen accessSenior author

  This study attempts to advance automated content analysis from consensus-oriented to coordination-oriented practices, thereby embracing diverse coding outputs and exploring the dynamics among differential perspectives. As an exploratory investigation, we evaluate six GPT-4o configurations to analyze sentiment in Fox News and MSNBC transcripts on Biden and Trump during the 2020 U.S. presidential campaign. By assessing each model’s alignment with partisan perspectives, we explore how partisan selective processing can be identified in LLM-Assisted Content Analysis (LACA). The findings indicate that LLM-based partisan perspective simulations reflect politically polarized standpoints across partisan groups, revealing a pronounced divergence in sentiment analysis between Democrat-aligned and Republican-aligned persona models. This pattern is evident in intercoder-reliability metrics, which are higher among same-partisan than cross-partisan persona model pairs. Results also suggest that LLM partisan simulations exhibit stronger ideological biases when analyzing politically congruent content. This approach enhances the nuanced understanding of LLM outputs and advances the integrity of AI-driven social science research and may also enable simulations of real-world implications.

  PublisherOA PDFDOI

• Replication Data for: Negativity and Misinformation

  Harvard Dataverse · 2025-12-19

  datasetOpen access1st authorCorresponding

  This submission includes the replication materials (dataset, and R script) for "Negativity and Misinformation," forthcoming in Political Communication.

  PublisherDOI

• Everything everywhere all at once: How Zohran Mamdani campaigned both online and with a ground game

  2025-12-04

  article1st authorCorresponding
  PublisherDOI

Recent grants

• Collaborative Research: Mass Media and Representative Democracy

  NSF · $151k · 2017–2022

Frequent coauthors

• Christopher Wlezien

  The University of Texas at Austin

  87 shared

• Patrick Fournier

  33 shared

• Lilach Nir

  Hebrew University of Jerusalem

  23 shared

• Shanto Iyengar

  Stanford University

  20 shared

• Allison Harell

  Université du Québec à Montréal

  20 shared

• Richard Johnston

  17 shared

• Keith Banting

  Queen's University

  15 shared

• Toril Aalberg

  Norwegian University of Science and Technology

  11 shared

Education

• PhD, Political Science

  University of British Columbia

  2000