Understanding the origins of militarized conflict is a complex, yet important undertaking. Existing research seeks to build this understanding by considering bi-lateral relationships between entity pairs (dyadic causes) and multi-lateral relationships among multiple entities (systemic causes). The aim of this work is to compare these two causes in terms of how they correlate with conflict between two entities.

Niklas Stoehr 11
Lucas Torroba Hennigen 13
Samin Ahbab
Robert West 15
Ryan Cotterell 11, 12

EMNLP 2021

↗ arXiv paper
↗ EMNLP paper
↗ Poster
↗ Video
↗ Slides
↗ Interactive dashboard
↗ Code

In common law, the outcome of a new case is determined mostly by precedent cases, rather than by existing statutes. However, how exactly does the precedent influence the outcome of a new case? Answering this question is crucial for guaranteeing fair and consistent judicial decision-making. We are the first to approach this question computationally by comparing two longstanding jurisprudential views; Halsbury's, who believes that the arguments of the precedent are the main determinant of the outcome, and Goodhart's, who believes that what matters most is the precedent's facts. We base our study on the corpus of legal cases from the European Court of Human Rights (ECtHR).

Josef Valvoda 12
Tiago Pimentel 12
Niklas Stoehr 11
Ryan Cotterell 11,12
Simone Teufel 12

NAACL-HLT 2021

Event information detection consists of multiple subsequent steps that could drastically affect the quality of the resulted event database. Thus, we believe one must consider a complete scenario that consists of document and sentence classification as relevant or not, event coreference resolution, event information extraction, and event classification in relation to an event taxonomy, and test the results on a list of events created manually to determine performance of the state-of-the-art on this task.

Niklas Stoehr 11
Tiancheng Hu 11
Francesco Re 11
Dániel Végh 11
Dennis Atzenhofer 11
Salvatore Giorgi
Ali Hürriyetoğlu
Hristo Tanev 14

ACL 2021 CASE

↗ Discovering Black Lives Matter Events
↗ Pretraining for Sentence-Level Protest Event Classification
↗ Document- and Sentence-Level Classification for Protest Event Detection

The proximity between newspapers and political parties is strongly subjective and difficult to measure. Yet, political tendencies of newspapers can have a significant impact on voters’ opinion‐forming and ought to be known by the public in a transparent and timely manner. This article introduces the Sentiment Political Compass (SPC), a data‐driven framework for analyzing political bias of newspapers toward political parties.

Fabian Falck 4
Julian Marstaller 7
Niklas Stoehr 5
Sören Maucher 7
Jeana Ren 7
Andreas Thalhammer 7
Achim Rettinger 7
Rudi Studer 7

Policy & Internet, Wiley Online Library, 2019

↗ Pre-Print Paper
↗ Journal Paper
↗ Code
↗ Data
↗ Interactive Website
↗ Speakerpolitics

Public intellectuals claim that populists thrive on fear of minority groups, but we suggest that what they thrive on is anger against governmental actors. It is governmental actors who increasingly rely on fear, be it to pursue policy objectives or to keep populists at bay. The Brexit referendum, election of Donald Trump, and COVID-19 are cases in point. In a battle for the hearts and minds of the people, governmental and populist actors send fear and anger signals, respectively. We theorize this dance of fear and anger as the fear-anger cycle.

Joerg Friedrichs 5
Niklas Stoehr 11
Giuliano Formisano 5

work in progress

↗ Project Webpage
↗ Presentation Video
↗ GDELT Blog Post
↗ Research Assistant Job Ad

The CoRisk-Index extends the spectre of existing, but less frequently updated economic indicators by tapping into an unexploited and highly abundant data source. The new indicator can be considered business-internally since corporations provide information themselves and data fidelity is self-incentivized due to law enforcement.

Fabian Stephany 5
Niklas Stoehr 9
Philipp Darius 10
Leonie Neuhäuser 10
Ole Teutloff 10
Fabian Braesemann 5

CEPR Covid Economics

↗ arXiv Paper
↗ CEPR Paper
↗ Online Dashboard
↗ Explanation Video
↗ OII Blog Post
↗ Oxford Blog Post
↗ Wirtschaftswoche
↗ Washington Post
↗ Talk at UNDP
↗ Talk at ODID

This work approaches graph generation (decoding) as the inverse of graph compression (encoding). We show that in a disentanglement-focused deep autoencoding framework, specifically Beta-Variational Autoencoders (Beta-VAE), choices of generative procedures and their parameters arise naturally in the latent space. 

Niklas Stoehr 3
Emine Yilmaz 3
Marc Brockschmidt 6
Jan Stuehmer 6

Workshop on Graph Representation Learning, 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver

↗ arXiv Paper
↗ NeurIPS Paper
↗ Presentation Video
↗ Interactive Code
↗ Poster
↗ Slides

The digital transformation is driving revolutionary innovations and new market entrants threaten established sectors of the economy such as the automotive industry. Following the need for monitoring shifting industries, we present a network-centered analysis of car manufacturer web pages. Solely exploiting publicly-available information, we construct large networks from web pages and hyperlinks. We tag web pages concerned with topics like e-mobility and environment or autonomous driving, and investigate their relevance in the network. 

