Skip to main content
University of Wisconsin–Madison

Category: Social Media and Democracy

Team receives $5 million award to continue research on misinformation correction

Course Correct logoThe award will allow researchers to further develop Course Correct, a precision tool providing journalists with guidance against misinformation.

MADISON, Wis. – A team of researchers that developed Course Correct, a tool to help journalists identify and combat misinformation online, will now be testing that tool in the real world, through partnerships with journalists.

The tool offers precision guidance against misinformation via a flexible and dynamic dashboard which helps journalists to identify trending misinformation on social media, strategically correct false claims and test the effectiveness of corrections in real time.

Dhavan Shah headshot

SJMC Professor and MCRC Director Dhavan Shah

“Challenges of misinformation are not restricted to elections and COVID or to a particular community; we see large volumes of false information circulating around product recalls, children’s vaccines, and natural disasters, all of which our system could be adjusted to address,” said University of Wisconsin School of Journalism and Mass Communication Professor Dhavan Shah, a collaborator on the project. “Countering misinformation will require vigilance and adaptation.”

The group received a Phase I grant last year to develop the tool. The next phase of the project will help roll the tool out to a wider audience, funded by a $5 million Phase II Convergence Accelerator cooperative agreement award from the National Science Foundation.

Mike Wagner headshot

SJMC Professor and PI Michael Wagner

“In Phase I, we developed our misinformation detection system and conducted promising preliminary tests of a method to correct misinformation within the networks it is spreading. Now, we will partner with journalists at the local, state and national levels to see how well Course Correct works in real world settings,” said UW SJMC Professor Mike Wagner, the principal investigator on the project. “It’s been thrilling to work with such a diverse team of experts, so many of them with UW ties, as we try to help accurate information find its way into misinformation networks. I hope we can play a small role in helping to increase the flow of accurate information about important issues and reduce the reach and power of misinformation.”

Course Correct’s strategy of observational correction reduces misperceptions across multiple types of issues.

Course Correct’s strategy of observational correction reduces misperceptions across multiple types of issues.

According to a recent Knight Foundation study, 74% of Americans are very concerned about the spread of misinformation on the internet, including strong majorities of both Democrats (84%) and Republicans (65%).

As a part of Phase II, the team will be forming formal partnerships with both local, state, national and global news organizations including The Capital Times in Madison, WI, the Wisconsin Center for Investigative Journalism, Snopes and the International Fact Checking Network. The team plans to present Course Correct to IFCN’s Global Fact 10 Conference in the second year of Phase II and invite signatories to join their team.

Srijan Kumar headshot

Georgia Tech Assistant Professor Srijan Kumar

“Phase I brought together experts with different skillsets who were driven by a shared passion of improving the cyber information ecosystem,” said Srijan Kumar, Assistant Professor at Georgia Tech and collaborator on the project. “In Phase II, I am looking forward to collaborations with the expanded team and I am excited about our impact potential and tools.”

Porismita Borah headshot

Washington State University Associate Professor Porismita Borah

“I’m excited to move this work forward in Phase II, continuing to develop A/B-tested correction strategies against misinformation and evaluating the effectiveness of evidence-based corrections,” said Washington State University Associate Professor Porismita Borah, a collaborator on the project and a UW-Madison SJMC alum. “By testing different strategies at the same time, Course Correct can tell journalists the most effective ways to correct misinformation in the actual networks where the misinformation is doing the most damage.”

The team has a road map for Phase II of the project with several key milestones, including completing the scalable misinformation detection system and the identification of best practices for misinformation correction. Then, they will train journalists on Course Correct and conduct randomized control trials to demonstrate the tool’s value. Next, they will introduce Course Correct to the 135 signatories of the IFCN and incorporate their feedback. Finally, the team will bring additional news organization partners on board after presenting at the Global Fact Summit.

Leticia Bode headshot

Georgetown University Associate Professor Leticia Bode

“The thing that I’m most excited about with regard to this work is how it is effectively combining lots of elements of misinformation research, in order to maximize impact,” said Georgetown University Associate Professor Leticia Bode, a collaborator on the project and an alum of UW-Madison SJMC. “Lots of these elements – mapping misinformation networks, testing corrective information, journalistic fact checking – have been going on, but they’ve mostly operated in isolation. Combining them should significantly increase the impact this work has on actually reducing the spread of misinformation on social media.”

Sijia Yang headshot

SJMC Assistant Professor Sijia Yang

“This project is unique in adopting a convergence accelerator approach where we engage with the journalistic and fact-checking communities from the beginning and throughout the system design and testing phases,” said UW SJMC Assistant Professor Sijia Yang. “We hope to build a system that would empower those working at the frontline fighting mis- and disinformation with real-time signals to identify emerging misinformation, rapid-response A/B testing capacities and evidence-based strategies for effective correction. I am so excited to work with a dream team to address this pressing societal challenge.”

