I am an Assistant Professor in Political Communication at Royal Holloway University of London in the Department of Politics, International Relations and Philosophy, and a Faculty Associate in the Center for Social Media and Politics at New York University. I received my PhD in Political Science from the University of Washington . Before joining Royal Holloway, I was an assistant professor at VU Amsterdam, and a Moore Sloan research fellow in the Center for Data Science and Center for Social Media and Politics at the New York University; and a research fellow at the Amsterdam School of Communication Research.

I am a computational political scientist working on political communication, public policy, legislative politics, and computational methods. The substantive goal of my research is to build a better understanding of the policymaking process, broadly speaking, in the current digital society. My research in political communication and public policy looks at how social media has shaped collective action dynamics; how social movements, interest groups, political parties, as well as the public, use public communications to influence the political agenda; the role of (social) media in increasing/ameliorating polarization; and the regulation of political speech by social media companies. My research on legislative politics looks at the conditions under which individual legislators and legislative groups influence policy through less prominent (e.g. amendments) and more informal (e.g. bundling legislation) mechanisms. In addition, in all my research I develop and/or apply novel computation methods (text-as-data and images-as-data) that allow me to unlock important (classic and new) research questions that I would not be able to address otherwise.




Images as Data for Social Science Research: An Introduction to Convolutional Neural for Image Classification (2020)
(with Nora Webb Williams and John Wilkerson)
Cambridge University Press
Book | Open source code

Abstract: Images play a crucial role in shaping and reflecting political life. Digitization has vastly increased the presence of such images in daily life, creating valuable new research opportunities for social scientists. We show how recent innovations in computer vision methods can substantially lower the costs of using images as data. We introduce readers to the deep learning algorithms commonly used for object recognition, facial recognition, and visual sentiment analysis. We then provide guidance and specific instructions for scholars interested in using these methods in their own research.

Special Issue

Special Issue: Images as Data (2022)
Guest Editor, with Nora Webb Williams
Computational Communication Research
Special Issue

Abstract: Visual information (primarily still images and videos) is crucial for the study of many current communications, political, and social phenomena. Yet research leveraging large corpora of visuals to answer social science questions is still scarce, especially relative to the explosion of research using “big data” text-as-data methods. This special issue fosters innovative theoretical and methodological research in the area of images as data. The featured articles use computational methods to analyze, from a social science perspective, large quantities of images as well as videos.


The Geopolitics of Deplatforming: A Study of Suspensions of Politically-Interested Iranian Accounts on Twitter (Forthcoming)
Political Communication
Article | Replication material

Abstract: Social media companies increasingly play a role in regulating freedom of speech. Debates over ideological motivations behind suspension policies of major platforms are on the rise. This study contributes to this ongoing debate by looking at content moderation from a geopolitical perspective. The starting premise is that US-based social media companies may be inclined to moderate content on their platforms in compliance with US sanctions laws, especially those concerned with the Specially Designated Nationals and Blocked Persons List. Despite the release of transparency reports by social media companies, we know little about the scope of the problem and the impact of suspensions on political conversations. I tracked 600,000 users who follow Iranian elites on Twitter. After accounting for alternative explanations, the results show that Principlist (conservative) users and those supportive of the Iranian government are significantly more likely to be suspended. Further analyses uncover the types of discussions that are being suppressed as a result of these suspensions. Although the exact mechanism at hand cannot be decisively isolated, this paper contributes to building a better understanding of how governments can influence conversations of geopolitical relevance, and how social media suspensions shape political conversations online.

Lowering the Language Barrier: Investigating Deep Transfer Learning and Machine Translation for Multilingual Analyses of Political Texts (2023)
(with Moritz Laurer, Wouter van Atteveldt, and Kasper Welbers)
Computational Communication Research
Article | Replication material

Abstract: The social science toolkit for computational text analysis is still very much in the making. We know surprisingly little about how to produce valid insights from large amounts of multilingual texts for comparative social science research. In this paper, we test several recent innovations from deep transfer learning to help advance the computational toolkit for social science research in multilingual settings. We investigate the extent to which ‘prior language and task knowledge’ stored in the parameters of modern language models is useful for enabling multilingual research; we investigate the extent to which these algorithms can be fruitfully combined with machine translation; and we investigate whether these methods are not only accurate but also practical and valid in multilingual settings – three essential conditions for lowering the language barrier in practice. We use two datasets with texts in 12 languages from 27 countries for our investigation. Our analysis shows, that, based on these innovations, supervised machine learning can produce substantively meaningful outputs. Our BERT-NLI model trained on only 674 or 1674 texts in only one or two languages can validly predict political party families’ stances towards immigration in eight other languages and ten other countries.

