{"id":"https://openalex.org/W2161022460","doi":"https://doi.org/10.1145/1277741.1277828","title":"Evaluating sampling methods for uncooperative collections","display_name":"Evaluating sampling methods for uncooperative collections","publication_year":2007,"publication_date":"2007-07-23","ids":{"openalex":"https://openalex.org/W2161022460","doi":"https://doi.org/10.1145/1277741.1277828","mag":"2161022460"},"language":"en","primary_location":{"id":"doi:10.1145/1277741.1277828","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1277741.1277828","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://openresearch-repository.anu.edu.au/bitstreams/7dfe6630-26cb-41ac-9fa0-34777a794af3/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046377370","display_name":"Paul Thomas","orcid":"https://orcid.org/0000-0003-2425-3136"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Paul Thomas","raw_affiliation_strings":["Australian National University, Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032211209","display_name":"David Hawking","orcid":"https://orcid.org/0000-0002-3704-5398"},"institutions":[{"id":"https://openalex.org/I1292875679","display_name":"Commonwealth Scientific and Industrial Research Organisation","ror":"https://ror.org/03qn8fb07","country_code":"AU","type":"funder","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"David Hawking","raw_affiliation_strings":["CSIRO ICT Centre, Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"CSIRO ICT Centre, Canberra, Australia","institution_ids":["https://openalex.org/I1292875679"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5046377370"],"corresponding_institution_ids":["https://openalex.org/I118347636"],"apc_list":null,"apc_paid":null,"fwci":6.7359,"has_fulltext":true,"cited_by_count":29,"citation_normalized_percentile":{"value":0.96983705,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"503","last_page":"510"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11478","display_name":"Caching and Content Delivery","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9966999888420105,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9961000084877014,"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/computer-science","display_name":"Computer science","score":0.8478598594665527},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.7471797466278076},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7361950874328613},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6451812386512756},{"id":"https://openalex.org/keywords/metasearch-engine","display_name":"Metasearch engine","score":0.5704376697540283},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.5696607232093811},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5279442667961121},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4718727469444275},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.33192288875579834},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.28141719102859497},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.14696228504180908}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8478598594665527},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.7471797466278076},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7361950874328613},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6451812386512756},{"id":"https://openalex.org/C173979980","wikidata":"https://www.wikidata.org/wiki/Q114106","display_name":"Metasearch engine","level":4,"score":0.5704376697540283},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.5696607232093811},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5279442667961121},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4718727469444275},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.33192288875579834},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.28141719102859497},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.14696228504180908},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1277741.1277828","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1277741.1277828","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:openresearch-repository.anu.edu.au:1885/36567","is_oa":true,"landing_page_url":"http://hdl.handle.net/1885/36567","pdf_url":"https://openresearch-repository.anu.edu.au/bitstreams/7dfe6630-26cb-41ac-9fa0-34777a794af3/download","source":{"id":"https://openalex.org/S4306402539","display_name":"ANU Open Research (Australian National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I118347636","host_organization_name":"Australian National University","host_organization_lineage":["https://openalex.org/I118347636"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"Conference paper"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.68.9067","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.68.9067","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://es.csiro.au/pubs/fp347-thomas.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:openresearch-repository.anu.edu.au:1885/36567","is_oa":true,"landing_page_url":"http://hdl.handle.net/1885/36567","pdf_url":"https://openresearch-repository.anu.edu.au/bitstreams/7dfe6630-26cb-41ac-9fa0-34777a794af3/download","source":{"id":"https://openalex.org/S4306402539","display_name":"ANU Open Research (Australian National University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I118347636","host_organization_name":"Australian National University","host_organization_lineage":["https://openalex.org/I118347636"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval","raw_type":"Conference paper"},"sustainable_development_goals":[{"score":0.49000000953674316,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2161022460.pdf","grobid_xml":"https://content.openalex.org/works/W2161022460.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W34395446","https://openalex.org/W1510634602","https://openalex.org/W1604437383","https://openalex.org/W1605217017","https://openalex.org/W1970173714","https://openalex.org/W1983416950","https://openalex.org/W1990388042","https://openalex.org/W2002682102","https://openalex.org/W2037320173","https://openalex.org/W2060088491","https://openalex.org/W2080676333","https://openalex.org/W2086253379","https://openalex.org/W2128941908","https://openalex.org/W2154707336","https://openalex.org/W2155711776","https://openalex.org/W4255459561","https://openalex.org/W6601400317"],"related_works":["https://openalex.org/W193889389","https://openalex.org/W2060088491","https://openalex.org/W4233958997","https://openalex.org/W4206551437","https://openalex.org/W2603671530","https://openalex.org/W1610765524","https://openalex.org/W2023370952","https://openalex.org/W2885550273","https://openalex.org/W2010034309","https://openalex.org/W2143079043"],"abstract_inverted_index":{"Many":[0],"server":[1],"selection":[2],"methods":[3,34,51],"suitable":[4],"for":[5,68],"distributed":[6],"information":[7],"retrieval":[8],"applications":[9],"rely,":[10],"in":[11,77],"the":[12,17,25,39,44,107],"absence":[13],"of":[14,19,22,32,43,55,58,90,103],"cooperation,":[15],"on":[16,38,52],"availability":[18],"unbiased":[20],"samples":[21,102],"documents":[23],"from":[24],"constituent":[26],"collections.":[27],"We":[28,48],"describe":[29],"a":[30,53,59,94],"number":[31,54],"sampling":[33,96],"which":[35,100],"depend":[36],"only":[37],"normal":[40],"query-response":[41],"mechanism":[42],"applicable":[45],"search":[46],"facilities.":[47],"evaluate":[49],"these":[50,80],"collections":[56],"typical":[57],"personal":[60],"metasearch":[61],"application.":[62],"Results":[63],"demonstrate":[64],"that":[65,76],"biases":[66,81],"exist":[67],"all":[69],"methods,":[70],"particularly":[71],"toward":[72],"longer":[73],"documents,":[74],"and":[75],"some":[78],"cases":[79],"can":[82],"be":[83],"reduced":[84,114],"but":[85,111],"not":[86],"eliminated":[87],"by":[88],"choice":[89],"parameters.We":[91],"also":[92],"introduce":[93],"new":[95],"technique,":[97],"\"multiple":[98],"queries\",":[99],"produces":[101],"similar":[104],"quality":[105],"to":[106],"best":[108],"current":[109],"techniques":[110],"with":[112],"significantly":[113],"cost.":[115]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
