{"id":"https://openalex.org/W2963364528","doi":null,"title":"Document Retrieval for Large Scale Content Analysis using Contextualized Dictionaries","display_name":"Document Retrieval for Large Scale Content Analysis using Contextualized Dictionaries","publication_year":2014,"publication_date":"2014-06-19","ids":{"openalex":"https://openalex.org/W2963364528","mag":"2963364528"},"language":"en","primary_location":{"id":"pmh:oai:HAL:hal-01005879v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-01005879","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Terminology and Knowledge Engineering 2014, Jun 2014, Berlin, Germany. 10 p","raw_type":"info:eu-repo/semantics/conferenceObject"},"volume":null,"type":"conference-paper","indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-01005879","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068268204","display_name":"Gregor Wiedemann","orcid":"https://orcid.org/0000-0002-4239-295X","observed_orcids":["https://orcid.org/0000-0002-4239-295X"]},"institutions":[{"id":"https://openalex.org/I926574661","display_name":"Leipzig University","ror":"https://ror.org/03s7gtk40","country_code":"DE","type":"education","lineage":["https://openalex.org/I926574661"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Wiedemann, Gregor","raw_affiliation_strings":["Abteilung Automatische Sprachverarbeitung, Institut f\u00fcr Informatik, Universtit\u00e4t Leipzig"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Abteilung Automatische Sprachverarbeitung, Institut f\u00fcr Informatik, Universtit\u00e4t Leipzig","institution_ids":["https://openalex.org/I926574661"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058667349","display_name":"Andreas Niekler","orcid":"https://orcid.org/0000-0002-3036-3318","observed_orcids":["https://orcid.org/0000-0002-3036-3318"]},"institutions":[{"id":"https://openalex.org/I926574661","display_name":"Leipzig University","ror":"https://ror.org/03s7gtk40","country_code":"DE","type":"education","lineage":["https://openalex.org/I926574661"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Niekler, Andreas","raw_affiliation_strings":["Abteilung Automatische Sprachverarbeitung, Institut f\u00fcr Informatik, Universtit\u00e4t Leipzig"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Abteilung Automatische Sprachverarbeitung, Institut f\u00fcr Informatik, Universtit\u00e4t Leipzig","institution_ids":["https://openalex.org/I926574661"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I926574661"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.31534091,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"10 p","last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.6557999849319458,"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":0.6557999849319458,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.13570000231266022,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.09120000153779984,"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/document-retrieval","display_name":"document retrieval","score":0.9990000128746033}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8313229084014893},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.8187144994735718},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6735719442367554},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6326756477355957},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.46050330996513367},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:HAL:hal-01005879v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-01005879","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Terminology and Knowledge Engineering 2014, Jun 2014, Berlin, Germany. 10 p","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-01005879v1","doi":null,"is_oa":true,"landing_page_url":"https://hal.science/hal-01005879","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4405252976","host_organization_name":"Centre pour la Communication Scientifique Directe","host_organization_lineage":["https://openalex.org/I4405252976"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Terminology and Knowledge Engineering 2014, Jun 2014, Berlin, Germany. 10 p","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.7799999713897705,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1831355885","https://openalex.org/W1880262756","https://openalex.org/W1892813713","https://openalex.org/W1974406477","https://openalex.org/W2000569744","https://openalex.org/W2096411881","https://openalex.org/W2104679989","https://openalex.org/W2105378642","https://openalex.org/W2116780029","https://openalex.org/W2153222072","https://openalex.org/W2154099718","https://openalex.org/W2165612380","https://openalex.org/W2407557870","https://openalex.org/W2597643885","https://openalex.org/W3160981298"],"related_works":["https://openalex.org/W2241668498","https://openalex.org/W1587290206","https://openalex.org/W2766722902","https://openalex.org/W2264667908","https://openalex.org/W7061227461","https://openalex.org/W2362826354","https://openalex.org/W67763452","https://openalex.org/W7038835495","https://openalex.org/W2035501029","https://openalex.org/W1981922192"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,44,68],"procedure":[4,133],"to":[5,29,65,90,103,142],"retrieve":[6],"subsets":[7],"of":[8,32,47,70,77,85,100,107,145],"rele-":[9],"vant":[10],"documents":[11,72,102],"from":[12,126],"large":[13,105],"text":[14],"collections":[15,99],"for":[16,25,138],"Content":[17],"Analysis,":[18],"e.g.":[19],"in":[20,88],"social":[21],"sciences.":[22],"Document":[23],"retrieval":[24,93,136],"this":[26,139],"purpose":[27,140],"needs":[28],"take":[30],"account":[31],"the":[33,132],"fact":[34],"that":[35,131],"analysts":[36],"often":[37],"cannot":[38],"describe":[39],"their":[40],"research":[41,58],"objective":[42],"with":[43,53],"small":[45],"set":[46,69],"key":[48,110,146],"terms,":[49,111],"especially":[50],"when":[51],"dealing":[52],"theoretical":[54],"or":[55],"rather":[56],"abstract":[57],"interests.":[59],"Instead,":[60],"it":[61],"is":[62],"much":[63],"easier":[64],"de":[66],"ne":[67],"paradigmatic":[71],"which":[73],"re":[74],"ect":[75],"topics":[76],"interest":[78],"as":[79,81,149,151],"well":[80,150],"tar-":[82],"geted":[83],"manner":[84],"speech.":[86],"Thus,":[87],"contrast":[89],"classic":[91],"information":[92],"tasks":[94],"we":[95],"employ":[96],"manually":[97],"compiled":[98],"reference":[101,127],"compose":[104],"queries":[106],"several":[108],"hundred":[109],"called":[112],"dictionar-":[113],"ies.":[114],"We":[115],"extract":[116],"dictionaries":[117],"via":[118],"Topic":[119],"Models":[120],"and":[121],"also":[122],"use":[123],"co-occurrence":[124,153],"data":[125],"collections.":[128],"Evaluations":[129],"show":[130],"im-":[134],"proves":[135],"results":[137],"compared":[141],"alternative":[143],"methods":[144],"term":[147],"extraction":[148],"neglecting":[152],"data.":[154]},"counts_by_year":[{"year":2019,"cited_by_count":1}],"updated_date":"2026-10-25T09:29:13.331239","created_date":"2025-10-10T00:00:00"}