Course Correct identifies creators of misinformation (red), sharers of misinformation (yellow) and the people exposed to the misinformation sharing (green) so journalists can (1) productively choose what to fact check and (2) specifically target at-risk individuals with sponsored content. Journalists we interviewed in Phase I told us that Impact Score figures like this one, for those making false claims that COVID-19 vaccines cause infertility, are extremely useful when it comes to selecting what to fact check.

Course Correct identifies creators of misinformation (red), sharers of misinformation (yellow) and the people exposed to the misinformation sharing (green) so journalists can (1) productively choose what to fact check and (2) specifically target at-risk individuals with sponsored content. Journalists we interviewed in Phase I told us that Impact Score figures like this one, for those making false claims that COVID-19 vaccines cause infertility, are extremely useful when it comes to selecting what to fact check.

Researchers at UW-Madison include Shah, Wagner, Yang and Electrical and Computer Engineering Professor William Sethares. They will work with several collaborators from other institutions, including Borah, Bode, Kumar, Georgia Tech Associate Professor Munmun De Choudhury, University of Minnesota Associate Professor Emily Vraga, and Founder and CEO of Anchor Change Katie Harbath. Borah, Bode, Vraga and Harbath are all UW-Madison SJMC alums.

Emily Vraga headshot

University of Minnesota Associate Professor Emily Vraga

“I’m excited to work with a truly interdisciplinary team focused on practical interventions that can reduce misinformation online,” Vraga said. “The scale of the problem requires us to consider how different strategies can all intersect to help address misinformation on social media. Actively working with journalists and fact-checkers, who will be such an important part of the correction process, will help this project have a meaningful impact on the problem.”

Katie Harbath headshot

CEO and Founder of Anchor Change Katie Harbath

“Combatting mis- and disinformation online is becoming a harder, not easier task to do as bad actors get more sophisticated, use more platforms and different types of content,” Harbath said. “Course Correct holds a lot of promise to help journalists spot, track and refute false narratives quickly. I’m excited the NSF has decided to fund Course Correct for Phase II, as providing tools like this will be crucial not just for the U.S. midterms, but as we go into the 2024 presidential election.”

Launched in 2019, the National Science Foundation’s Convergence Accelerator builds upon research and discovery to accelerate use-inspired convergence research into practical application. The Convergence Accelerator is making timely investments to solve high-risk societal challenges.

New article from SMAD “Vaccine discourse during the onset of the COVID-19 pandemic: Topical structure and source patterns informing efforts to combat vaccine hesitancy”

In the new article “Vaccine discourse during the onset of the COVID-19 pandemic: Topical structure and source patterns informing efforts to combat vaccine hesitancy” in PLoS One, the Social Media and Democracy group extracted a total of 349,979 COVID-19 vaccine-related tweets from the initial period of the pandemic to investigate 1) the major topics that emerged from public conversation on Twitter concerning vaccines for COVID-19, 2) the topics that were emphasized in tweets with either positive or negative sentiment toward a COVID-19 vaccine, and 3) the type of online accounts in which tweets with either positive or negative sentiment were more likely to circulate.

Abstract:

Background: Understanding public discourse about a COVID-19 vaccine in the early phase of the COVID-19 pandemic may provide key insights concerning vaccine hesitancy. However, few studies have investigated the communicative patterns in which Twitter users participate discursively in vaccine discussions.

Objectives: This study aims to investigate 1) the major topics that emerged from public conversation on Twitter concerning vaccines for COVID-19, 2) the topics that were emphasized in tweets with either positive or negative sentiment toward a COVID-19 vaccine, and 3) the type of online accounts in which tweets with either positive or negative sentiment were more likely to circulate.

Methods: We randomly extracted a total of 349,979 COVID-19 vaccine-related tweets from the initial period of the pandemic. Out of 64,216 unique tweets, a total of 23,133 (36.03%) tweets were classified as positive and 14,051 (21.88%) as negative toward a COVID-19 vaccine. We conducted Structural Topic Modeling and Network Analysis to reveal the distinct topical structure and connection patterns that characterize positive and negative discourse toward a COVID-19 vaccine.