To amend or not to amend: under what circumstances do Spanish legislators propose amendments to executive bills? (2023)
(with Anna Palau and Luz Muñoz)
West European Politics

Abstract: Based on a new comprehensive dataset containing information on 93,722 amendments, this article explores the circumstances under which Spanish legislators propose amendments to executive bills. Our results show that legislators respond to variations in both governmental factors and bargaining dynamics. In single-party minority governments, ad hoc legislature agreements translate into more amendments. However, legislators do not introduce significantly fewer amendments under absolute majority governments, when the chances of their proposals being accepted fall. After controlling for many confounders, the results show that amending activity reacts to attention allocation dynamics – mediatised bills receive more amendments – but not to variations in contextual factors – the number of amendments does not significantly increase when the economic situation deteriorates. Finally, bills associated with a greater number of committee appearances from interest groups, experts and public officials are more often the target of amendments, signalling that an informational logic is also at play.

Less Annotating, More Classifying: Addressing the Data Scarcity Issue of Supervised Machine Learning with Deep Transfer Learning and BERT-NLI (2023)
(with Moritz Laurer, Wouter van Atteveldt, and Kasper Welbers)
Political Analysis
Article | Replication material

Abstract: Supervised machine learning is an increasingly popular tool for analyzing large political text corpora. The main disadvantage of supervised machine learning is the need for thousands of manually annotated training data points. This issue is particularly important in the social sciences where most new research questions require new training data for a new task tailored to the specific research question. This paper analyses how deep transfer learning can help address this challenge by accumulating “prior knowledge” in language models. Models like BERT can learn statistical language patterns through pre-training (“language knowledge”), and reliance on task-specific data can be reduced by training on universal tasks like natural language inference (NLI; “task knowledge”). We demonstrate the benefits of transfer learning on a wide range of eight tasks. Across these eight tasks, our BERT-NLI model fine-tuned on 100 to 2,500 texts performs on average 10.7 to 18.3 percentage points better than classical models without transfer learning. Our study indicates that BERT-NLI fine-tuned on 500 texts achieves similar performance as classical models trained on around 5,000 texts. Moreover, we show that transfer learning works particularly well on imbalanced data. We conclude by discussing limitations of transfer learning and by outlining new opportunities for political science.

Most users do not follow political elites on Twitter; Those who do, show overwhelming preferences for ideological congruity (2022)
(with Magdalena Wojcieszak, Xudong Yu, Jonathan Nagler, and Joshua A. Tucker)
Science Advances
Article | Replication material

Abstract: We offer comprehensive evidence of preferences for ideological congruity when people engage with politicians, pundits, and news organizations on social media. Using four years of data (2016-2019) from a random sample of 1.5 million Twitter users, we examine three behaviors studied separately to date: (a) following of in-group vs. out-group elites, (b) sharing in-group vs. out-group information (retweeting), and (c) commenting on the shared information (quote tweeting). We find the majority of users (60%) do not follow any political elites. Those who do, follow in- group elite accounts at much higher rates than out-group accounts (90% vs. 10%), share information from in-group elites 13 times more frequently than from out-group elites, and often add negative comments to the shared out-group information. Conservatives are twice as likely as liberals to share in-group vs. out-group content. These patterns are robust, emerge across issues and political elites, and regardless of users’ ideological extremity.

Fueling Toxicity? Studying Deceitful Opinion Leaders and Behavioral Changes of Their Followers (2022)
(with Puck Guldemond and Mariken van der Velden)
Politics and Governance

Abstract: The spread of deceiving content on social media platforms is a growing concern amongst scholars, policymakers, and the public at large. We examine the extent to which influential users (i.e., “deceitful opinion leaders”) on Twitter engage in the spread of different types of deceiving content, thereby overcoming the compartmentalized state of the field. We introduce a theoretical concept and approach that puts these deceitful opinion leaders at the center, instead of the content they spread. Moreover, our study contributes to the understanding of the effects that these deceiving messages have on other Twitter users. For 5,574 users and 731,371 unique messages, we apply computational methods to study changes in messaging behavior after they started following a set of eight Dutch deceitful opinion leaders on Twitter during the Dutch 2021 election campaign. The results show that users apply more uncivil language, become more affectively polarized, and talk more about politics after following a deceitful opinion leader. Our results thereby underline that this small group of deceitful opinion leaders change the norms of conversation on these platforms. Hence, this accentuates the need for future research to study the literary concept of deceitful opinion leaders.

