{"id":"https://openalex.org/W1608710254","doi":"https://doi.org/10.1002/9781118834732.ch10","title":"Statistical Text Processing","display_name":"Statistical Text Processing","publication_year":2014,"publication_date":"2014-07-28","ids":{"openalex":"https://openalex.org/W1608710254","doi":"https://doi.org/10.1002/9781118834732.ch10","mag":"1608710254"},"language":"en","primary_location":{"id":"doi:10.1002/9781118834732.ch10","doi":"https://doi.org/10.1002/9781118834732.ch10","is_oa":false,"landing_page_url":"https://doi.org/10.1002/9781118834732.ch10","pdf_url":null,"source":{"id":"https://openalex.org/S4306464293","display_name":"Wiley eBooks","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"ebook platform"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Automated Data Collection with R","raw_type":"other"},"volume":{"id":"https://openalex.org/W4244170802","display_name":"Automated Data Collection with R"},"type":"other","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000465232","display_name":"Simon Munzert","orcid":"https://orcid.org/0000-0003-4760-367X","observed_orcids":["https://orcid.org/0000-0003-4760-367X"]},"institutions":[{"id":"https://openalex.org/I189712700","display_name":"University of Konstanz","ror":"https://ror.org/0546hnb39","country_code":"DE","type":"education","lineage":["https://openalex.org/I189712700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Simon Munzert","raw_affiliation_strings":["Department of Politics and Public Administration, University of Konstanz, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Politics and Public Administration, University of Konstanz, Germany","institution_ids":["https://openalex.org/I189712700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060101788","display_name":"Christian Rubba","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Christian Rubba","raw_affiliation_strings":["Department of Political Science, University of Zurich and National Center of Competence in Research, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Political Science, University of Zurich and National Center of Competence in Research, Switzerland","institution_ids":["https://openalex.org/I202697423"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Peter Mei\u00dfner","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I189712700","display_name":"University of Konstanz","ror":"https://ror.org/0546hnb39","country_code":"DE","type":"education","lineage":["https://openalex.org/I189712700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Peter Mei\u00dfner","raw_affiliation_strings":["Department of Politics and Public Administration, University of Konstanz, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Politics and Public Administration, University of Konstanz, Germany","institution_ids":["https://openalex.org/I189712700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055335379","display_name":"Dominic Nyhuis","orcid":"https://orcid.org/0000-0001-6790-4117","observed_orcids":["https://orcid.org/0000-0001-6790-4117"]},"institutions":[{"id":"https://openalex.org/I177802217","display_name":"University of Mannheim","ror":"https://ror.org/031bsb921","country_code":"DE","type":"education","lineage":["https://openalex.org/I177802217"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dominic Nyhuis","raw_affiliation_strings":["Department of Political Science, University of Mannheim, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Political Science, University of Mannheim, Germany","institution_ids":["https://openalex.org/I177802217"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"295","last_page":"321"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.6190999746322632,"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"}},"topics":[{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.6190999746322632,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.36820000410079956,"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/T10028","display_name":"Topic Modeling","score":0.003000000026077032,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/text-mining","display_name":"text mining","score":0.765999972820282},{"id":"https://openalex.org/keywords/text-classification","display_name":"text classification","score":0.7099999785423279},{"id":"https://openalex.org/keywords/supervised-classification","display_name":"supervised classification","score":0.6589999794960022},{"id":"https://openalex.org/keywords/unsupervised-classification","display_name":"unsupervised classification","score":0.8840000033378601},{"id":"https://openalex.org/keywords/unstructured-text","display_name":"unstructured text","score":0.7850000262260437},{"id":"https://openalex.org/keywords/text-preprocessing","display_name":"text preprocessing","score":0.48399999737739563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5005660057067871},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3696177005767822},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3264293074607849}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1002/9781118834732.ch10","doi":"https://doi.org/10.1002/9781118834732.ch10","is_oa":false,"landing_page_url":"https://doi.org/10.1002/9781118834732.ch10","pdf_url":null,"source":{"id":"https://openalex.org/S4306464293","display_name":"Wiley eBooks","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320595","host_organization_name":"Wiley","host_organization_lineage":["https://openalex.org/P4310320595"],"host_organization_lineage_names":["Wiley"],"type":"ebook platform"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Automated Data Collection with R","raw_type":"other"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2625924629","https://openalex.org/W2161793142","https://openalex.org/W7218202334","https://openalex.org/W2803748618","https://openalex.org/W3175166206","https://openalex.org/W7084169642","https://openalex.org/W2952710771","https://openalex.org/W4205515834","https://openalex.org/W4408033692","https://openalex.org/W4387193942"],"abstract_inverted_index":{"This":[0],"chapter":[1,42,75,115,120],"offers":[2],"a":[3,14,60,127,130],"brief":[4],"introduction":[5],"to":[6,25,34,38,44,51,67,107,129,139],"statistical":[7],"text":[8,70,87,112,141],"processing.":[9],"The":[10,41,74,119],"Internet":[11],"is":[12,142],"predominantly":[13],"vast":[15],"collection":[16],"of":[17,47,54,86,99,110,132],"more":[18],"or":[19],"less":[20],"unclassified":[21,55],"text.":[22,40],"In":[23,97],"order":[24,106],"access":[26],"such":[27],"data,":[28,113],"numerous":[29],"techniques":[30,50,101],"have":[31],"been":[32],"devised":[33],"assign":[35],"systematic":[36],"meaning":[37],"unstructured":[39,111],"seeks":[43],"elaborate":[45],"several":[46],"the":[48,77,82,91,94,100,114,122,133,145],"available":[49,134],"make":[52,108],"use":[53],"data.":[56],"It":[57],"first":[58],"presents":[59,116],"small":[61],"running":[62],"example,":[63],"and":[64,84,88],"elaborates":[65],"how":[66],"perform":[68],"large-scale":[69],"operations":[71],"in":[72,105,144],"R.":[73],"introduces":[76,121],"tm":[78],"package":[79,124],"that":[80,102],"allows":[81],"organization":[83],"preparation":[85],"also":[89],"provides":[90,126],"infrastructure":[92],"for":[93],"analytical":[95],"packages.":[96,135],"terms":[98],"are":[103],"presented":[104,143],"sense":[109],"supervised":[117],"methods.":[118],"RTextTools":[123],"which":[125],"wrapper":[128],"number":[131],"A":[136],"second":[137],"approach":[138],"classifying":[140],"chapter-unsupervised":[146],"classifiers.":[147]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}