{"id":"https://openalex.org/W2141441158","doi":"https://doi.org/10.1145/1255175.1255249","title":"Organizing the OCA","display_name":"Organizing the OCA","publication_year":2007,"publication_date":"2007-06-18","ids":{"openalex":"https://openalex.org/W2141441158","doi":"https://doi.org/10.1145/1255175.1255249","mag":"2141441158"},"language":"en","primary_location":{"id":"doi:10.1145/1255175.1255249","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1255175.1255249","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM/IEEE-CS joint conference on Digital libraries","raw_type":"proceedings-article"},"type":"article","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/A5086934220","display_name":"David Mimno","orcid":"https://orcid.org/0000-0001-7510-9404"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Mimno","raw_affiliation_strings":["University of Massachusetts: Amherst, Amherst, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts: Amherst, Amherst, MA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008354502","display_name":"Andrew McCallum","orcid":"https://orcid.org/0000-0003-2843-6992"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew McCallum","raw_affiliation_strings":["University of Massachusetts: Amherst, Amherst, MA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts: Amherst, Amherst, MA","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":11.6256,"has_fulltext":false,"cited_by_count":79,"citation_normalized_percentile":{"value":0.98403568,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"376","last_page":"385"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9991000294685364,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9980000257492065,"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/computer-science","display_name":"Computer science","score":0.7909374237060547},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.7660089731216431},{"id":"https://openalex.org/keywords/digitization","display_name":"Digitization","score":0.6480899453163147},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6441817879676819},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.5908036231994629},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5674343109130859},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.5580670833587646},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.5121476650238037},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4866717457771301},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.46282464265823364},{"id":"https://openalex.org/keywords/multinomial-distribution","display_name":"Multinomial distribution","score":0.42291656136512756},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3980812430381775},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37420719861984253},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3392942547798157}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7909374237060547},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.7660089731216431},{"id":"https://openalex.org/C2779308522","wikidata":"https://www.wikidata.org/wiki/Q843958","display_name":"Digitization","level":2,"score":0.6480899453163147},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6441817879676819},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.5908036231994629},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5674343109130859},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.5580670833587646},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.5121476650238037},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4866717457771301},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.46282464265823364},{"id":"https://openalex.org/C192065140","wikidata":"https://www.wikidata.org/wiki/Q1147928","display_name":"Multinomial distribution","level":2,"score":0.42291656136512756},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3980812430381775},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37420719861984253},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3392942547798157},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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":"doi:10.1145/1255175.1255249","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1255175.1255249","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM/IEEE-CS joint conference on Digital libraries","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4699999988079071,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320311089","display_name":"National Security Agency","ror":"https://ror.org/0047bvr32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W53445681","https://openalex.org/W190008395","https://openalex.org/W1602031264","https://openalex.org/W1618045731","https://openalex.org/W1880262756","https://openalex.org/W2025653016","https://openalex.org/W2042980227","https://openalex.org/W2053606794","https://openalex.org/W2093390569","https://openalex.org/W2100163972","https://openalex.org/W2106447713","https://openalex.org/W2112247328","https://openalex.org/W2115376222","https://openalex.org/W2118722427","https://openalex.org/W2135631383","https://openalex.org/W2160586919","https://openalex.org/W2506392202","https://openalex.org/W2886815573","https://openalex.org/W6602187886"],"related_works":["https://openalex.org/W2888805565","https://openalex.org/W4312773271","https://openalex.org/W4315588616","https://openalex.org/W2769501189","https://openalex.org/W2962686197","https://openalex.org/W2207653751","https://openalex.org/W3159709618","https://openalex.org/W2611137333","https://openalex.org/W3005513013","https://openalex.org/W4389543811"],"abstract_inverted_index":{"Large":[0],"scale":[1,199],"library":[2],"digitization":[3],"projects":[4],"such":[5],"as":[6,147],"the":[7,128,154],"Open":[8],"Content":[9],"Alliance":[10],"are":[11,32,66],"producing":[12],"vast":[13],"quantities":[14],"of":[15,108,130,156,183],"text,":[16],"but":[17,34,73],"little":[18],"has":[19],"been":[20,76],"done":[21],"to":[22,71,80,104,113,152],"organize":[23],"this":[24,176],"data.":[25],"Subject":[26],"headings":[27],"inherited":[28],"from":[29,187],"card":[30],"catalogs":[31],"useful":[33],"limited,":[35],"while":[36],"full-text":[37],"indexing":[38],"is":[39,100],"most":[40],"appropriate":[41],"for":[42,123],"readers":[43,151],"who":[44],"already":[45],"know":[46],"exactly":[47],"what":[48],"they":[49,74],"want.":[50],"Statistical":[51],"topic":[52,90,121],"models":[53,59,122],"provide":[54],"a":[55,89,157,181],"complementary":[56],"function.":[57],"These":[58],"can":[60,144],"identify":[61],"semantically":[62],"coherent":[63],"\"topics\"":[64],"that":[65],"easily":[67,197],"recognizable":[68],"and":[69,110,168,195],"meaningful":[70],"humans,":[72],"have":[75],"too":[77],"computationally":[78],"intensive":[79],"run":[81],"on":[82,93,127,180],"library-scale":[83],"corpora.":[84],"This":[85,98],"paper":[86],"presents":[87],"DCM-LDA,":[88],"model":[91,99],"based":[92,126],"Dirichlet":[94],"Compound":[95],"Multinomial":[96],"distributions.":[97],"simultaneously":[101],"better":[102],"able":[103],"represent":[105],"observed":[106],"properties":[107],"text":[109,116],"more":[111],"scalable":[112],"extremely":[114],"large":[115],"collections.":[117],"We":[118,134,174],"train":[119],"individual":[120],"each":[124],"book":[125],"cooccurrence":[129],"words":[131,186],"within":[132],"pages.":[133],"then":[135],"cluster":[136],"topics":[137,155,179],"across":[138],"books.":[139,173],"The":[140],"resulting":[141],"topical":[142,170],"clusters":[143],"be":[145],"interpreted":[146],"subject":[148],"facets,":[149],"allowing":[150],"browse":[153],"collection":[158],"quickly,":[159],"find":[160],"relevant":[161],"books":[162,189],"using":[163],"topically":[164],"expanded":[165],"keyword":[166],"searches,":[167],"explore":[169],"relationships":[171],"between":[172],"demonstrate":[175],"method":[177],"finding":[178],"corpus":[182],"1.49":[184],"billion":[185],"42,000":[188],"in":[190],"less":[191],"than":[192],"20":[193],"hours,":[194],"it":[196],"could":[198],"well":[200],"beyond":[201],"this.":[202]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2016-06-24T00:00:00"}
