| <?xml version="1.0" encoding="UTF-8"?> |
| <?xml-model href="header.rng" type="application/xml" schematypens="http://relaxng.org/ns/structure/1.0"?> |
| <!DOCTYPE idsCorpus PUBLIC "-//IDS//DTD IDS-XCES 1.0//EN" "http://corpora.ids-mannheim.de/idsxces1/DTD/ids.xcesdoc.dtd"> |
| <idsHeader type="corpus" pattern="text" status="new" version="1.0" TEIform="teiHeader"> |
| <fileDesc> |
| <titleStmt> |
| <korpusSigle>NGAFC</korpusSigle> |
| <c.title>Newsgroup: de.sci.informatik.misc</c.title> |
| </titleStmt> |
| <editionStmt version="1.0"/> |
| <publicationStmt> |
| <distributor>Institut für Deutsche Sprache</distributor> |
| <pubAddress>Postfach 10 16 21, D-68016 Mannheim</pubAddress> |
| <telephone>+49 (0)621 1581 0</telephone> |
| <eAddress type="www">http://www.ids-mannheim.de</eAddress> |
| <eAddress type="www">http://www.ids-mannheim.de/kl/projekte/korpora/</eAddress> |
| <eAddress type="email">dereko@ids-mannheim.de</eAddress> |
| <availability region="ids" status="unknown" Default="n">QAO-NC-LOC:ids</availability> |
| <pubDate>2016</pubDate> |
| </publicationStmt> |
| <sourceDesc Default="n"> |
| <biblStruct Default="n" status="draft"> |
| <monogr> |
| <h.title type="main">Usenet-Newsgroup</h.title> |
| <h.title type="sub">de.sci.informatik.misc</h.title> |
| <h.author/> |
| <editor>Usenet</editor> |
| <edition> |
| <further>Download from server news.individual.de 2015-06-01 using nntp client in Python; Download from server news.individual.de 2016-01-16 using nntp client in Python</further> |
| <kind/> |
| <appearance/> |
| </edition> |
| <imprint> |
| <publisher>Usenet</publisher> |
| </imprint> |
| </monogr> |
| </biblStruct> |
| </sourceDesc> |
| </fileDesc> |
| <encodingDesc> |
| <projectDesc Default="n"> |
| <p part="N">Project "Korpusausbau", Program area "Korpuslinguistik", Institut fuer Deutsche Sprache, Mannheim, 2015-2016 </p> |
| </projectDesc> |
| <editorialDecl Default="n"> |
| <conformance level="0">This document conforms to I5 (see http://jtei.revues.org/508)</conformance> |
| <transduction n="1" Default="n">Downloading usenet data from server news.individual.de using nntp client in Python on 2015-06-01 and converting it to a first XML format (nntpXML) using lxml.</transduction> |
| <transduction n="2" Default="n">Converting data from nntpXML to I5 using using lxml and Python.</transduction> |
| <transduction n="3" Default="n">Annotating phenomenona of computer-mediated communication (quotes, introduction lines of quotes, openers, closers, postscripts, emoticons, links to the world wide web and to other newsgroups, signatures and paragraphs) using XSLT and regular expressions. For further information see B.A. thesis by Jasmin Schroeck, Universitaet Heidelberg, 2015: Erstellung eines deutschsprachigen Usenet-Newsgroup-Korpus und Annotation von Phaenomenen internetbasierter Kommunikation.</transduction> |
| <transduction n="4" Default="n">Downloading usenet data from server news.individual.de using nntp client in Python on 2016-01-16 and converting it to a first XML format (nntpXML) using lxml.</transduction> |
| <transduction n="5" Default="n">Anonymising the articles (removing messageIDs,links to newsgroups and the WWW, signatures, e-mails and names) and removing quotations.</transduction> |
| </editorialDecl> |
| <classDecl> |
| <taxonomy id="topic"> |
| <h.bibl>Thementaxonomie (siehe http://www.ids-mannheim.de/kl/projekte/methoden/te.html)</h.bibl> |
| <category id="topic.fiktion"> |
| <catDesc>Fiktion</catDesc> |
| <category id="topic.fiktion.vermischtes"> |
| <catDesc>Fiktion:Vermischtes</catDesc> |
| </category> |
| </category> |
| <category id="topic.freizeit-unterhaltung"> |
| <catDesc>Freizeit_Unterhaltung</catDesc> |
| <category id="topic.freizeit-unterhaltung.reisen"> |
