{"id":"https://openalex.org/W2062538491","doi":"https://doi.org/10.1002/meet.2011.14504801048","title":"Building topic models in a federated digital library through selective document exclusion","display_name":"Building topic models in a federated digital library through selective document exclusion","publication_year":2011,"publication_date":"2011-01-01","ids":{"openalex":"https://openalex.org/W2062538491","doi":"https://doi.org/10.1002/meet.2011.14504801048","mag":"2062538491"},"language":"en","primary_location":{"id":"doi:10.1002/meet.2011.14504801048","is_oa":true,"landing_page_url":"https://doi.org/10.1002/meet.2011.14504801048","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/meet.2011.14504801048","source":{"id":"https://openalex.org/S4306523999","display_name":"Proceedings of the American Society for Information Science and Technology","issn_l":"1550-8390","issn":["1550-8390","1936-1734"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the American Society for Information Science and Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/meet.2011.14504801048","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065007271","display_name":"Miles Efron","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Miles Efron","raw_affiliation_strings":["Graduate School of Library and Information Science University of Illinois, Urbana-Champaign 501 E. Daniel St. Champaign, IL 61820","Graduate School of Library and Information Science University of Illinois, Urbana\u2010Champaign 501 E. Daniel St. Champaign, IL 61820"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Library and Information Science University of Illinois, Urbana-Champaign 501 E. Daniel St. Champaign, IL 61820","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Graduate School of Library and Information Science University of Illinois, Urbana\u2010Champaign 501 E. Daniel St. Champaign, IL 61820","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001038669","display_name":"Peter Organisciak","orcid":"https://orcid.org/0000-0002-9058-2280"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Peter Organisciak","raw_affiliation_strings":["Graduate School of Library and Information Science University of Illinois, Urbana-Champaign 501 E. Daniel St. Champaign, IL 61820","Graduate School of Library and Information Science University of Illinois, Urbana\u2010Champaign 501 E. Daniel St. Champaign, IL 61820"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Library and Information Science University of Illinois, Urbana-Champaign 501 E. Daniel St. Champaign, IL 61820","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Graduate School of Library and Information Science University of Illinois, Urbana\u2010Champaign 501 E. Daniel St. Champaign, IL 61820","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002257700","display_name":"Katrina Fenlon","orcid":"https://orcid.org/0000-0003-1483-5335"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Katrina Fenlon","raw_affiliation_strings":["Graduate School of Library and Information Science University of Illinois, Urbana-Champaign 501 E. Daniel St. Champaign, IL 61820","Graduate School of Library and Information Science University of Illinois, Urbana\u2010Champaign 501 E. Daniel St. Champaign, IL 61820"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Library and Information Science University of Illinois, Urbana-Champaign 501 E. Daniel St. Champaign, IL 61820","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Graduate School of Library and Information Science University of Illinois, Urbana\u2010Champaign 501 E. Daniel St. Champaign, IL 61820","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5001038669","https://openalex.org/A5002257700","https://openalex.org/A5065007271"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":3.077,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.91950127,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"48","issue":"1","first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9943000078201294,"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":0.9943000078201294,"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/T11309","display_name":"Music and Audio Processing","score":0.992900013923645,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9925000071525574,"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/metadata","display_name":"Metadata","score":0.9170428514480591},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7968258261680603},{"id":"https://openalex.org/keywords/digital-collections","display_name":"Digital collections","score":0.6332058310508728},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.6116669774055481},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5838112831115723},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5827744007110596},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.5501400828361511},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4628177881240845},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3551347255706787}],"concepts":[{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.9170428514480591},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7968258261680603},{"id":"https://openalex.org/C2988765800","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital