RESEARCH
Job Market Paper
"The Impact of Political Campaigns on Demand for Partisan News"
Abstract
In this paper, I study how electoral campaigns shape the demand for partisan news and, in turn, political polarization. I construct a daily, story-level measure of slant in Spanish TV news using machine learning and Large Language Models (LLMs) and link it to high-frequency audience-meter records. I then integrate it into a structural model of news demand and supply. Leveraging exogenous news supply shocks as cost shifters to identify demand, I show that polarization in news consumption intensifies only when the electoral campaign begins, with out-party aversion dominating. Regions with more polarized media consumption also exhibit a sharper and more persistent rise in ideological polarization. Finally, I evaluate the effects of media regulation policies. Enforcing the proportional-airtime rule during campaigns has unexpected effects: it widens cross-outlet dispersion in supplied slant thus amplifying audience responses to partisan content, yielding a more polarized media landscape.
Other Works
"Breaking the Echo Chamber: Nonviolent Protest and Police Violence on Twitter"
--(submitted)--with Hannes Mueller, Daniel Montolio, and Francesco Slataper.
Abstract
This article exploits data from a political conflict between language groups to show how political events can rapidly redefine how these groups interact on social media. Leveraging on a unique dataset of 26 million retweets by 120 000 Catalan- and Spanish-speaking Twitter users, we estimate individual exposure to tweets with a network-based model. We then compare two shocks in the same region and year: the Barcelona terror attack and the Catalan independence referendum. The referendum — and the circulated images of police violence — triggered a sharp, symmetric jump in cross-language retweeting. The terror attack, by contrast, did not lead to a similar realignment.
"Online and Offline protest participation: An Empirical Analysis for the 2020 Black Lives Matter Movement"
Abstract
The recent wave of world-wide protests that took place after George Floyd’s killing has sparked attention in the Black Lives Matter movement, specially in terms of online activism. How does offline protesting behavior interact with the underlying online social networks? In this work, I build a classification algorithm to identify individuals who physically participated in the BLM demonstrations across the US. Thanks to this unique dataset, I explore at an individual level their full Twitter activity to better understand the role of influential users, coordination patterns and speech evolution. Through this analysis, I aim to examine assumptions regarding slacktivism, which involves engaging in online activism with minimal effort, in comparison to more traditional forms of protesting. By exploring how social media contributes to the development of traditional activism, we can gain a deeper understanding of the role of social media in protesting behavior.
"Media Entry and Political Slant"
with Manuel Lleonart.
Abstract
his paper investigates how competition shapes ideological slant in television news. While theoretical models suggest that increased media competition can either intensify or mitigate bias—depending on whether audiences seek confirmation or accuracy—empirical evidence remains limited. We address this gap by analyzing the entry of a new Spanish TV news outlet and measuring how it alters the political slant of existing providers. Our approach combines a formal model of political media markets with a novel empirical strategy that leverages large-language-model and text-analysis techniques. We disentangle media bias into topic selection, ideological tone, and airtime allocation—capturing the three primary channels through which slant manifests. Our findings offer the first direct evidence of how heightened rivalry influences not just audience composition, but the strategic editorial decisions that shape political coverage.
"The End of the Iberian Exception: Populists and
the Economy"
with Agustina Martínez and Henry Redondo.
PROJECTS
Spanish Media Monitor
Spanish Media Monitor is the first effort to monitor TV media using large language models (LLMs). I built this project to provide real-time analysis of Spanish television news content, leveraging LLMs for story identification, classification, and visualization. You can visit the webpage here.
TEACHING
Instructor:
Teaching Assistant:
Course evaluations available upon request.