Results: Our STM analysis revealed the most prominent topic emerged on Twitter of a COVID-19 vaccine was “other infectious diseases”, followed by “vaccine safety concerns”, and “conspiracy theory.” While the positive discourse demonstrated a broad range of topics such as “vaccine development”, “vaccine effectiveness”, and “safety test”, negative discourse was more narrowly focused on topics such as “conspiracy theory” and “safety concerns.” Beyond topical differences, positive discourse was more likely to interact with verified sources such as scientists/medical sources and the media/journalists, whereas negative discourse tended to interact with politicians and online influencers.

Conclusions: Positive and negative discourse was not only structured around distinct topics but also circulated within different networks. Public health communicators need to address specific topics of public concern in varying information hubs based on audience segmentation, potentially increasing COVID-19 vaccine uptake.

Full Citation: Hwang J, Su MH, Jiang X, Lian R, Tveleneva A, Shah D. Vaccine discourse during the onset of the COVID-19 pandemic: Topical structure and source patterns informing efforts to combat vaccine hesitancy. PLoS One. 2022 Jul 27;17(7):e0271394. doi: 10.1371/journal.pone.0271394. PMID: 35895626; PMCID: PMC9328525.

Access the Article: https://pubmed.ncbi.nlm.nih.gov/35895626/

Professor Dhavan Shah Receives ICA B. Aubrey Fisher Mentorship Award

Dhavan Shah on stage at the ICA Conference receiving the B. Audrey Fisher Mentorship Award

Dhavan Shah on stage at the ICA Conference receiving the B. Audrey Fisher Mentorship Award

At their 72nd Annual Conference in Paris France, the International Communication Association (ICA) awarded its B. Aubrey Fisher Mentorship Award to SJMC Maier-Bascom Professor Dhavan Shah.

Since 1988, the B. Aubrey Fisher Award has been given to honor outstanding scholars, teachers, and advisors who serve as role models in those capacities and who have had a major impact on the field of communication. Most importantly, recipients of this award have influenced the discipline through their former students, who themselves are important figures in the communication discipline.

“Shah is praised for his fairness, willingness to collaborate, unconditional support, ability to help students see the larger implications of their ideas, and unwavering intellectual generosity,” said Craig Scott, Professor in the Department of Communication Studies at the University of Texas-Austin, who conferred the award to Shah. “Dr. Dhavan Shah embodies the B. Aubrey Fisher Mentorship Award, and we are delighted to present him with it.”

“I owe a great debt to my mentors — Ivan Preston, Dan Wackman, Jack McLeod, and Dave Gustafson — who shaped my approach to research, teaching, and advising,” Shah said. “To be recognized for mentoring others and shaping the field through our joint scholarship and the work of my advisees means I paid that debt forward.”

Dhavan Shah headshot

SJMC Professor and MCRC Director Dhavan Shah

Shah has involved many students in his research and has served as major advisor for over 40 doctoral students, and a committee member on another 80 dissertations across ten departments. His advisees and mentees have gone on to research and teach at some of the world’s leading institutions and earn recognition for their work.

“Dhavan has supported my career teaching me about the research process, doing research with me, but most importantly teaching me how to become an independent researcher, one that can help develop new cohorts of researchers,” said Hernando Rojas, SJMC Professor and Director and one of Shah’s doctoral advisees. “Most importantly his mentoring never ends. Having been a professor for 15 years now myself, I regularly turn to his advice on how to navigate professional challenges, knowing I will always find a sympathetic ear and a smart answer. Simply put, I would not be in academia today if it were not for Dhavan.”

Shah’s research focuses on the influence of electronic and digital media on social judgments, civic and political engagement, and health support and behavior. He is the author of over 140 articles and 20 book chapters. He has co-edited five books and is the author of News Frames and National Security: Covering Big Brother with SJMC colleague Professor Doug McLeod and Battleground: Asymmetric Communication Ecologies and the Erosion of Civil Society in Wisconsin with current and former UW colleagues Lew Friedland, Mike Wagner, Chris Wells, Kathy Cramer, and Jon Pevehouse.

Dhavan Shah seated at a table speaking into a microphone

Dhavan Shah responds to questions during a panel “Media After The Midterms” at the Overture Center in Madison, Wis., on Nov. 7, 2018. (Photo by Jeff Miller / UW-Madison)

“Dhavan continues to be a sounding board of advice and perspective, nearly 10 years removed from my student days,” said Stephanie Edgerly, Associate Professor in the Medill School of Journalism, Media and Integrated Marketing Communications at Northwestern University and one of Shah’s doctoral advisees. “I am forever grateful for his mentorship and imprint on my career. He provided me with a map for navigating the world of academia, while encouraging me to choose my own path and go at my own pace. The fields of communication, journalism, and political science are better because of Dhavan’s mentorship.”

