@incollection{BeisswengerWighamEtienneetal.2017, author = {Michael Bei{\"s}wenger and Ciara Wigham and Carole Etienne and Darja Fišer and Holger Grumt Su{\´a}rez and Laura Herzberg and Erhard Hinrichs and Tobias Horsmann and Natali Karlova-Bourbonus and Lothar Lemnitzer and Julien Longhi and Harald L{\"u}ngen and Lydia-Mai Ho-Dac and Christophe Parisse and C{\´e}line Poudat and Thomas Schmidt and Egon W. Stemle and Angelika Storrer and Torsten Zesch}, title = {Connecting resources: Which issues have to be solved to integrate CMC corpora from heterogeneous sources and for different languages?}, series = {Proceedings of the 5th Conference on CMC and Social Media Corpora for the Humanities (cmccorpora17). 3-4 October 2017, Eurac Research, Italy}, editor = {Egon W. Stemle and Ciara R. Wigham}, edition = {First edition}, address = {Bolzano}, url = {https://nbn-resolving.org/urn:nbn:de:bsz:mh39-66401}, pages = {52 -- 55}, year = {2017}, abstract = {The paper reports on the results of a scientific colloquium dedicated to the creation of standards and best practices which are needed to facilitate the integration of language resources for CMC stemming from different origins and the linguistic analysis of CMC phenomena in different languages and genres. The key issue to be solved is that of interoperability – with respect to the structural representation of CMC genres, linguistic annotations metadata, and anonymization/pseudonymization schemas. The objective of the paper is to convince more projects to partake in a discussion about standards for CMC corpora and for the creation of a CMC corpus infrastructure across languages and genres. In view of the broad range of corpus projects which are currently underway all over Europe, there is a great window of opportunity for the creation of standards in a bottom-up approach.}, language = {en} }