Working Papers

Limits of Media Effects

Under review

Dissertation project exploiting a natural shift in the media framing of migration to estimate the effect of framing on voters’ issue attitudes.

Working Paper | Github | Slides

Measuring Rhetorical Similarity with Supervised Machine Learning

Working paper on the measurement of rhetorical similarity in political speech.

Working Paper | Github | Slides

Work in progress

Do Issue Attitudes Influence Voting Behaviour? An Experimental Assessment of the Economic Model of Voting

Dissertation project using framing to instrument voters issue attitudes and assess their impact on voting intentions

Github | Slides

The Impact of Emphasis Framing on Party Competition

Dissertation project combining transformer models and document embeddings to assess the impact of news framing of migration on political parties’ electoral support


Leading by Example? How Elite Behaviour affects Individual Vaccination Decisions

Ongoing project assessing the impact of party cues on vaccination behaviour

Github | Slides

Measuring Media Bias with Cross-Domain Deep Learning

Work together with Tom Arend, looking into cross-domain learning to estimate newspapers’ leanings towards different political parties.

Report | Blogpost | GitHub

Right-Wing Terrorist Attacks, the Media’s Reactions, and Radical Right Party Support

Ongoing project (with Werner Krause) studying media reactions to radical-right terrorism in Germany



Die Nationalratswahl 2017 unter besonderer Berücksichtigung der Silberstein-Affäre

Chapter in: Weßels, B., & Schoen, H. (2021). Wahlen und Wähler. Analysen aus Anlass der Bundestagswahl 2017. Springer VS Wiesbaden. Co-authored with Julia Partheymüller and Jakob-Moritz Eberl



Supervised Machine Learning with Imbalanced Data

Self-designed workshop introducing different techniques to deal withimbalanced data in supervised classification problems.

Github | Slides

May 2022, CompText Conference, Dublin, Ireland

Intro to R and Statistics

Taught two independent labs as addition to Prof. Mark Kayser’s Stats I lecture for Master students, focusing on the R programming language

September - December 2020 and 2021, Hertie School, Berlin, Germany

Academic Blogposts

Classifying Newspaper Bias with Cross-Domain Learning

Can we use party communication to train transformer models detecting newspaper bias? The short answer: no.

Blogpost | Report | GitHub

May 2021

Silberstein und Kern - hat der Skandal der SPÖ geschadet?

Blog-post (Coauthored with Markus Wagner) on a scandal in the Austrian Lower House Election 2017; also covered by Austrian daily newspaper “Der Standard”.

Blogpost | News article

March 2018


Word embeddings of German Newspaper articles

Word embedding model of over 2.2M German newspaper articles 2013-2021 (Bild, Frankfurter Allgemeine, Spiegel Online, Süddeutsche Zeitung, TAZ, Welt).

Dataset | Github

August 2021, HU Berlin, Germany

EUSpeech v2.0. A dataset of 11,466 speeches by European Leaders

In charge of data collection using web-scrapers

Dataset | Report

September 2018 – July 2020, University of Amsterdam, Netherlands

AUTNES Online Panel Study 2017

Responsible for data cleaning, manual coding and preparation of questionnaires.


April 2017 - March 2018, University of Vienna, Austria

AUTNES Comparative Study of Electoral Systems Post-Election Survey 2017

Responsible for data cleaning, manual coding and preparation of questionnaires.


April 2017 - March 2018, University of Vienna, Austria


Apart - Affective Polarization in Text

Collaborative project (with João Areal Neto and Phillip Mendoza) measuring hostility in parliaments using targeted sentiment analysis


September 2019 – February 2020