Null effects of news exposure: a test of the (un)desirable effects of a ‘news vacation’ and ‘news binging’ (2022)
(with Magdalena Wojcieszak, Bernhard Clemm von Hohenberg, Ericka Menchen-Trevino, Sjifra de Leeuw, Alexandre Gonçalves, and Miriam Boon)
Humanities and Social Science Communications

Abstract: Democratic theorists and the public emphasize the centrality of news media to a well-functioning society. Yet, there are reasons to believe that news exposure can have a range of largely overlooked detrimental effects. This preregistered project examines news exposure effects on desirable outcomes, i.e., political knowledge, participation, and support for compromise, and detrimental outcomes, i.e., attitude and affective polarization, negative system perceptions, and worsened individual well-being. We rely on two complementary over-time experiments that combine participants’ survey self-reports and their behavioral browsing data: one that incentivized participants to take a ’news vacation’ for a week (N = 803; 6M visits) in the US, the other to ‘news binge’ for 2 weeks (N = 939; 4M visits) in Poland. Across both experiments, we demonstrate that reducing or increasing news exposure has no impact on the positive or negative outcomes tested. These null effects emerge irrespective of participants’ prior levels of news consumption and whether prior news diet was like-minded, and regardless of compliance levels. We argue that these findings reflect the reality of limited news exposure in the real world, with news exposure comprising on average roughly 3% of citizens’ online information diet.

Using Social Media Data to Reveal Patterns of Policy Engagement in State Legislatures (2022)
(with Julya Payson, Jonathan Nagler, Richard Bonneau, and Joshua A. Tucker)
State Politics and Policy Quarterly
Article | Replication material

Abstract: State governments are tasked with making important policy decisions in the United States. How do state legislators use their public communications —particularly social media— to engage with policy debates? Due to previous data limitations, we lack systematic information about whether and how state legislators publicly discuss policy and how this behavior varies across contexts. Using Twitter data and state of the art topic modeling techniques, we introduce a method to study state legislator policy priorities and apply the method to fifteen U.S. states in 2018. We show that we are able to accurately capture the policy issues discussed by state legislators with substantially more accuracy than existing methods. We then present initial findings that validate the method and speak to debates in the literature. For example, state legislators in competitive districts are more likely to discuss policy than those in less competitive districts, and legislators from more professional legislatures discuss policy at similar rates to those in less professional legislatures. We conclude by discussing promising avenues for future state politics research using this new approach.

Exposure to extremely partisan news from the other political side shows scarce boomerang effects (2022)
(with Ericka Menchen-Trevino and Magdalena Wojcieszak)
Political Behavior
Article | Replication material

Abstract: A narrow information diet may be partly to blame for the growing political divides in the United States, suggesting exposure to dissimilar views as a remedy. These efforts, however, could be counterproductive, exacerbating attitude and affective polarization. Yet findings on whether such boomerang effect exists are mixed and the consequences of dissimilar exposure on other important outcomes remain unexplored. To contribute to this debate, we rely on a preregistered longitudinal experimental design combining participants' survey self-reports and their behavioral browsing data, in which one should observe boomerang effects. We incentivized liberals to read political articles on extreme conservative outlets (Breitbart, The American Spectator, and The Blaze) and conservatives to read extreme left-leaning sites (Mother Jones, Democracy Now, and The Nation). We maximize ecological validity by embedding the treatment in a larger project that tracks over time changes in online exposure and attitudes. We explored the effects on attitude and affective polarization, as well as on perceptions of the political system, support for democratic principles, and personal well-being. Overall we find little evidence of boomerang effects.

Partisan media, untrustworthy news sites, and political misperceptions (2021)
(with Brian E Weeks, Ericka Menchen-Trevino, Christopher Calabrese, and Magdalena Wojcieszak)
New Media & Society

Abstract: This study investigates the potential role both untrustworthy and partisan websites play in misinforming audiences by testing whether actual exposure to these sites is associated with political misperceptions. Using a sample of American adult social media users, we match data from individuals’ Internet browser histories with a survey measuring the accuracy of political beliefs. We find that visits to partisan websites are at times related to misperceptions consistent with the political bias of the site. However, we do not find strong evidence that untrustworthy websites consistently relate to false beliefs. There is also little evidence that visits to less partisan, centrist news sites are associated with more accurate political beliefs about these issues, suggesting that exposure to politically neutral news is not necessarily the antidote to misinformation. Results suggest that focusing on partisan news sites—rather than untrustworthy sites—may be fruitful to understanding how media contribute to political misperceptions.

