Wouter van Atteveldt

Wouter van Atteveldt

Professor of Computational Communication Science & Political Communication

OPTED - Observatory for Political Texts in European Democracies

OPTED is a design study that lays the foundation for an infrastructure that will serve a major hub for political text analysis in Europe. The EU-funded H2020 project involves 17 research institutions organized in 10 work packages which collaboratively work on designing the building blocks of the infrastructure. Among the objectives of the infrastructure are scientific community building, the extension of text analysis tools, and learning materials for social scientists, the broader public and journalists.

Work Package 7: Pre-processing, storage and data sharing

WP7 (Pre-processing, storage and data sharing) establishes routines and protocols for varieties of standardizations of pre-processing, pending on source and purpose of usage of text. It assesses and provides prototypes of open science and open data structures in terms of data storage. Concretely, the WP has the following concrete objectives: (i) Design principles and requirements for storage of political text and related metadata and annotations. (ii) Design principles and requirements for multilingual NLP preprocessing. (iii) Design principles and requirements for a system that allows maximal data transparency while respecting restrictions on underlying data (e.g. copyright, privacy). (iv) Prototyping and implementation of the relevant components. Learn more about WP7!

Scientific team WP7