Andreu Casas
YOU?
Author Swipe
View article: Commentary: How do we get platforms to share data with independent researchers? Regulation alone will not cut it: a commentary on Livingston et al. (2023), Bourgaize et al. (2025)
Commentary: How do we get platforms to share data with independent researchers? Regulation alone will not cut it: a commentary on Livingston et al. (2023), Bourgaize et al. (2025) Open
We respond to articles in the Child and Adolescent Mental Health journal about whether, and under what, conditions researchers should collaborate with digital companies. In particular, we discuss the challenges academics face to access and…
View article: Academic Access to Social Media Data for the Study of Political Online Safety
Academic Access to Social Media Data for the Study of Political Online Safety Open
In this report we provide an overview of the kinds of data academics need in order to conduct independent research into political online safety matters on social media platforms, and the challenges they currently face. Additionally, we put…
View article: The Landscape of Lawmaking
The Landscape of Lawmaking Open
Lawmaking is not about enacting bills. It is about enacting policies. We portray bills as necessary vehicles for the advancement of policy ideas. To survive, a policy must be incorporated into a successful bill. But bills and policies are …
View article: On Measurement Validity and Language Models: Increasing Validity and Decreasing Bias with Instructions
On Measurement Validity and Language Models: Increasing Validity and Decreasing Bias with Instructions Open
Language models like BERT or GPT are becoming increasingly popular measurement tools, but are the measurements they produce valid? Literature suggests that there is still a relevant gap between the ambitions of computational text analysis …
View article: The Geopolitics of Deplatforming: A Study of Suspensions of Politically-Interested Iranian Accounts on Twitter
The Geopolitics of Deplatforming: A Study of Suspensions of Politically-Interested Iranian Accounts on Twitter Open
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 a…
View article: Building Efficient Universal Classifiers with Natural Language Inference
Building Efficient Universal Classifiers with Natural Language Inference Open
Generative Large Language Models (LLMs) have become the mainstream choice for fewshot and zeroshot learning thanks to the universality of text generation. Many users, however, do not need the broad capabilities of generative LLMs when they…
View article: Less Annotating, More Classifying: Addressing the Data Scarcity Issue of Supervised Machine Learning with Deep Transfer Learning and BERT-NLI
Less Annotating, More Classifying: Addressing the Data Scarcity Issue of Supervised Machine Learning with Deep Transfer Learning and BERT-NLI Open
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 i…
View article: Replication Data for: Less Annotating, More Classifying: Addressing the Data Scarcity Issue of Supervised Machine Learning with Deep Transfer Learning and BERT-NLI
Replication Data for: Less Annotating, More Classifying: Addressing the Data Scarcity Issue of Supervised Machine Learning with Deep Transfer Learning and BERT-NLI Open
Supervised machine learning is an increasingly popular tool for analysing large political text corpora. The main disadvantage of supervised machine learning is the need for thousands of manually annotated training data points. This issue i…
View article: Lowering the Language Barrier: Investigating Deep Transfer Learning and Machine Translation for Multilingual Analyses of Political Texts
Lowering the Language Barrier: Investigating Deep Transfer Learning and Machine Translation for Multilingual Analyses of Political Texts Open
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. …
View article: Correction: Null effects of news exposure: a test of the (un)desirable effects of a ‘news vacation’ and ‘news binging’
Correction: Null effects of news exposure: a test of the (un)desirable effects of a ‘news vacation’ and ‘news binging’ Open
The following errors have been corrected in the published article. The introduction originally stated: From over 8847 million visits, we analyze 10 million visits from the month before the experiments and use these data in conjunction with…
View article: Using Social Media Data to Reveal Patterns of Policy Engagement in State Legislatures
Using Social Media Data to Reveal Patterns of Policy Engagement in State Legislatures Open
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, w…
View article: Most users do not follow political elites on Twitter; those who do show overwhelming preferences for ideological congruity
Most users do not follow political elites on Twitter; those who do show overwhelming preferences for ideological congruity Open
We offer comprehensive evidence of preferences for ideological congruity when people engage with politicians, pundits, and news organizations on social media. Using 4 years of data (2016–2019) from a random sample of 1.5 million Twitter us…
