Logo Utrecht University

Translantis

BILAND: Sentiment mining in historical news media

The digital tools WAHSP and BILAND are able to perform advanced forms of text-mining in large data sets of different news media (newspapers, magazines and transcripts of radio recordings). The tools will enable historians in general to collect and process large sets of opinionated text-data from news media and extract discourse identity and intensity patterns. BILAND can compare these patterns in two different languages.

The starting point for BILAND has been the open-source software infrastructure xTAS developed by the Intelligent Systems Lab at the University of Amsterdam. Building on this infrastructure the CLARIN-supported web-application WAHSP for historical sentiment mining in public media has been built under supervision of historian Stephen Snelders. Every developmental task and research activity within the project has been a trans-disciplinary co-production between historians–as the envisaged end-users–and computer scientists: from selecting and filtering out meaningful lexical items, carrying out text-mining tasks, training the algorithms to meet the needs of the domain users up to in-process feed-back loops.

The BILAND project aims to make the tool useful for bilingual research and to improve its tools of analysis. The search engine is set to search through the digital newspaper collection of the Royal Library in The Hague, consisting of around nine million digitized pages by the end of 2012. The Staatsbibliothek zu Berlin has granted Biland access to three of its digitized historical newspapers, the Amtspresse Preussens, to make the tool also useful for searching through German texts.

CLARIN

CLARIN-NL aims to design, construct, validate, and exploit a research infrastructure that is needed to provide a sustainable and persistent eScience working environment for researchers in the Humanities, and Linguistics in particular, who want to make use of language resources and the technology to use these resources for their research.

The CLARIN-NL project is a large national project in the Netherlands which aims to play a central role in the Europe-wide CLARIN infrastructure. CLARIN-NL offers scholars the tools to allow computer-aided language processing, addressing one or more of the multiple roles language plays (i.e. carrier of cultural content and knowledge, instrument of communication, component of identity and object of study) in the Humanities and Social Sciences.

(From: www.clarin.nl)