Header

School of Applied Linguistics

Swiss-AL: a language data platform for applied sciences

Swiss-AL is a multilingual language data resource of Swiss public communication that allows for data-driven analyses and simulations of social discourse. Swiss-AL is available to researchers and the public as an open research data resource.

As a language data resource, Swiss-AL consists of (1) a family of multilingual Swiss public communication corpora, (2) a corpus and computational linguistics pipeline for compiling and processing these corpora and (3) a browser-based workbench for analysing these corpora. Swiss-AL allows for data-driven research on social discourses in Switzerland. It contains Swiss journalistic media, media releases, news reports and blog posts from players in the worlds of politics  and administration, industry, academia and civil society. To analyse discourses, a flexible processing pipeline makes it possible to model tailor-made sub-corpora.

Application areas

The ZHAW Digital Discourse Lab uses Swiss-AL in applied research projects in order to analyse and simulate public discourses in Switzerland. These projects include the following:

The journalistic data contained in Swiss-AL forms the basis for "Switzerland's Word of the Year"  in German, French, Italian and Romansch.

The ZHAW School of Applied Linguistics uses Swiss-AL for research-based teaching in the School's degree programmes for the preparation of theses at a Bachelor's and Master's level or as part of core studies across all degree programmes.

Swiss-AL and open research data

Swiss-AL has been funded by the ZHAW and swissuniversities as part of the Swiss Open Research Data Grants with the objective of further developing practices for dealing with language-based research data and transferring them into concrete forms of use. Focus here is placed on the practices used by researchers from application-oriented, non-linguistic disciplines to analyse language data.

Access

You can access Swiss-AL using the Swiss-AL workbench developed at the School of Applied Linguistics:

Composition

The Swiss-AL corpus family comprises three components:

  1. Swiss-AL Base: a selection of central players in the area of Swiss public communication from the worlds of journalism, politics and administration, academia, business and civil society. The corpus is suitable for exploring discourses and formulating hypotheses.
  2. Swiss-AL Media: broad compilation of journalistic media (daily and weekly newspapers, local/regional/cross-regional).
  3. Swiss-AL Projects: corpora from interdisciplinary and transdisciplinary research projects about specific discourses; methodological innovations in these projects contribute to compiling and producing Swiss-AL Media and Base.

The ZHAW Digital Discourse Lab creates corpora using a corpus and computational linguistic pipeline developed at the ZHAW. The text data is regularly and automatically downloaded from the web (web crawling) and obtained via the Swiss Media Database (Swissdox@LiRI) in the case of journalistic media.

Publications

Team