{"id":"https://openalex.org/W2115701094","doi":"https://doi.org/10.1145/1148170.1148230","title":"Distributed query sampling","display_name":"Distributed query sampling","publication_year":2006,"publication_date":"2006-08-06","ids":{"openalex":"https://openalex.org/W2115701094","doi":"https://doi.org/10.1145/1148170.1148230","mag":"2115701094"},"language":"en","primary_location":{"id":"doi:10.1145/1148170.1148230","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1148170.1148230","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th 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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048489384","display_name":"James Caverlee","orcid":"https://orcid.org/0000-0001-8350-8528"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"James Caverlee","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA","Georgia Institute of Technology Atlanta, GA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology Atlanta, GA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343991","display_name":"Ling Liu","orcid":"https://orcid.org/0000-0002-4138-3082"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ling Liu","raw_affiliation_strings":["Georgia Institute of Technology, Atlanta, GA","Georgia Institute of Technology Atlanta, GA"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology, Atlanta, GA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Georgia Institute of Technology Atlanta, GA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103345105","display_name":"Joonsoo Bae","orcid":null},"institutions":[{"id":"https://openalex.org/I80611190","display_name":"Jeonbuk National University","ror":"https://ror.org/05q92br09","country_code":"KR","type":"education","lineage":["https://openalex.org/I80611190"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joonsoo Bae","raw_affiliation_strings":["Chonbuk National University, Jeonju, Jeonbuk, South Korea"],"affiliations":[{"raw_affiliation_string":"Chonbuk National University, Jeonju, Jeonbuk, South Korea","institution_ids":["https://openalex.org/I80611190"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5048489384"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":6.895,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.96341303,"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":"340","last_page":"347"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9986000061035156,"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"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9986000061035156,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9950000047683716,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9929999709129333,"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/sampling","display_name":"Sampling (signal processing)","score":0.8324152827262878},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8308882117271423},{"id":"https://openalex.org/keywords/adaptive-sampling","display_name":"Adaptive sampling","score":0.7388049364089966},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5849446654319763},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5640968084335327},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5548356175422668},{"id":"https://openalex.org/keywords/query-optimization","display_name":"Query optimization","score":0.4983210563659668},{"id":"https://openalex.org/keywords/distributed-database","display_name":"Distributed database","score":0.4115641713142395},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.38038238883018494},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3379341661930084},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.15229180455207825},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10542744398117065},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.07034450769424438}],"concepts":[{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.8324152827262878},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8308882117271423},{"id":"https://openalex.org/C2781395549","wikidata":"https://www.wikidata.org/wiki/Q4680762","display_name":"Adaptive sampling","level":3,"score":0.7388049364089966},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5849446654319763},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5640968084335327},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5548356175422668},{"id":"https://openalex.org/C157692150","wikidata":"https://www.wikidata.org/wiki/Q2919848","display_name":"Query optimization","level":2,"score":0.4983210563659668},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.4115641713142395},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.38038238883018494},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3379341661930084},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15229180455207825},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10542744398117065},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.07034450769424438},{"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/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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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":2,"locations":[{"id":"doi:10.1145/1148170.1148230","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1148170.1148230","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.90.3007","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.90.3007","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://faculty.cs.tamu.edu/caverlee/pubs/caverlee06distributed.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.5899999737739563}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W335656077","https://openalex.org/W1564059483","https://openalex.org/W1586176254","https://openalex.org/W1660390307","https://openalex.org/W1985483915","https://openalex.org/W1986828474","https://openalex.org/W1992053235","https://openalex.org/W2002682102","https://openalex.org/W2012426233","https://openalex.org/W2013905639","https://openalex.org/W2029911720","https://openalex.org/W2037320173","https://openalex.org/W2059344928","https://openalex.org/W2060088491","https://openalex.org/W2061973112","https://openalex.org/W2081948558","https://openalex.org/W2086253379","https://openalex.org/W2091777463","https://openalex.org/W2096565380","https://openalex.org/W2098162425","https://openalex.org/W2112276485","https://openalex.org/W2116908444","https://openalex.org/W2137845970","https://openalex.org/W2146950091","https://openalex.org/W2152766222","https://openalex.org/W2170188121","https://openalex.org/W2170205495","https://openalex.org/W2221553715","https://openalex.org/W4247346926","https://openalex.org/W4255459561","https://openalex.org/W4285719527","https://openalex.org/W6635193281","https://openalex.org/W6637101025","https://openalex.org/W6682602269","https://openalex.org/W6685116542"],"related_works":["https://openalex.org/W2038693912","https://openalex.org/W1991602789","https://openalex.org/W1582396021","https://openalex.org/W2189039295","https://openalex.org/W1988359706","https://openalex.org/W312558119","https://openalex.org/W4210985407","https://openalex.org/W2123323016","https://openalex.org/W2335441444","https://openalex.org/W138014004"],"abstract_inverted_index":{"We":[0,85],"present":[1],"an":[2,24],"adaptive":[3,64],"distributed":[4],"query-sampling":[5],"framework":[6,17,67,103],"that":[7,100],"is":[8,42,68],"quality-conscious":[9,88],"for":[10,91],"extracting":[11],"high-quality":[12],"text":[13,81],"database":[14,48,93],"samples.":[15],"The":[16,59],"divides":[18],"the":[19,36,39,55,76,101],"query-based":[20,65],"sampling":[21,27,33,40,57,66,89,107],"process":[22,41],"into":[23],"initial":[25,97],"seed":[26],"phase":[28,38],"and":[29,50,71,95],"a":[30],"quality-aware":[31],"iterative":[32],"phase.":[34],"In":[35],"second":[37],"dynamically":[43],"scheduled":[44],"based":[45,74],"on":[46,75],"estimated":[47],"size":[49],"quality":[51,78],"parameters":[52],"derived":[53],"during":[54],"previous":[56],"process.":[58],"unique":[60],"characteristic":[61],"of":[62,79],"our":[63,96],"its":[69],"self-learning":[70],"self-configuring":[72],"ability":[73],"overall":[77],"all":[80],"databases":[82],"under":[83],"consideration.":[84],"introduce":[86],"three":[87],"schemes":[90],"estimating":[92],"quality,":[94],"results":[98],"show":[99],"proposed":[102],"supports":[104],"higher-quality":[105],"document":[106],"than":[108],"existing":[109],"approaches.":[110]},"counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}