Can AI Enhance People’s Support for Online Moderation and Their Openness to Dissimilar Political Views? (2021)
(with Magdalena Wojcieszak, Arti Thakur, João Fernando Ferreira Gonçalves, Ericka Menchen-Trevino, and Miriam Boon)
Journal of Computer-Mediated Communication

Abstract: Although artificial intelligence is blamed for many societal challenges, it also has underexplored potential in political contexts online. We rely on six preregistered experiments in three countries (N = 6,728) to test the expectation that AI and AI-assisted humans would be perceived more favorably than humans (a) across various content moderation, generation, and recommendation scenarios and (b) when exposing individuals to counter-attitudinal political information. Contrary to the preregistered hypotheses, participants see human agents as more just than AI across the scenarios tested, with the exception of news recommendations. At the same time, participants are not more open to counter-attitudinal information attributed to AI rather than a human or an AI-assisted human. These findings, which—with minor variations—emerged across countries, scenarios, and issues, suggest that human intervention is preferred online and that people reject dissimilar information regardless of its source. We discuss the theoretical and practical implications of these findings.

The (Null) Effects of Happiness on Affective Polarization, Conspiracy Endorsement, and Deep Fake Recognition: Evidence from Five Survey Experiments in Three Countries (2021)
(with Xudong Yu, Magdalena Wojcieszak, Seungsu Lee, Rachid Azrout and Tomasz Gackowski )
Political Behavior
Article | Replication material

Abstract: Affective polarization is a key concern in America and other democracies. Although past evidence suggests some ways to minimize it, there are no easily applicable interventions that have been found to work in the increasingly polarized climate. This project examines whether irrelevant factors, or incidental happiness more specifically, have the power to reduce affective polarization (i.e., misattribution of affect or “carryover effect”). On the flip side, happiness can minimize systematic processing, thus enhancing beliefs in conspiracy theories and impeding individual ability to recognize deep fakes. Three preregistered survey experiments in the US, Poland, and the Netherlands (total N = 3611) induced happiness in three distinct ways. Happiness had no effects on affective polarization toward political outgroups and hostility toward various divisive social groups, and also on endorsement of conspiracy theories and beliefs that a deep fake was real. Two additional studies in the US and Poland (total N = 2220), also induced anger and anxiety, confirming that all these incidental emotions had null effects. These findings, which emerged uniformly in three different countries, among different partisan and ideological groups, and for those for whom the inductions were differently effective, underscore the stability of outgroup attitudes in contemporary America and other countries.

What Was the Problem in Parkland? Using Social Media to Measure the Effectiveness of Issue Frames (2020)
(with Kevin Aslett, Nora Webb Williams, Wesley Zuidema and John Wilkerson)
Policy Studies Journal

Abstract: Agenda setting and issue framing research investigates how frames impact public attention, policy decisions, and political outcomes. Social media sites, such as Twitter, provide opportunities to study framing dynamics in an important area of political discourse. We present a method for identifying frames in tweets and measuring their effectiveness. We use topic modeling combined with manual validation to identify recurrent problem frames and topics in thousands of tweets by gun rights and gun control groups following the Marjory Stoneman Douglas High School in Parkland, Florida, shooting. We find that each side used Twitter to advance policy narratives about the problem in Parkland. Gun rights groups’ narratives implied that more gun restrictions were not the solution. Their most effective frame focused on officials’ failures to enforce existing laws. In contrast, gun control groups portrayed easy access to guns as the problem and emphasized the importance of mobilizing politically to force change.

More Effective Than We Thought: Accounting for Legislative Hitchhikers Reveals a More Inclusive and Productive Lawmaking Process (2020)
(with Matthew Denny and John Wilkerson)
American Journal of Political Science
Article | Replication Material

Abstract: For more than half a century, scholars have been studying legislative effectiveness using a single metric - whether the bills a member sponsors progress through the legislative process. We investigate a less orthodox form of effectiveness - bill proposals that become law as provisions of other bills. Counting these “hitchhiker” bills as additional cases of bill sponsorship success reveals a more productive, less hierarchical and less partisan lawmaking process. We argue that agenda and procedural constraints are central to understanding why lawmakers pursue hitchhiker strategies. We also investigate the legislative vehicles that attract hitchhikers and find, among other things, that more Senate bills are enacted as hitchhikers on House laws than become law on their own.