Shah serves as the Director of the Mass Communication Research Center (MCRC), Scientific Director in the Active Aging Research Center and Scientific Director in the Center for Health Enhancement System Studies (CHESS). He holds appointments in the Industrial and Systems Engineering, Marketing and Political Science departments.

Dhavan Shah standing at a podium in front of a projector screen

Dhavan guided me and my colleagues toward important lessons about how to live as a scholar,” said Kjerstin Thorson, Brandt Endowed Associate Professor of Political Communication in the College of Communication Arts & Sciences at Michigan State University and one of Shah’s doctoral advisees. “The lesson I value most is generosity. Dhavan taught us that a great scholar is generous with their time, ideas, opportunities, and mentorship.”

In 2016, Shah was elected as an ICA Fellow in recognition of his distinguished scholarly contributions to the broad field of communications. Shah’s SJMC colleague Professor Emeritus Jack McLeod also received the Fisher Award in 1991.

New publication “Algorithmic Agents in the Hybrid Media System: Social Bots, Selective Amplification, and Partisan News about COVID-19” from CAMER

In the new article “Algorithmic Agents in the Hybrid Media System: Social Bots, Selective Amplification, and Partisan News about COVID-19” in the journal Human Communication Research, the Computational Approaches and Message Effects Research group employed bot detection techniques, structural topic modeling, and time series analysis to characterize the temporal associations between the topics Twitter bots tend to amplify and subsequent news coverage across the partisan spectrum.

Abstract: Social bots, or algorithmic agents that amplify certain viewpoints and interact with selected actors on social media, may influence online discussion, news attention, or even public opinion through coordinated action. Previous research has documented the presence of bot activities and developed detection algorithms. Yet, how social bots influence attention dynamics of the hybrid media system remains understudied. Leveraging a large collection of both tweets (N = 1,657,551) and news stories (N = 50,356) about the early COVID-19 pandemic, we employed bot detection techniques, structural topic modeling, and time series analysis to characterize the temporal associations between the topics Twitter bots tend to amplify and subsequent news coverage across the partisan spectrum. We found that bots represented 8.98% of total accounts, selectively promoted certain topics and predicted coverage aligned with partisan narratives. Our macro-level longitudinal description highlights the role of bots as algorithmic communicators and invites future research to explain micro-level causal mechanisms.

Full citation: Zening Duan, Jianing Li, Josephine Lukito, Kai-Cheng Yang, Fan Chen, Dhavan V Shah, Sijia Yang, Algorithmic Agents in the Hybrid Media System: Social Bots, Selective Amplification, and Partisan News about COVID-19, Human Communication Research, 2022;, hqac012, https://doi.org/10.1093/hcr/hqac012

Access the article: https://academic.oup.com/hcr/advance-article-abstract/doi/10.1093/hcr/hqac012/6587151

New article from SMAD “Covering# MeToo across the News Spectrum: Political Accusation and Public Events as Drivers of Press Attention”

In the new article “Covering# MeToo across the News Spectrum: Political Accusation and Public Events as Drivers of Press Attention” in the International Journal of Press/Politics, the Social Media and Democracy Group examines how news media across the partisan spectrum covered the movement using different sexual violence language markers, latent topic, and word choices and which accusations and events drove media attention.

Abstract
Garnering coverage across the political spectrum is a major challenge for burgeoning social movements. The #MeToo movement stands out due to the volume of attention it generated. Yet, it is unclear how news media across the partisan spectrum covered the movement using different sexual violence language markers, latent topic, and word choices and which accusations and events drove media attention. To examine this, we used Media Cloud to extract 17,877 news articles from nine media outlets across the political spectrum, containing specific n-grams or co-occurrences of (1) “metoo,” (2) “sexual misconduct,” (3) “sexual harassment,” and (4) “sexual assault” from October 2017 through February 2018. The analyses first examined whether language and attention differed across the ideological news ecology and then turned to time-series modeling of these discourses to examine what drove press coverage and structural topic modeling (STM) and term frequency-inverse document frequency (TF-IDF) analysis to understand latent topics and language usage. Findings reveal that (1) left-leaning media dedicated more relative attention across all topics—#MeToo, sexual misconduct, sexual harassment, and sexual assault—relative to centrist and right-leaning media. Moreover, across the right, left, and centrist media, the language markers “misconduct,” “harassment,” and “assault” decreased over the study period, while the mentions of #MeToo movement increased during the same period; (2) stories relating to entertainment and those accusing politicians, especially those belonging to the party in power at the Federal level, seemed to be by far the strongest driver of news media attention; and (3) we further observed partisan differences in topics of news coverage and language usage.