collections","level":2,"score":0.6332058310508728},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.6116669774055481},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5838112831115723},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5827744007110596},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.5501400828361511},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4628177881240845},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3551347255706787},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1002/meet.2011.14504801048","is_oa":true,"landing_page_url":"https://doi.org/10.1002/meet.2011.14504801048","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/meet.2011.14504801048","source":{"id":"https://openalex.org/S4306523999","display_name":"Proceedings of the American Society for Information Science and Technology","issn_l":"1550-8390","issn":["1550-8390","1936-1734"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the American Society for Information Science and Technology","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.371.9647","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.371.9647","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://people.lis.illinois.edu/~mefron/papers/ASIST2011.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.458.7494","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.458.7494","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.asis.org/asist2011/proceedings/submissions/48_FINAL_SUBMISSION.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1002/meet.2011.14504801048","is_oa":true,"landing_page_url":"https://doi.org/10.1002/meet.2011.14504801048","pdf_url":"https://onlinelibrary.wiley.com/doi/pdfdirect/10.1002/meet.2011.14504801048","source":{"id":"https://openalex.org/S4306523999","display_name":"Proceedings of the American Society for Information Science and Technology","issn_l":"1550-8390","issn":["1550-8390","1936-1734"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the American Society for Information Science and Technology","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306122","display_name":"Institute of Museum and Library Services","ror":"https://ror.org/030prv062"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2062538491.pdf","grobid_xml":"https://content.openalex.org/works/W2062538491.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W72866020","https://openalex.org/W1494811239","https://openalex.org/W1880262756","https://openalex.org/W1972716651","https://openalex.org/W2020842694","https://openalex.org/W2100026518","https://openalex.org/W2141441158","https://openalex.org/W2147946282","https://openalex.org/W2158266063","https://openalex.org/W2158479092","https://openalex.org/W2159426623","https://openalex.org/W2163382007","https://openalex.org/W2170909627","https://openalex.org/W4211088835"],"related_works":["https://openalex.org/W1987401411","https://openalex.org/W2129427004","https://openalex.org/W4229534697","https://openalex.org/W2027523974","https://openalex.org/W3127814564","https://openalex.org/W1964419532","https://openalex.org/W4255100935","https://openalex.org/W2483159737","https://openalex.org/W1967737214","https://openalex.org/W2368778223"],"abstract_inverted_index":{"Abstract":[0],"Building":[1],"topic":[2,41,61,130],"models":[3,131],"in":[4,43,86,112,116],"federated":[5],"digital":[6],"collections":[7,45],"presents":[8],"numerous":[9],"challenges":[10],"due":[11],"to":[12,22,39,128],"metadata":[13,19],"inconsistencies.":[14],"The":[15],"quality":[16],"of":[17,83,98],"topical":[18,53,64,78],"is":[20,25,73],"difficult":[21],"ascertain":[23],"and":[24,100,105],"interspersed":[26],"with":[27],"often":[28],"irrelevant":[29],"administrative":[30],"metadata.":[31],"In":[32,89,118],"this":[33],"study,":[34],"we":[35,121],"propose":[36],"a":[37,87,93],"way":[38],"improve":[40],"modeling":[42],"large":[44],"by":[46,80],"identifying":[47,76],"documents":[48,56,79,85],"that":[49,123],"convey":[50],"only":[51],"weak":[52],"information.":[54],"These":[55],"are":[57,66],"ignored":[58],"when":[59],"training":[60],"models.":[62],"Their":[63],"associations":[65],"instead":[67],"inferred":[68],"model":[69],"training.":[70],"A":[71],"method":[72],"outlined":[74],"for":[75],"weakly":[77],"defining":[81],"runs":[82],"similar":[84],"collection.":[88],"preliminary":[90],"evaluation":[91],"using":[92,132],"corpus":[94],"from":[95],"the":[96],"Institute":[97],"Museum":[99],"Library":[101],"Services":[102],"Digital":[103],"Collections":[104],"Content":[106],"aggregation,":[107],"results":[108],"show":[109],"an":[110],"increase":[111],"coherence":[113],"among":[114],"words":[115],"topics.":[117],"showing":[119],"this,":[120],"demonstrate":[122],"it":[124],"may":[125],"be":[126],"beneficial":[127],"induce":[129],"less,":[133],"higher\u2010quality":[134],"data.":[135]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