Leaders or Followers? Measuring Political Responsiveness in the U.S. Congress Using Social Media Data (2019)
(with Pablo Barbera, Jonathan Nagler, Patrick Egan, Richard Bonneau, John T. Jost, and Joshua A. Tucker)
American Political Science Review
Article | Supporting Information | Replication Material

Abstract: Are legislators responsive to the issue demands of the public? If so, are they more likely to be responsive to some citizens than to others? Research on agenda setting and responsiveness finds a correspondence between the issue priorities of the public and politicians, but it does not provide conclusive evidence on who influences whom. We argue that determining the direction of the effect is of great relevance to adjudicate between particular models of representation and to judge political responsiveness generally. We fill this current gap by studying all tweets sent by Members of the United States Congress, sets of Democratic and Republican supporters and attentive citizens, and a random sample of Twitter users located in the United States from January 2013 to December 2014. Using a Latent Dirichlet Allocation model, we extract topics that represent the diversity of issues that legislators discuss. Then, we exploit variation in the distribution of topics over time to test whether Members of Congress lead or follow their constituents in their selection of issues to discuss. We find that legislators are more likely to respond to than to influence discussion of public issues, results that hold even after controlling for media effects. We also find that legislators are more likely to be responsive to their own supporters and attentive voters than to the general public.

Images that Matter: Online Protests and the Mobilizing Role of Pictures (2019)
(with Nora Webb Williams)
Political Research Quarterly
Article | Replication Material

Abstract: Do images affect online political mobilization? If so, how? These questions are of fundamental importance to scholars of social movements, contentious politics, and political behavior generally. However, little prior work has systematically addressed the role of images in mobilizing online participation in social movements. We first confirm that images have a positive mobilizing effect in the context of online protest activity. We then argue that images are mobilizing because they trigger stronger emotional reactions than text. Building on existing political psychology models we theorize that images evoking enthusiasm, anger, and fear should be particularly mobilizing, while sadness should be demobilizing. We test the argument through a study of Twitter activity related to a Black Lives Matter protest. We find that both images in general and some of the proposed emotional attributes (enthusiasm and fear) contribute to online participation. The results hold when controlling for alternative theoretical mechanisms for why images should be mobilizing, as well as for the presence of frequent image features. Our paper thus provides evidence supporting the broad argument that images increase the likelihood of a protest to spread online while also teasing out the mechanisms at play in a new media environment.

Community Foundations as Advocates: Social Change Discourse in the Philanthropic Sector (2018)
(with David Suarez and Kelly Husted)
Interest Groups and Advocacy

Abstract: Foundations are much more than disinterested philanthropic institutions that award grants to service-providing nonprofits. Foundations are political actors that seek to produce social change, not only by donating resources to nonprofits that promote causes but also by supporting policy reform in a more direct manner. We investigate engagement in advocacy among community foundations in the United States, which we define as the effort to influence public policy by proposing or endorsing ideas and by mobilizing stakeholders for social change. Drawing primarily on organizational sociology, we posit that the environmental context in which community foundations are situated and particular structural characteristics or operational features of community foundations (institutional logics, identity and embeddedness, and managerialism) will be associated with advocacy. We utilize machine learning techniques to establish an outcome measure of advocacy discourse on community foundation websites and ordinary least squares (OLS) regression to model that outcome with a cross-sectional dataset compiled from multiple sources. We find considerable support for our conceptual frame, and we conclude by offering an agenda for future research on foundations as interest groups.

A Delicate Balance: Party Branding during the 2013 Government Shutdown (2017)
(with John Wilkerson)
American Politics Research

Abstract: Strong party brands help congressional parties elect candidates, maintain or gain majority control, and advance their policy agendas. Because successful branding efforts depend on consistent messaging, party leaders try to choose issues that most members are willing to promote. But what do leaders do when a party majority pressures them to take up issues that harm the brand for others? We investigate the 2013 government shutdown as a branding event. House Republican leaders instigated the shutdown after learning that a majority of Republicans would not vote for a clean funding bill. However, instead of highlighting the issues that led to the shutdown, they publicized the party's efforts to resolve it. Party leaders sought to exploit the fact that party brands have both position and valence components to simultaneously address the demands of the party base and the electoral concerns of members representing competitive districts.