Full Citation: Ghosh, S., Su, M.-H., Abhishek, A., Suk, J., Tong, C., Kamath, K., Hills, O., Correa, T., Garlough, C., Borah, P., & Shah, D. (2022). Covering #MeToo across the News Spectrum: Political Accusation and Public Events as Drivers of Press Attention. The International Journal of Press/Politics, 27(1), 158–185. https://doi.org/10.1177/1940161220968081

Access the Article: https://journals.sagepub.com/doi/abs/10.1177/1940161220968081

New Book Chapter from SMAD “Counter a reactive media system” in “Fixing American Politics”

New chapter “Counter a reactive media system” in the book Fixing American Politics from the Social Media and Democracy Group.

Full Citation: Counter a reactive media system
D Shah, Y Zhang, J Pevehouse, S Valenzuela
Fixing American Politics, 129-136
2021

Read more: https://www.taylorfrancis.com/chapters/edit/10.4324/9781003212515-20/counter-reactive-media-system-dhavan-shah-yini-zhang-jon-pevehouse-sebasti%C3%A1n-valenzuela

Alum Yini Zhang (PhD’20) wins Thomas E. Patterson Best Dissertation Award

At the American Political Science Association’s 2021 Annual Meeting, alum Yini Zhang (PhD’20) received the Thomas E. Patterson Best Dissertation Award from the Political Communication section for her dissertation “A Network Approach to Understanding Public Attention, Public Opinion and Communication Flows in the Digital Media System.”

The Thomas E. Patterson Best Dissertation Award recognizes the best dissertation completed in the field of political communication in the previous year. Zhang centered her dissertation around the core question of how digital media impact the U.S. political communication landscape.

“In my dissertation, I proposed a new theoretical and methodological framework to study the question of “who follows and who leads” in the US communication ecology,” Zhang said. “Specifically, the framework takes into account how actors of different backgrounds are now able to use social media to build online networks and project voices. It emphasizes the heterogeneous communication streams on social media, applies social network analysis to detect networks of actors, and explores their relationship with news media attention and coverage.”

Yini Zhang headshot

University at Buffalo Assistant Professor Yini Zhang (PhD’20)

Now an Assistant Professor in the Communication Department at the University at Buffalo, Zhang is also a UW-Madison Mass Communication Research Center (MCRC) Fellow. She credits her time in the School of Journalism and Mass Communication with giving her the tools she needed to craft her award-winning dissertation.

“I see this award as more of a collective than a personal achievement,” Zhang said. “At SJMC, there has been a strong support system and a nourishing academic environment. My advisors, colleagues, the staff members and all those who I interacted with helped me become who I am today. I feel very lucky that I get to do things that I enjoy doing and get recognized for my work.”

One such member of Zhang’s strong support system was her co-advisor SJMC Maier-Bascom Professor Dhavan Shah. Shah is also the director of the MCRC.

Dhavan Shah headshot

SJMC Professor and MCRC Director Dhavan Shah

“Yini’s dissertation and her broader program of research are incredibly innovative and impactful, integrating communication and sociology with network and computer science, She is a worthy recipient of this honor,” Shah said. “She enriched the MCRC not just with her intelligence and research acumen but by being a generous collaborator, student leader and peer mentor. We are lucky to still have her as a fellow.”

Zhang’s other co-advisor was former SJMC faculty member Chris Wells. Wells is now an Associate Professor of Emerging Media Studies in the College of Communication at Boston University and serves as a participating faculty member in the MCRC.

Chris Wells Headshot

Boston University Associate Professor Chris Wells

“This award is such a well-deserved recognition of Yini’s work,” Wells said. “While at UW-Madison, she crafted an innovative field of study for herself rooted in SJMC. But she also branched out and took courses and collaborated with professors from statistics, computer science and elsewhere. Her work is on the cutting edge of both communication theory and computational methods, and this award shows it.”

UW Team Publishes “Polarization Over Vaccination: Ideological Differences in Twitter Expression About COVID-19”

New article “Polarization Over Vaccination: Ideological Differences in Twitter Expression About COVID-19 Vaccine Favorability and Specific Hesitancy Concerns” in the journal Social Media + Society from the Center for Communication and Civic Renewal. Continue reading

SMAD group publishes “Resonant Moments in Media Events: Discursive Shifts, Agenda Control, and Twitter Dynamics”

In the new article “Resonant Moments in Media Events: Discursive Shifts, Agenda Control, and Twitter Dynamics in the First Clinton-Trump Debate” in the Journal of Quantitative Description: Digital Media, the Social Media and Democracy (SMAD) group found key differences in social media discourse about the two candidates during the first 2016 U.S. presidential debate. Continue reading