Niklas Stoehr 9
Fabian Braesemann 5
Michael Frommelt 9
Shi Zhou 3

CompleNet 2020, published in Springer Nature

↗ arXiv Paper
↗ Springer Paper
↗ IBM Blog Post
↗ IBM Livestudio
↗ OII Blog Post
↗ Presentation Video
↗ Code

To understand the dynamics of the digital knowledge economy, it is crucial to reveal the geography of global flows of knowledge on digital platforms. This article visualizes a key form of knowledge production in the digital economy: mapping the joint collaborations of users from different cities on Stack Overflow, the world’s most popular question-and-answer website for programming questions.

Fabian Braesemann 5
Niklas Stoehr 3
Mark Graham 5

Regional Studies, Regional Science, Volume 6, 2019

↗ Journal Paper
↗ OII Blog Post
↗ Code

Classical graph modeling approaches such as Erdos-Renyi (ER) random graphs or Barabasi-Albert (BA) graphs, here referred to as stylized models, aim to reproduce properties of real-world graphs in an interpretable way. While useful, graph generation with stylized models requires domain knowledge and iterative trial and error simulation.

Cristina Guzman 11
Daphna Keidar 11
Andreas Opedal 11
Tristan Meynier 11
Niklas Stoehr 11

ICLR 2021 Geometrical and Topological Representation Learning

↗ ICLR GTRL Paper
↗ arXiv Paper
↗ Poster
↗ Code

EMNLP 2021

Niklas Stoehr 11
Lucas Torroba Hennigen 13
Samin Ahbab
Robert West 15
Ryan Cotterell 11, 12

↗ arXiv paper
↗ EMNLP paper
↗ Poster
↗ Video
↗ Slides
↗ Interactive dashboard
↗ Code

NAACL-HLT 2021

Josef Valvoda 12
Tiago Pimentel 12
Niklas Stoehr 11
Ryan Cotterell 11,12
Simone Teufel 12

↗ NAACL Paper
↗ arXiv Paper
↗ Short Teaser Video
↗ Code

ACL 2021 CASE

Niklas Stoehr 11
Tiancheng Hu 11
Francesco Re 11
Dániel Végh 11
Dennis Atzenhofer 11
Salvatore Giorgi
Ali Hürriyetoğlu
Hristo Tanev 14

↗ Discovering Black Lives Matter Events
↗ Pretraining for Sentence-Level Protest Event Classification
↗ Document- and Sentence-Level Classification for Protest Event Detection

Policy & Internet, Wiley Online Library, 2019

Fabian Falck 4
Julian Marstaller 7
Niklas Stoehr 5
Sören Maucher 7
Jeana Ren 7
Andreas Thalhammer 7
Achim Rettinger 7
Rudi Studer 7

↗ Pre-Print Paper
↗ Journal Paper
↗ Code
↗ Data
↗ Interactive Website
↗ Speakerpolitics

work in progress

Joerg Friedrichs 5
Niklas Stoehr 11
Giuliano Formisano 5

↗ Project Webpage
↗ Presentation Video
↗ GDELT Blog Post
↗ Research Assistant Job Ad

CEPR Covid Economics

Fabian Stephany 5
Niklas Stoehr 9
Philipp Darius 10
Leonie Neuhäuser 10
Ole Teutloff 10
Fabian Braesemann 5

↗ arXiv Paper
↗ CEPR Paper
↗ Online Dashboard
↗ Explanation Video
↗ OII Blog Post
↗ Oxford Blog Post
↗ Wirtschaftswoche
↗ Washington Post
↗ Talk at UNDP
↗ Talk at ODID

Workshop on Graph Representation Learning, 33rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver

Niklas Stoehr 3
Emine Yilmaz 3
Marc Brockschmidt 6
Jan Stuehmer 6

↗ arXiv Paper
↗ NeurIPS Paper
↗ Presentation Video
↗ Interactive Code
↗ Poster
↗ Slides

CompleNet 2020, published in Springer Nature

Niklas Stoehr 9
Fabian Braesemann 5
Michael Frommelt 9
Shi Zhou 3

↗ arXiv Paper
↗ Springer Paper
↗ IBM Blog Post
↗ IBM Livestudio
↗ OII Blog Post
↗ Presentation Video
↗ Code

Regional Studies, Regional Science, Volume 6, 2019

Fabian Braesemann 5
Niklas Stoehr 3
Mark Graham 5

↗ Journal Paper
↗ OII Blog Post
↗ Code

ICLR 2021 Geometrical and Topological Representation Learning

Cristina Guzman 11
Daphna Keidar 11
Andreas Opedal 11
Tristan Meynier 11
Niklas Stoehr 11

↗ ICLR GTRL Paper
↗ arXiv Paper
↗ Poster
↗ Code