Text-as-Data Initiative


Motivation of our group

We are researchers bulding up a community of machine learning, text-as-data and NLP enthusiasts in the social science domain and friends of all related fields. We aim to create a supportive enviroment to bring like minded researcher togehter for collaboration and knowledge exchange. 

🌱 Spring Speaker Series 2023 🌱

We will host again 7 amazing speakers from around the world. They will present their outstanding text-as-data work to us and we'll discuss their papers in depth.

Named-Entity Recognition with Application to Foreign Leader Mentions in Congressional Speeches

Ashrakat Elshehawy (University of Oxdord) @AshElshehawy

2023-03-08, 3:30 pm CEST (online)

Battle of Words: Dynamics of Echo Chambers among European Elites

Joris Frese (European University Institute) @fresejoris

2022-03-22, 5 pm CEST (online)


Tobias Widmann (Aarhus University) @TobiasWidmann

2023-04-19, 5 pm CEST (online)

Political Metaphors in U.S. Governor Speeches

Léo Picard (University of Basel) @leops95

2023-05-03, 5 pm CEST (online)


Gloria Gennaro (University College London) @gloriagennaro

2023-05-17, 5 pm CEST (online)

Visuals within Multimodal Studies

Erik Bucy (Texas Tech University) @erikpbucy

2023-05-31, 5 pm CEST (online)


Gabriella Lapesa (University of Stuttgart) @GabriellaLapesa

2023-06-14, 5 pm CEST (online)

Previous talks

Sequential Seeded LDA: A Topic Model for Theory-driven Classification of Sentences

Kohei Watanabe (Lazard Asset Management) @koheiw7

2022-09-20, 10-11am CEST (online)

Perceptions of Changing Status Hierarchies: An Analysis of Open-ended Survey Responses

Delia Zollinger (University of Zurich) @dpzollinger

2022-10-04, 5-6pm CEST (online)

Word Embeddings for the Analysis of Ideological Placement in Parliamentary Corpora [Video]

Ludovic Rheault (University of Toronto) @LudovicRheault

2022-10-18, 5-6pm CEST (online)

Named-Entity Recognition with Application to Foreign Leader Mentions in Congressional Speeches

Ashrakat Elshehawy (University of Oxford) @AshElshehawy

2022-11-01, 5-6pm CEST (online)

Fairness and Inclusion in NLP: Challenges and Opportunities [Video]

Anne Lauscher (Bocconi University) @anne_lauscher

2022-11-15, 5-6pm CEST (online)

Validating Topic Models: Does it matter how we do it? [Video]

Jana Bernhard (University of Vienna)

2022-11-29, 5-6pm CEST (online)

Who are they talking to? Automated measurement of group appeals in political texts [Video]

Hauke Licht (University of Cologne) @hauke_licht

2022-12-13, 5-6pm CEST (online)

When do political parties listen to interest groups? [Paper] [Video]

Maiken Roed (Lund University)

2022-04-12, 5-6pm (online) 

Multilingual Topic Models [Paper] [Slides] [Code]

Fabienne Lind (University of Vienna) @FabienneLind

2022-04-26, 5-6pm (online)

Three Gaps in Computational Text Analysis Methods for Social Sciences: A Research Agenda [Paper]

Christian Pipal (University of Amsterdam) @christianpipal

2022-05-10, 5-6pm (online)

How Simple Messages Affect Voters' Knowledge and Their Perceptions of Politicans - Evidence from Large-Scale Survey Experiment [Paper]

Roman Senninger (Aarhus University) @r_senninger

2022-05-24, 5-6pm (online)

Linking Datasets on Organizations Using Half A Billion Open Collaborated Records 

Connor Jerzak (University of Texas) 

2022-06-07, 5-6pm (online)

Measuring Agenda Setting in Interactive Political Communication

Erin Rossiter (University of Notre Dame) @erinrossiter

2022-06-21, 5-6pm (online)

Troublemakers in the streets? A framing of protest in the UK 1992-2017 [Video]

Johannes Gruber (European University Viadrina) @JohannesBGruber

2022-07-05, 5-6pm (online)

Twitter-Demographer: A Flow-based Tool to Enrich Twitter Data [Paper]

Federico Bianchi (Stanford University) @federicobianchy

2022-07-19, 5-6pm (online)

Join the community ⬇️

Send us a DM @nicolaiberk or @chklamm on Twitter to join the text-as-data slack channel.