{"id":"https://openalex.org/W2112012331","doi":"https://doi.org/10.1145/1555400.1555405","title":"Topic model methods for automatically identifying out-of-scope resources","display_name":"Topic model methods for automatically identifying out-of-scope resources","publication_year":2009,"publication_date":"2009-06-15","ids":{"openalex":"https://openalex.org/W2112012331","doi":"https://doi.org/10.1145/1555400.1555405","mag":"2112012331"},"language":"en","primary_location":{"id":"doi:10.1145/1555400.1555405","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1555400.1555405","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th ACM/IEEE-CS joint conference on Digital libraries","raw_type":"proceedings-article"},"type":"conference-paper","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/A5068978543","display_name":"Steven Bethard","orcid":"https://orcid.org/0000-0001-9560-6491"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Steven Bethard","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077112143","display_name":"Soumya Ghosh","orcid":"https://orcid.org/0000-0001-8508-0641"},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Soumya Ghosh","raw_affiliation_strings":["University of Colorado, Boulder, CO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Colorado, Boulder, CO, USA","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010984350","display_name":"James Martin","orcid":"https://orcid.org/0000-0002-9654-3864"},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"James H. Martin","raw_affiliation_strings":["University of Colorado, Boulder, CO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Colorado, Boulder, CO, USA","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051906525","display_name":"Tamara Sumner","orcid":"https://orcid.org/0000-0002-8785-3238"},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tamara Sumner","raw_affiliation_strings":["University of Colorado, Boulder, CO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Colorado, Boulder, CO, USA","institution_ids":["https://openalex.org/I188538660"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2437,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.49262254,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"2008","issue":null,"first_page":"19","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9890999794006348,"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":0.9890999794006348,"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":0.9868000149726868,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9861000180244446,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.9069428443908691},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8513533473014832},{"id":"https://openalex.org/keywords/digital-library","display_name":"Digital library","score":0.7136287093162537},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.6458243727684021},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6285120248794556},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5939823389053345},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.5120061039924622},{"id":"https://openalex.org/keywords/theme","display_name":"Theme (computing)","score":0.5083824992179871},{"id":"https://openalex.org/keywords/subject","display_name":"Subject (documents)","score":0.4801296889781952},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4436846971511841},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.41879069805145264},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41244417428970337},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.12210538983345032}],"concepts":[{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.9069428443908691},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8513533473014832},{"id":"https://openalex.org/C513874922","wikidata":"https://www.wikidata.org/wiki/Q212805","display_name":"Digital library","level":3,"score":0.7136287093162537},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.6458243727684021},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6285120248794556},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5939823389053345},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.5120061039924622},{"id":"https://openalex.org/C33566652","wikidata":"https://www.wikidata.org/wiki/Q1065927","display_name":"Theme (computing)","level":2,"score":0.5083824992179871},{"id":"https://openalex.org/C2777855551","wikidata":"https://www.wikidata.org/wiki/Q12310021","display_name":"Subject (documents)","level":2,"score":0.4801296889781952},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4436846971511841},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.41879069805145264},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41244417428970337},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.12210538983345032},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C164913051","wikidata":"https://www.wikidata.org/wiki/Q482","display_name":"Poetry","level":2,"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":1,"locations":[{"id":"doi:10.1145/1555400.1555405","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1555400.1555405","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 9th 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":0.8600000143051147,"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/F4320332167","display_name":"Directorate for Biological Sciences","ror":"https://ror.org/001xhss06"},{"id":"https://openalex.org/F4320337389","display_name":"Division of Information and Intelligent Systems","ror":"https://ror.org/053a2cp42"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W132466238","https://openalex.org/W167522204","https://openalex.org/W171478201","https://openalex.org/W1540550673","https://openalex.org/W1557561175","https://openalex.org/W1584013643","https://openalex.org/W1597939937","https://openalex.org/W1604792744","https://openalex.org/W1880262756","https://openalex.org/W1902027874","https://openalex.org/W1941537533","https://openalex.org/W2020959717","https://openalex.org/W2039429473","https://openalex.org/W2070771761","https://openalex.org/W2075858744","https://openalex.org/W2087021579","https://openalex.org/W2094595236","https://openalex.org/W2098062695","https://openalex.org/W2105895401","https://openalex.org/W2118020653","https://openalex.org/W2118722427","https://openalex.org/W2119079505","https://openalex.org/W2122329662","https://openalex.org/W2122384383","https://openalex.org/W2122520221","https://openalex.org/W2124998943","https://openalex.org/W2129279762","https://openalex.org/W2135029798","https://openalex.org/W2141441158","https://openalex.org/W2146128929","https://openalex.org/W2150102617","https://openalex.org/W2169384781","https://openalex.org/W2170934897","https://openalex.org/W2231216812","https://openalex.org/W2334889010","https://openalex.org/W2399746551","https://openalex.org/W2886815573","https://openalex.org/W2990138404","https://openalex.org/W6672500095","https://openalex.org/W6674735981","https://openalex.org/W6680012447","https://openalex.org/W6703074907"],"related_works":["https://openalex.org/W2000785801","https://openalex.org/W986318368","https://openalex.org/W2384410913","https://openalex.org/W2352878646","https://openalex.org/W2004734601","https://openalex.org/W2130149817","https://openalex.org/W2990194547","https://openalex.org/W1480123525","https://openalex.org/W2620865396","https://openalex.org/W2414054180"],"abstract_inverted_index":{"Recent":[0],"years":[1],"have":[2],"seen":[3],"the":[4,12,16,39,42,84,152,157,165],"rise":[5],"of":[6,41,56,77,144,159],"subject-themed":[7],"digital":[8,89,160],"libraries,":[9],"such":[10,47],"as":[11,151],"NSDL":[13],"pathways":[14],"and":[15,60,83,116,162],"Digital":[17],"Library":[18],"for":[19,88],"Earth":[20],"System":[21],"Education":[22],"(DLESE).":[23],"These":[24],"libraries":[25,90,161],"often":[26],"need":[27],"to":[28,112,130,168],"manually":[29],"verify":[30],"that":[31,36,46,133,139],"contributed":[32],"resources":[33,79,132,138],"cover":[34],"topics":[35,118],"fit":[37],"within":[38],"theme":[40],"library.":[43],"We":[44,147],"show":[45],"scope":[48,71],"judgments":[49],"can":[50],"be":[51],"automated":[52],"using":[53],"a":[54,74],"combination":[55],"text":[57,97],"classification":[58,98],"techniques":[59],"topic":[61,85,123],"modeling.":[62],"Our":[63,125],"models":[64,105,150],"address":[65],"two":[66],"significant":[67],"challenges":[68],"in":[69,135],"making":[70],"judgments:":[72],"only":[73],"small":[75],"number":[76],"out-of-scope":[78],"are":[80,91],"typically":[81],"available,":[82],"distinctions":[86],"required":[87,167],"much":[92],"more":[93],"subtle":[94],"than":[95],"classic":[96],"problems.":[99],"To":[100],"meet":[101],"these":[102,149],"challenges,":[103],"our":[104],"combine":[106],"support":[107],"vector":[108],"machine":[109],"learners":[110],"optimized":[111],"different":[113],"performance":[114],"metrics":[115],"semantic":[117],"induced":[119],"by":[120],"unsupervised":[121],"statistical":[122],"models.":[124],"best":[126],"model":[127],"is":[128],"able":[129],"distinguish":[131],"belong":[134],"DLESE":[136],"from":[137],"don't":[140],"with":[141],"an":[142],"accuracy":[143],"around":[145],"70%.":[146],"see":[148],"first":[153],"steps":[154],"towards":[155],"increasing":[156],"scalability":[158],"dramatically":[163],"reducing":[164],"workload":[166],"maintain":[169],"them.":[170]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}