Large-Scale Computerized Text Analysis in Political Science: Opportunities and Challenges (2017)
(with John Wilkerson)
Annual Review of Political Science
Article | Replication Material

Abstract: Text has always been an important data source in political science. What has changed in recent years is the feasibility of investigating large amounts of text quantitatively. The internet provides political scientists with more data than their mentors could have imagined, and the research community is providing accessible text analysis software packages, along with training and support. As a result, text as data research is beginning to mainstream in political science. Scholars are tapping new data sources, they are employing more diverse methods, and they are becoming critical consumers of findings based on those methods. In this article, we first introduce readers to the subject by describing the four stages of a typical text as data project. We then review recent political science applications, and explore one important methodological challenge - topic model instability - in greater detail.

Media Coverage of a 'Conective Action': The Interaction between the 15-M Movement and the Mass Media (2016)
(with Ferran Davesa and Mariluz Congosto)
Revista Española de Investigaciones Sociológicas
English Version | Spanish Version

Abstract: In May 2011, thousands of outraged citizens (i.e. the indignados) occupied the squares of the main Spanish cities to express their discontent and claim for reforms. This article investigates via Twitter messages the ability of the 15-M movement to place their claims into the media agenda and to keep ownership of their own discourse. The analysis emphasizes the fact that the social movement originated in the Internet with a highly decentralized structure and with scarce organizational resources. Results show that protesters discourse included a great number of claims, although the activists focused their discussions on three specific issues: electoral and party systems, democracy and governance, and finally, civil liberties. Moreover, the study reveals that the indignados managed to keep control over their repertoires and were able to determine the media agenda despite the later mainly focused on the most dramatic events.

Selected Working Papers

The Mechanisms of Protest Recruitment through Social Media Networks.
(with Joshua Tucker, Leon Yin, Jonathan Nagler, and Jennifer M. Larson)

The protest mobilization literature has long suggested that social ties influence a person’s decision to protest. However, previous research has not clearly established why this is the case. We consider four possible mechanisms: networks mobilize because they a) provide logistical information, b) motivate people about the cause, c) solve coordination problems, and d) apply social pressure to attend. We test these with novel protest attendance data. We identify Twitter users who participated in the 2018 U.S. Women’s March, categorize the tweets they could have seen, and compare these and their network positions to those of individuals who were similar but did not participate. We find strong evidence that networks indeed mattered for mobilization. Furthermore, we show that even after controlling for a variety of confounders, exposure to messages providing information, helping to coordinate, and applying pressure predicted protest attendance while exposure to messages seeking to motivate did not.

Bottom-Up or Top-Down Influence? Determinants of Issue-Attention in State Politics
(with Oscar Stuhler, Julia Payson, Jonathan Nagler, Richard Bonneau, and Joshua A. Tucker)
Under Review

Who shapes the issue-attention cycle of state legislators? Although state governments make critical policy decisions, data and methodological constraints have limited researchers' ability to study state-level agenda setting. For this paper, we collect nearly 105 million Twitter messages sent by state and national actors in 2018 and 2021. We then employ supervised machine learning and time series techniques to study how the issue-attention of state lawmakers evolves vis-à-vis a series of local- and national-level actors. Our findings suggest that state legislators operate at the confluence of national and local influences. In line with arguments highlighting the nationalization of state politics, we find that state legislators are consistently responsive to policy debates among members of Congress. However, despite growing nationalization concerns, we also find strong evidence of issue responsiveness by legislators to the public in their states. In both years, shifts in attention by partisan members of the public within states had the strongest influence on the public agenda of state legislators. Local and state media had a moderate influence on state legislators while the President and the national media had little direct effect.

When Conservatives See Red but Liberals Feel Blue: Why Labeler-Characteristic Bias Matters for Data Annotation
(with Nora Webb Williams, Kevin Aslett and John Wilkerson)
Revise & Resubmit

Human annotation of data, including text and image materials, is a bedrock of political science research. Yet we often overlook how the identities of our annotators may systematically affect their labels. We call the sensitivity of labels to annotator identity "labeler-characteristic bias" (LCB). We demonstrate the persistence and risks of LCB for downstream analyses in two examples, first with image data from the United States and second with text data from the Netherlands. In both examples we observe significant differences in annotations based on annotator gender and political identity. After laying out a general typology of annotator biases and their relationship to inter-rater reliability, we provide suggestions and solutions for how to handle LCB. The first step to addressing LCB is to recruit a diverse labeler corps and test for LCB. Where LCB is found, solutions are modeling subgroup effects or generating composite labels based on target population demographics.


Automated Image and Video Analysis with Python (GESIS: 2022, 2023)

Courses at Royal Holloway University of London

Courses at the Vrije Universiteit Amsterdam

Courses taught at the University of Washington