| <catDesc>Freizeit_Unterhaltung:Reisen</catDesc> |
| </category> |
| <category id="topic.freizeit-unterhaltung.rundfunk"> |
| <catDesc>Freizeit_Unterhaltung:Rundfunk</catDesc> |
| </category> |
| <category id="topic.freizeit-unterhaltung.vereine-veranstaltungen"> |
| <catDesc>Freizeit_Unterhaltung:Vereine_Veranstaltungen</catDesc> |
| </category> |
| </category> |
| <category id="topic.gesundheit-ernaehrung"> |
| <catDesc>Gesundheit_Ernaehrung</catDesc> |
| <category id="topic.gesundheit-ernaehrung.ernaehrung"> |
| <catDesc>Gesundheit_Ernaehrung:Ernaehrung</catDesc> |
| </category> |
| <category id="topic.gesundheit-ernaehrung.gesundheit"> |
| <catDesc>Gesundheit_Ernaehrung:Gesundheit</catDesc> |
| </category> |
| </category> |
| <category id="topic.kultur"> |
| <catDesc>Kultur</catDesc> |
| <category id="topic.kultur.bildende-kunst"> |
| <catDesc>Kultur:Bildende Kunst</catDesc> |
| </category> |
| <category id="topic.kultur.darstellende-kunst"> |
| <catDesc>Kultur:Darstellende Kunst</catDesc> |
| </category> |
| <category id="topic.kultur.film"> |
| <catDesc>Kultur:Film</catDesc> |
| </category> |
| <category id="topic.kultur.literatur"> |
| <catDesc>Kultur:Literatur</catDesc> |
| </category> |
| <category id="topic.kultur.mode"> |
| <catDesc>Kultur:Mode</catDesc> |
| </category> |
| <category id="topic.kultur.musik"> |
| <catDesc>Kultur:Musik</catDesc> |
| </category> |
| </category> |
| <category id="topic.natur-umwelt"> |
| <catDesc>Natur_Umwelt</catDesc> |
| <category id="topic.natur-umwelt.garten"> |
| <catDesc>Natur_Umwelt:Garten</catDesc> |
| </category> |
| <category id="topic.natur-umwelt.tiere"> |
| <catDesc>Natur_Umwelt:Tiere</catDesc> |
| </category> |
| <category id="topic.natur-umwelt.wetter-klima"> |
| <catDesc>Natur_Umwelt:Wetter_Klima</catDesc> |
| </category> |
| </category> |
| <category id="topic.politik"> |
| <catDesc>Politik</catDesc> |
| <category id="topic.politik.ausland"> |
| <catDesc>Politik:Ausland</catDesc> |
| </category> |
| <category id="topic.politik.inland"> |
| <catDesc>Politik:Inland</catDesc> |
| </category> |
| <category id="topic.politik.kommunalpolitik"> |
| <catDesc>Politik:Kommunalpolitik</catDesc> |
| </category> |
| </category> |
| <category id="topic.rest"> |
| <catDesc>Rest</catDesc> |
| <category id="topic.rest.boersenkurse"> |
| <catDesc>Rest:boersenkurse</catDesc> |
| </category> |
| <category id="topic.rest.geburt-tod-heirat"> |
| <catDesc>Rest:geburt_tod_heirat</catDesc> |
| </category> |
| <category id="topic.rest.impressum"> |
| <catDesc>Rest:impressum</catDesc> |
| </category> |
| <category id="topic.rest.inhaltsverzeichnisse"> |
| <catDesc>Rest:inhaltsverzeichnisse</catDesc> |
| </category> |
| <category id="topic.rest.ligatabellen"> |
| <catDesc>Rest:ligatabellen</catDesc> |
| </category> |
| <category id="topic.rest.tabellen"> |
| <catDesc>Rest:tabellen</catDesc> |
| </category> |
| <category id="topic.rest.veranstaltungshinweise"> |
| <catDesc>Rest:veranstaltungshinweise</catDesc> |
| </category> |
| </category> |
| <category id="topic.sport"> |
| <catDesc>Sport</catDesc> |
| <category id="topic.sport.ballsport"> |
| <catDesc>Sport:Ballsport</catDesc> |
| </category> |
| <category id="topic.sport.fussball"> |
| <catDesc>Sport:Fussball</catDesc> |
| </category> |
| <category id="topic.sport.motorsport"> |
| <catDesc>Sport:Motorsport</catDesc> |
| </category> |
| <category id="topic.sport.radsport"> |
| <catDesc>Sport:Radsport</catDesc> |
| </category> |
| <category id="topic.sport.tennis"> |
| <catDesc>Sport:Tennis</catDesc> |
| </category> |
| <category id="topic.sport.vermischtes"> |
| <catDesc>Sport:Vermischtes</catDesc> |
| </category> |
| <category id="topic.sport.wintersport"> |
| <catDesc>Sport:Wintersport</catDesc> |
| </category> |
| </category> |
