arXiv subjects

Niklas Stoehr

Publications and source records attributed to Niklas Stoehr.

25 records · Page 2Linked to original sources

arXiv2021

Classifying Dyads for Militarized Conflict Analysis

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. We do this by devising a set of textual and graph-based features which represent each of the causes. The features are extracted from Wikipedia and modeled as a large graph. Nodes in this graph represent entities connected by labeled edges representing ally or enemy-relationships. This allows casting the problem as an edge classification task, which we term dyad classification. We propose and evaluate classifiers to determine if a particular pair of entities are allies or enemies. Our results suggest that our systemic features might be slightly better correlates of conflict. Further, we find that Wikipedia articles of allies are semantically more similar than enemies.

cs.CL↗

arXiv2021

SeismographAPI: Visualising Temporal-Spatial Crisis Data

Effective decision-making for crisis mitigation increasingly relies on visualisation of large amounts of data. While interactive dashboards are more informative than static visualisations, their development is far more time-demanding and requires a range of technical and financial capabilities. There are few open-source libraries available, which is blocking contributions from low-resource environments and impeding rapid crisis responses. To address these limitations, we present SeismographAPI, an open-source library for visualising temporal-spatial crisis data on the country- and sub-country level in two use cases: Conflict Monitoring Map and Pandemic Monitoring Map. The library provides easy-to-use data connectors, broad functionality, clear documentation and run time-efficiency.

cs.HC↗

arXiv2021

Recovering Barabási-Albert Parameters of Graphs through Disentanglement

Classical graph modeling approaches such as Erdős Rényi (ER) random graphs or Barabási-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. Previous work by Stoehr et al. (2019) addresses these issues by learning the generation process from graph data, using a disentanglement-focused deep autoencoding framework, more specifically, a $β$-Variational Autoencoder ($β$-VAE). While they successfully recover the generative parameters of ER graphs through the model's latent variables, their model performs badly on sequentially generated graphs such as BA graphs, due to their oversimplified decoder. We focus on recovering the generative parameters of BA graphs by replacing their $β$-VAE decoder with a sequential one. We first learn the generative BA parameters in a supervised fashion using a Graph Neural Network (GNN) and a Random Forest Regressor, by minimizing the squared loss between the true generative parameters and the latent variables. Next, we train a $β$-VAE model, combining the GNN encoder from the first stage with an LSTM-based decoder with a customized loss.

cs.SI↗

arXiv2021

What About the Precedent: An Information-Theoretic Analysis of Common Law

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), which allows us to access not only the case itself, but also cases cited in the judges' arguments (i.e. the precedent cases). Taking an information-theoretic view, and modelling the question as a case outcome classification task, we find that the precedent's arguments share 0.38 nats of information with the case's outcome, whereas precedent's facts only share 0.18 nats of information (i.e., 58% less); suggesting Halsbury's view may be more accurate in this specific court. We found however in a qualitative analysis that there are specific statues where Goodhart's view dominates, and present some evidence these are the ones where the legal concept at hand is less straightforward.

cs.CY↗

arXiv2020

The CoRisk-Index: A data-mining approach to identify industry-specific risk assessments related to COVID-19 in real-time

While the coronavirus spreads, governments are attempting to reduce contagion rates at the expense of negative economic effects. Market expectations plummeted, foreshadowing the risk of a global economic crisis and mass unemployment. Governments provide huge financial aid programmes to mitigate the economic shocks. To achieve higher effectiveness with such policy measures, it is key to identify the industries that are most in need of support. In this study, we introduce a data-mining approach to measure industry-specific risks related to COVID-19. We examine company risk reports filed to the U.S. Securities and Exchange Commission (SEC). This alternative data set can complement more traditional economic indicators in times of the fast-evolving crisis as it allows for a real-time analysis of risk assessments. Preliminary findings suggest that the companies' awareness towards corona-related business risks is ahead of the overall stock market developments. Our approach allows to distinguish the industries by their risk awareness towards COVID-19. Based on natural language processing, we identify corona-related risk topics and their perceived relevance for different industries. The preliminary findings are summarised as an up-to-date online index. The CoRisk-Index tracks the industry-specific risk assessments related to the crisis, as it spreads through the economy. The tracking tool is updated weekly. It could provide relevant empirical data to inform models on the economic effects of the crisis. Such complementary empirical information could ultimately help policymakers to effectively target financial support in order to mitigate the economic shocks of the crisis.

econ.GN↗

arXiv2020

Mining the Automotive Industry: A Network Analysis of Corporate Positioning and Technological Trends

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-centred analysis of car manufacturer web pages. Solely exploiting publicly-available information, we construct large networks from web pages and hyperlinks. The network properties disclose the internal corporate positioning of the three largest automotive manufacturers, Toyota, Volkswagen and Hyundai with respect to innovative trends and their international outlook. We tag web pages concerned with topics like e-mobility and environment or autonomous driving, and investigate their relevance in the network. Sentiment analysis on individual web pages uncovers a relationship between page linking and use of positive language, particularly with respect to innovative trends. Web pages of the same country domain form clusters of different size in the network that reveal strong correlations with sales market orientation. Our approach maintains the web content's hierarchical structure imposed by the web page networks. It, thus, presents a method to reveal hierarchical structures of unstructured text content obtained from web scraping. It is highly transparent, reproducible and data driven, and could be used to gain complementary insights into innovative strategies of firms and competitive landscapes, which would not be detectable by the analysis of web content alone.

cs.SI↗

arXiv2019

Disentangling Interpretable Generative Parameters of Random and Real-World Graphs

While a wide range of interpretable generative procedures for graphs exist, matching observed graph topologies with such procedures and choices for its parameters remains an open problem. Devising generative models that closely reproduce real-world graphs requires domain knowledge and time-consuming simulation. While existing deep learning approaches rely on less manual modelling, they offer little interpretability. 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. Our model is capable of learning disentangled, interpretable latent variables that represent the generative parameters of procedurally generated random graphs and real-world graphs. The degree of disentanglement is quantitatively measured using the Mutual Information Gap (MIG). When training our Beta-VAE model on ER random graphs, its latent variables have a near one-to-one mapping to the ER random graph parameters n and p. We deploy the model to analyse the correlation between graph topology and node attributes measuring their mutual dependence without handpicking topological properties.

cs.LG↗