<?xml version='1.0' encoding='UTF-8'?><?xml-stylesheet href='static/style.xsl' type='text/xsl'?><OAI-PMH xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/ http://www.openarchives.org/OAI/2.0/OAI-PMH.xsd"><responseDate>2026-04-12T09:44:33Z</responseDate><request verb="GetRecord" identifier="oai:clarin.vdu.lt:20.500.11821/57" metadataPrefix="oai_dc">https://clarin.vdu.lt/oai/request</request><GetRecord><record><header><identifier>oai:clarin.vdu.lt:20.500.11821/57</identifier><datestamp>2024-03-21T17:53:16Z</datestamp><setSpec>hdl_20.500.11821_6</setSpec><setSpec>hdl_20.500.11821_7</setSpec></header><metadata><oai_dc:dc xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:doc="http://www.lyncode.com/xoai" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:dc="http://purl.org/dc/elements/1.1/" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
<dc:title>Wordlist of the Contemporary Corpus of Lithuanian Language in the Face of War in Ukraine</dc:title>
<dc:creator>Dadurkevičius, Virginijus</dc:creator>
<dc:subject>wordlist</dc:subject>
<dc:subject>Lithuanian</dc:subject>
<dc:subject>Ukraine</dc:subject>
<dc:subject>war</dc:subject>
<dc:subject>wartime</dc:subject>
<dc:subject>frequency counts</dc:subject>
<dc:description>We present the comparative wordlist based on the Corpus of the Contemporary Lithuanian Language (CCLL2 version 2, pre-2020), supplemented by the media (courtesy of the news media company 15min – www.15min.lt) and social networks lexicons of the war in Ukraine period (Feb 2022 to Feb 2024).&#xd;
&#xd;
For a fair comparison, all word counts have been normalized as if they were 100m words in each source. CCLL2 has 162m words, wartime media – 36m words and wartime social networks – 2m words. The term "word" does not apply here to punctuation, numbers, dates, URL's, hashtags, popular English words, etc.&#xd;
&#xd;
The data itself is in the form of a tab-separated-values (TSV) text file consisting of the following columns: word(token), CCLL2 count, CCLL2 docs, media count, media docs, social networks count, social networks docs. Where "docs" mean number (normalized) of documents with a particular word. All words are written as case-insensitive using capital letters.</dc:description>
<dc:date>2024-03-13</dc:date>
<dc:type>lexicalConceptualResource</dc:type>
<dc:identifier>http://hdl.handle.net/20.500.11821/57</dc:identifier>
<dc:language>lit</dc:language>
<dc:rights>PUB_CLARIN-LT_End-User-Licence-Agreement_EN-LT</dc:rights>
<dc:rights>https://clarin.vdu.lt/licenses/eula/PUB_CLARIN-LT_End-User-Licence-Agreement_EN-LT.htm</dc:rights>
<dc:rights>PUB</dc:rights>
<dc:format>application/zip</dc:format>
<dc:format>text/plain; charset=utf-8</dc:format>
<dc:format>downloadable_files_count: 1</dc:format>
<dc:publisher>SITTI</dc:publisher>
</oai_dc:dc>
</metadata></record></GetRecord></OAI-PMH>