| <category id="topic.staat-gesellschaft"> |
| <catDesc>Staat_Gesellschaft</catDesc> |
| <category id="topic.staat-gesellschaft.arbeit-und-beruf"> |
| <catDesc>Staat_Gesellschaft:Arbeit_und_Beruf</catDesc> |
| </category> |
| <category id="topic.staat-gesellschaft.bildung"> |
| <catDesc>Staat_Gesellschaft:Bildung</catDesc> |
| </category> |
| <category id="topic.staat-gesellschaft.biographien-interviews"> |
| <catDesc>Staat_Gesellschaft:Biographien_Interviews</catDesc> |
| </category> |
| <category id="topic.staat-gesellschaft.drittes-reich-rechtsextremismus"> |
| <catDesc>Staat_Gesellschaft:Drittes_Reich_Rechtsextremismus</catDesc> |
| </category> |
| <category id="topic.staat-gesellschaft.familie-geschlecht"> |
| <catDesc>Staat_Gesellschaft:Familie_Geschlecht</catDesc> |
| </category> |
| <category id="topic.staat-gesellschaft.kirche"> |
| <catDesc>Staat_Gesellschaft:Kirche</catDesc> |
| </category> |
| <category id="topic.staat-gesellschaft.recht"> |
| <catDesc>Staat_Gesellschaft:Recht</catDesc> |
| </category> |
| <category id="topic.staat-gesellschaft.tod"> |
| <catDesc>Staat_Gesellschaft:Tod</catDesc> |
| </category> |
| <category id="topic.staat-gesellschaft.verbrechen"> |
| <catDesc>Staat_Gesellschaft:Verbrechen</catDesc> |
| </category> |
| </category> |
| <category id="topic.technik-industrie"> |
| <catDesc>Technik_Industrie</catDesc> |
| <category id="topic.technik-industrie.edv-elektronik"> |
| <catDesc>Technik_Industrie:EDV_Elektronik</catDesc> |
| </category> |
| <category id="topic.technik-industrie.kfz"> |
| <catDesc>Technik_Industrie:Kfz</catDesc> |
| </category> |
| <category id="topic.technik-industrie.transport-verkehr"> |
| <catDesc>Technik_Industrie:Transport_Verkehr</catDesc> |
| </category> |
| <category id="topic.technik-industrie.umweltschutz"> |
| <catDesc>Technik_Industrie:Umweltschutz</catDesc> |
| </category> |
| <category id="topic.technik-industrie.unfaelle"> |
| <catDesc>Technik_Industrie:Unfaelle</catDesc> |
| </category> |
| </category> |
| <category id="topic.wirtschaft-finanzen"> |
| <catDesc>Wirtschaft_Finanzen</catDesc> |
| <category id="topic.wirtschaft-finanzen.banken"> |
| <catDesc>Wirtschaft_Finanzen:Banken</catDesc> |
| </category> |
| <category id="topic.wirtschaft-finanzen.bilanzen"> |
| <catDesc>Wirtschaft_Finanzen:Bilanzen</catDesc> |
| </category> |
| <category id="topic.wirtschaft-finanzen.oeffentliche-finanzen"> |
| <catDesc>Wirtschaft_Finanzen:Oeffentliche_Finanzen</catDesc> |
| </category> |
| <category id="topic.wirtschaft-finanzen.sozialprodukt"> |
| <catDesc>Wirtschaft_Finanzen:Sozialprodukt</catDesc> |
| </category> |
| <category id="topic.wirtschaft-finanzen.waehrung"> |
| <catDesc>Wirtschaft_Finanzen:Waehrung</catDesc> |
| </category> |
| </category> |
| <category id="topic.wissenschaft"> |
| <catDesc>Wissenschaft</catDesc> |
| <category id="topic.wissenschaft.populaerwissenschaft"> |
| <catDesc>Wissenschaft:Populaerwissenschaft</catDesc> |
| </category> |
| </category> |
| <category id="topic.unklassifizierbar"> |
| <catDesc>Text ist thematisch nicht klassifizierbar.</catDesc> |
| </category> |
| </taxonomy> |
| </classDecl> |
| </encodingDesc> |
| <profileDesc> |
| <langUsage Default="n"> |
| <language id="de">Deutsch</language> |
| </langUsage> |
| <textDesc Default="n"> |
| <textType>Newsgroup-Diskussionen</textType> |
| <textTypeRef/> |
| </textDesc> |
| </profileDesc> |
| <revisionDesc status="draft"> |
| <listChange ordered="true"> |
| <change when="2015-08-24" status="draft">Completion of first annotated version</change> |
| <change when="2016-04-27" status="draft">Merging of two downloads of the same newsgroup with different messages (see <further> for more information).</change> |
| </listChange> |
| </revisionDesc> |
| </idsHeader> |