Der Blog

Unsere Blogartikel werden von Mitgliedern des Projektteams verfasst. Die Themen umfassen ein breites Spektrum: Bericht über Tagungen, auf denen wir vertreten waren, Reflexionen über aktuelle Herausforderungen und Themen, interne Ergebnisse und Fortschrittsberichte, Case Studies aus dem Bereich der digitalen Geisteswissenschaften, sowie Nachrichten über aktuelle Publikationen aus dem Projekt. Die Blogbeiträge werden hauptsächlich auf Englisch verfasst, ab und zu aber auch in der Sprache des*der Verfasser*in. Wir sind schließlich ein multilinguales Team! Wir wünschen spannende Lektüre.

 

What's Past is Prologue: The NewsEye International Conference 2021

This summer, the NewsEye blog will be looking back on NewsEye events that have been held this year. Follow along with #summernewseye.

Over the past year and a half, many of us have become more accustomed to working and keeping up with loved ones through videoconference platforms. Our International Conference, which was held on the 16th and 17th of March 2021, did not make an exception to this rule. Despite taking place completely online, the conference was attended by more than two hundred people across the world. Featuring the work of four keynote speakers and over thirty presenters hailing from eleven countries, the conference was truly international and interdisciplinary, much like the NewsEye project!

The conference was kicked off in the afternoon by four keynote speakers: Ann Dooms, Clemens Neudecker, Ian Milligan and Gerben Zaagsma. Then, presentations by NewsEye colleagues wrapped up a dense first half day. Day Two featured work on the topics of 'Digitised Newspapers and Machine Learning: Extraction and Classification of News Items', 'Digitised Historical Newspapers: Working with Classified News Items and Information Extraction', 'Digitised Historical Material: Improving Data Quality' and 'Challenges and Perspectives in Digital Research: Workflows, Pipelines, Digital Libraries and Digital Literacy'. Check out the conference videos below!

Detailed Conference Programme

 

List of Keynote Speakers & Presenters

 

Download the Book of Abstracts from Zenodo

 

Introduction, Keynote Speaker Presentations and Roundtable Discussion

Keynote Speakers: Ann Dooms (Vrije Universiteit Brussel, Belgium), Clemens Neudecker (Berlin State Library, Germany), Gerben Zaagsma (University of Luxembourg, Luxembourg) and Ian Milligan (University of Waterloo, Canada)

Moderated by Eva Pfanzelter (University of Innsbruck, Austria) and featuring Antoine Doucet (University of La Rochelle, France)

Paper Presentations from NewsEye Contributors and Colleagues

  1. Corpus Building Meets Text Mining: The creation of a topic-specific newspaper corpus on the topic of return migration using LDA and JSD (Sarah Oberbichler, University of Innsbruck)
  2. Towards automated discourse change detection (Quan Duong and Lidia Pivovarova, University of Helsinki)

Moderated by Sally Chambers (KBR, the Royal Library of Belgium and Ghent Centre for Digital Humanities

Digitised Newspapers and Machine Learning: Extraction and Classification of News Items

  1. Challenges in extraction and classification of news articles from historical newspapers (Dilawar Ali and Steven Verstockt)
  2. Semantic segmentation and document layout recognition - approaches to full text recognition of early Chinese newspapers (Matthias Arnold)

Moderated by Sarah Oberbichler (University of Innsbruck, Austria)

Digitised Historical Newspapers: Working with Classified News Items and Information Extraction

  1. The incredibly differentiating labor market: Evidence from job offers (Vera Maria Charvat and Nenad Pantelic)
  2. The DIGITARIUM as a research corpus: New approaches to extracting and linking named entities from historical newspapers (Nina C. Rastinger and Matthias Schlögl)

Moderated by Jean-Philippe Moreux (The National Library of France)

Digitised Historical Material: Improving Data Quality

  1. Discovering Spatial Relations in Literature: What is the influence of OCR noise? (Gaël Lejeune and Caroline Parfait)
  2. Evaluating the multilingual capabilities of PERO-OCR with digitised historical newspapers: A Belgian case study (Julie M. Birkholz, Sally Chambers, Michal Hradis and Pavel Smrz)
  3. Two Examples of Analysis of Textual Document in Oriental and Under-Resourced Languages (Chahan Vidal-Gorène)

Moderated by Juha Rautiainen (The National Library of Finland)

Challenges and Perspectives in Digital Research: Workflows, Pipelines, Digital Libraries and Digital Literacy

Moderated by Sally Chambers (KBR, the Royal Library of Belgium and Ghent Centre for Digital Humanities)

  1. From Chronicling America to Newspaper Navigator: Improving Access to Historic Newspaper Photos at the Library of Congress through Machine Learning (Ben Lee and Nathan Yarasavage)
  2. DAHN: An accessible and transparent pipeline for publishing historical egodocuments (Alix Chagué and Floriane Chiffoleau)
  3. The Case for Magazines: Citizen Historian and Citizen Scientist Perspectives (Timlynn Babitsky, James Hyman, Steven Lomazow and Jim Salmons)