{"id":"https://openalex.org/W950278104","doi":null,"title":"Mining corpora of computer-mediated communication: analysis of linguistic features in Wikipedia talk pages using machine learning methods","display_name":"Mining corpora of computer-mediated communication: analysis of linguistic features in Wikipedia talk pages using machine learning methods","publication_year":2014,"publication_date":"2014-01-01","ids":{"openalex":"https://openalex.org/W950278104","mag":"950278104"},"language":"en","primary_location":{"id":"pmh:oai:hildok.bsz-bw.de:276","doi":null,"is_oa":true,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:gbv:hil2-opus-2930","pdf_url":"https://hildok.bsz-bw.de/files/276/01_06.pdf","source":{"id":"https://openalex.org/S4306400083","display_name":"HilDok \u2013 Institutional Repository (Universit\u00e4t Hildesheim)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210142515","host_organization_name":"Springer Nature (Switzerland)","host_organization_lineage":["https://openalex.org/I4210142515"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conferenceobject"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hildok.bsz-bw.de/files/276/01_06.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062241567","display_name":"Michael Bei\u00dfwenger","orcid":"https://orcid.org/0000-0001-9442-5402","observed_orcids":["https://orcid.org/0000-0001-9442-5402"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Bei\u00dfwenger","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006681555","display_name":"Harald L\u00fcngen","orcid":"https://orcid.org/0009-0009-3107-0080","observed_orcids":["https://orcid.org/0009-0009-3107-0080"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Harald L\u00fcngen","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0009-3107-0080","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068441853","display_name":"Eliza Margaretha","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eliza Margaretha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5000254667","display_name":"Christian P\u00f6litz","orcid":"https://orcid.org/0000-0003-1690-0540","observed_orcids":["https://orcid.org/0000-0003-1690-0540"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christian P\u00f6litz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":93},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.614300012588501,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.614300012588501,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.09279999881982803,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12377","display_name":"Digital Humanities and Scholarship","score":0.08269999921321869,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-mediated-communication","display_name":"computer-mediated communication","score":0.9639999866485596},{"id":"https://openalex.org/keywords/wikipedia-talk-pages","display_name":"Wikipedia talk pages","score":0.9829999804496765},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"support vector machine","score":0.8220000267028809},{"id":"https://openalex.org/keywords/german-wikipedia","display_name":"German Wikipedia","score":0.5479999780654907},{"id":"https://openalex.org/keywords/dereko","display_name":"DeReKo","score":0.8840000033378601},{"id":"https://openalex.org/keywords/corpus-annotation","display_name":"corpus annotation","score":0.671999990940094},{"id":"https://openalex.org/keywords/syntactic-and-semantic-features","display_name":"syntactic and semantic features","score":0.7609999775886536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7882384061813354},{"id":"https://openalex.org/C154775046","wikidata":"https://www.wikidata.org/wiki/Q188","display_name":"German","level":2,"score":0.7030933499336243},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6903880834579468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6680202484130859},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.6487312912940979},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6030781269073486},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5732927918434143},{"id":"https://openalex.org/C2987219923","wikidata":"https://www.wikidata.org/wiki/Q777864","display_name":"Linguistic analysis","level":2,"score":0.45453813672065735},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.35188180208206177},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3215082585811615},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:hildok.bsz-bw.de:276","doi":null,"is_oa":true,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:gbv:hil2-opus-2930","pdf_url":"https://hildok.bsz-bw.de/files/276/01_06.pdf","source":{"id":"https://openalex.org/S4306400083","display_name":"HilDok \u2013 Institutional Repository (Universit\u00e4t Hildesheim)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210142515","host_organization_name":"Springer Nature (Switzerland)","host_organization_lineage":["https://openalex.org/I4210142515"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conferenceobject"},{"id":"pmh:oai:ids-pub.bsz-bw.de:3187","doi":null,"is_oa":true,"landing_page_url":"https://ids-pub.bsz-bw.de/frontdoor/index/index/docId/3187","pdf_url":null,"source":{"id":"https://openalex.org/S4306401750","display_name":"Publication Server of the Institute for German Language (Institute for German Language)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210099471","host_organization_name":"Leibniz Institute for the German Language","host_organization_lineage":["https://openalex.org/I4210099471"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conferenceobject"},{"id":"mag:950278104","doi":null,"is_oa":false,"landing_page_url":"https://hildok.bsz-bw.de/files/276/01_06.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:hildok.bsz-bw.de:276","doi":null,"is_oa":true,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:gbv:hil2-opus-2930","pdf_url":"https://hildok.bsz-bw.de/files/276/01_06.pdf","source":{"id":"https://openalex.org/S4306400083","display_name":"HilDok \u2013 Institutional Repository (Universit\u00e4t Hildesheim)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210142515","host_organization_name":"Springer Nature (Switzerland)","host_organization_lineage":["https://openalex.org/I4210142515"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conferenceobject"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W950278104.pdf","grobid_xml":"https://content.openalex.org/works/W950278104.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7096743156","https://openalex.org/W7113505071","https://openalex.org/W2200577185","https://openalex.org/W2617438846","https://openalex.org/W7208555432","https://openalex.org/W2972680047","https://openalex.org/W6903418837","https://openalex.org/W122475380","https://openalex.org/W2807997249","https://openalex.org/W7212129491"],"abstract_inverted_index":{"Machine":[0,64],"learning":[1,36],"methods":[2,37],"offer":[3],"a":[4,61],"great":[5],"potential":[6],"to":[7,19,38,96],"automatically":[8],"investigate":[9,90],"large":[10],"amounts":[11],"of":[12,41,47,69,76,93,113,118],"data":[13,95],"in":[14,26,44,73,81,121],"the":[15,20,27,39,52,67,77,85,94,104,116],"humanities.":[16],"Our":[17],"contribution":[18],"workshop":[21],"reports":[22],"about":[23],"ongoing":[24],"work":[25],"BMBF":[28],"project":[29],"KobRA":[30],"(http://www.kobra.tu-dortmund.de)":[31],"where":[32],"we":[33,54],"apply":[34],"machine":[35],"analysis":[40],"big":[42],"corpora":[43],"language-focused":[45],"research":[46,112],"computer-mediated":[48],"communication":[49],"(CMC).":[50],"At":[51],"workshop,":[53],"will":[55,89],"discuss":[56],"first":[57],"results":[58,107],"from":[59],"training":[60],"Support":[62],"Vector":[63],"(SVM)":[65],"for":[66,103],"classification":[68],"selected":[70],"linguistic":[71,119],"features":[72,120],"talk":[74],"pages":[75],"German":[78],"Wikipedia":[79],"corpus":[80],"DeReKo":[82],"provided":[83],"by":[84],"IDS":[86],"Mannheim.":[87],"We":[88],"different":[91],"representations":[92],"integrate":[97],"complex":[98],"syntactic":[99],"and":[100,115],"semantic":[101],"information":[102],"SVM.":[105],"The":[106],"shall":[108],"foster":[109],"both":[110],"corpus-based":[111],"CMC":[114,122],"annotation":[117],"corpora.":[123]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-09-21T07:43:02.447757","created_date":"2016-06-24T00:00:00"}
