Welcome!

I am a computational social scientist who loves Text as Data methods

Soon, I will be looking for postdoc opportunities

War News on Russian Television

Solo-authored. Under review

How does an autocracy use its domestic mass media when going to war? The social science literature has yet to reach a consensus on this question. I argue that when the mass media are state-controlled and trusted by the populace, the regime may attempt to use news narratives for warfare agenda-setting and distraction from events at home. Using semi-supervised Naive Bayes-based classification of 2.7 million stories broadcast in Russia between 2009 and 2019 and applying the difference in differences technique, I show that state-enforced change in news management induced RBC television network to increase its war reporting by more than half. Additionally, I demonstrate that on national television networks, the rise in war coverage came at the expense of domestic news. This article is the first study to expose large-scale evidence of attempts by state media to amplify the importance of foreign conflicts for domestic audience.


Key words: diversionary war, mass media, autocratic resilience

How Russia Sets Its News Agenda at Home

Solo-authored. Work in progress

I offer the first large-scale study of how news manipulations in an autocracy vary across different media outlets. I conjecture that in Russia, state-controlled news published online, for consumption by a digitally literate audience, exhibits less pro-regime bias than programming created for those who rely on state television to learn about daily affairs. I evaluate the conjecture using three data sets: headlines displayed on the Yandex News Aggregator, transcripts of evening news on Channel 1, and reports from a private news agency Interfax, testing how daily reporting varied in topics across the media outlets. Using crowdsourcing, supervised machine learning, and dictionary techniques, I analyse 70000 news reports from August 2018 - March 2020. Results indicate that the state-controlled online platform, in contrast to national television channels, demonstrates less tendency to censor stories about political opposition and bad economic news, but promotes stronger measurable bias in the coverage of foreign affairs, specifically news that involves Ukraine and the US.


Key words: online news, autocracy, media bias

Bias in domestic criminal justice? Judging war crimes without accounting for war

with Ivor Sokolić (LSE), Denisa Kostovicova (LSE), and Sanja Vico (LSE). Work in progress

The saliency of identity issues in post-conflict societies has been shown to impact on fairness of transitional justice processes, including domestic war crimes trials. Scholars have observed ethnic bias by examining characteristics of participants and features of legal proceedings. However, they have overlooked how different conflict dynamics, conflict actors and patterns of violence drive these outcomes. This study posits that the features of conflict are consequential for the outcomes of war crimes trials. They not only provide insight into the fairness of the legal process, but also show how the state understands its responsibility for the commission of human rights violations. This study innovates by drawing on original datasets based on 165 domestic war crimes trials in Serbia from 2000 until 2019, and by combining statistical modelling and quantitative text analysis. This paper contributes to the emerging scholarship that draws on data from international and domestic war crimes trials to model various aspects of retributive justice, such as sentencing, and their relationship with peace-building. Using novel evidence, including the study of war crimes verdicts as text-as-data, the paper points to structural underpinnings of post-conflict injustice beyond the courtroom.


Key words: transitional justice, content analysis


Gendering Parliamentary Interactions: Interrogative Style and Legislative Oversight

with Denisa Kostovicova (LSE), Tolga Sinmazdemir (SOAS), and Vesna Popovski (LSE). Work in progress

Women have a distinctive voice in parliaments. Analysis of female legislators’ speaking behavior, including floor apportionment and policy issues they address, informs inferences about their effectiveness. In this vein, less adversarial tenor of female MPs’ speeches has been taken as an indicator of their less robust questioning of the members of the executive. To advance our understanding of the gendered patterns of legislative behaviour and their implications, we draw on the scholarship on gender and language in the field of social psychology and scrutinize the legislators’ speaking style. We analyze the text corpus comprised of parliamentary questions and answer sequences in the Croatian parliament from 2004 and 2020, and conduct quantitative content analysis that combines computer-assisted techniques and human coding of the discourse. A novel assessment of how female legislators’ interrogate ministers, rooted in Conversation Analysis―an approach to the study of interactive features of talk―systematically captures linguistic, deliberative and semantic features of discourse. The results show that female parliamentarians are no less robust questioners than their male counterparts. They put pressure on the answerer to account for government policy using different linguistic forms, rather than open aggression evident in semantic features of a speaker’s language. This research furthers the study of gender and politics by demonstrating that the masculine discourse in parliaments is used not only to ensure male dominance in parliaments, as scholars of feminist institutionalism have argued, but also to obscure the agency of female MPs and their effective oversight of the executive.


Key words: gender, legislature, content analysis

Gender Bias in News

an early stage project started at SICSS London

with Anastasiia Menshikova (LiU SE) and Katharina Lawall (LSE)

we are training word embeddings models (mostly BERT) on a set of large English language news corpora


Key words: gender, news

Entropy-based Newsmap

a very early stage project with Kohei Watanabe

A methods paper about an improved version of Newsmap


Key words: news, semi-supervised learning, text classifiers


Blog post about Telegram and its role in protests at Media@LSE

Protests in Russia raise questions about the role of new media in democratisation