View article: Replication Data for: "Most users do not engage with political elites on Twitter; Those who do, show overwhelming preferences for ideological congruity"
Replication Data for: "Most users do not engage with political elites on Twitter; Those who do, show overwhelming preferences for ideological congruity" Open
This repository contains the replication material of the article "Most users do not engage with political elites on Twitter; Those who do, show overwhelming preferences for ideological congruity", to be published at Sience Advances, by Mag…
View article: Introduction to the Special Issue on Images as Data
Introduction to the Special Issue on Images as Data Open
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 s…
View article: Null effects of news exposure: A causal test of the (un)desirable effects of a ‘news vacation’ and ‘news binging’
Null effects of news exposure: A causal test of the (un)desirable effects of a ‘news vacation’ and ‘news binging’ Open
This preregistered project examines the general belief that news has a beneficial impact on society. We test news exposure effects on desirable outcomes, i.e., political knowledge and participation, and detrimental outcomes, i.e., attitude…
View article: Partisan media, untrustworthy news sites, and political misperceptions
Partisan media, untrustworthy news sites, and political misperceptions Open
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 ad…
View article: Affective polarization on social media: In-party love among American politicians, greater engagement with out-party hate among ordinary users
Affective polarization on social media: In-party love among American politicians, greater engagement with out-party hate among ordinary users Open
Americans view their in-party members positively and out-party members negatively. It remains unclear, however, whether in-party love (i.e., positive partisanship) or out-party hate (i.e., negative partisanship) more strongly influences po…
View article: Can AI Enhance People’s Support for Online Moderation and Their Openness to Dissimilar Political Views?
Can AI Enhance People’s Support for Online Moderation and Their Openness to Dissimilar Political Views? Open
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…
View article: Replication Data for: Partisan Media, Untrustworthy News Sites, and Political Misperceptions
Replication Data for: Partisan Media, Untrustworthy News Sites, and Political Misperceptions Open
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 ad…
View article: The (Null) Effects of Happiness on Affective Polarization, Conspiracy Endorsement, and Deep Fake Recognition: Evidence from Five Survey Experiments in Three Countries
The (Null) Effects of Happiness on Affective Polarization, Conspiracy Endorsement, and Deep Fake Recognition: Evidence from Five Survey Experiments in Three Countries Open
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 cli…
View article: The (null) effects of happiness on affective polarization, conspiracy endorsement, and deep fake recognition: Evidence from five survey experiments in three countries
The (null) effects of happiness on affective polarization, conspiracy endorsement, and deep fake recognition: Evidence from five survey experiments in three countries Open
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 cli…
View article: Echo chambers revisited: The (overwhelming) sharing of in-group politicians, pundits and media on Twitter
Echo chambers revisited: The (overwhelming) sharing of in-group politicians, pundits and media on Twitter Open
Analyzing four years of data from a random sample of about 1.5 million Twitter users (and about 180,000 politically engaged users), we revisit the debate regarding the extent to which social media users live in political ``echo chambers'' …
View article: Echo chambers revisited: The (overwhelming) sharing of in-group politicians, pundits and media on Twitter
Echo chambers revisited: The (overwhelming) sharing of in-group politicians, pundits and media on Twitter Open
Analyzing four years of data from a random sample of about 1.5 million Twitter users (and about 180,000 politically engaged users), we revisit the debate regarding the extent to which social media users live in political ``echo chambers'' …
View article: What Was the Problem in Parkland? Using Social Media to Measure the Effectiveness of Issue Frames
What Was the Problem in Parkland? Using Social Media to Measure the Effectiveness of Issue Frames Open
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 …
View article: Who Leads? Who Follows? Measuring Issue Attention and Agenda Setting by Legislators and the Mass Public Using Social Media Data
Who Leads? Who Follows? Measuring Issue Attention and Agenda Setting by Legislators and the Mass Public Using Social Media Data Open
Are legislators responsive to the priorities of the public? Research demonstrates a strong correspondence between the issues about which the public cares and the issues addressed by politicians, but conclusive evidence about who leads whom…