Generating Politically-Relevant Event Data
This work addresses the need for updated automated data extraction in social sciences, representing an incremental improvement over existing methods.
The paper tackles the problem of generating political event data from news text by applying deep neural networks, showing that these modern methods can be effectively used for this task, though specific numerical results are not provided in the abstract.
Automatically generated political event data is an important part of the social science data ecosystem. The approaches for generating this data, though, have remained largely the same for two decades. During this time, the field of computational linguistics has progressed tremendously. This paper presents an overview of political event data, including methods and ontologies, and a set of experiments to determine the applicability of deep neural networks to the extraction of political events from news text.