{"id":"https://openalex.org/W2015159801","doi":"https://doi.org/10.1109/icde.2008.4497600","title":"Quality-Aware Retrieval of Data Objects from Autonomous Sources for Web-Based Repositories","display_name":"Quality-Aware Retrieval of Data Objects from Autonomous Sources for Web-Based Repositories","publication_year":2008,"publication_date":"2008-04-01","ids":{"openalex":"https://openalex.org/W2015159801","doi":"https://doi.org/10.1109/icde.2008.4497600","mag":"2015159801"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2008.4497600","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2008.4497600","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE 24th International Conference on Data Engineering","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/A5089245564","display_name":"Houtan Shirani-Mehr","orcid":null},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Houtan Shirani-Mehr","raw_affiliation_strings":["Department of Information and Computer Science, University of California, Irvine, CA, USA","Department of Information and Computer Science, University of California, Irvine, Ca"],"affiliations":[{"raw_affiliation_string":"Department of Information and Computer Science, University of California, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]},{"raw_affiliation_string":"Department of Information and Computer Science, University of California, Irvine, Ca","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100369885","display_name":"Chen Li","orcid":"https://orcid.org/0000-0002-8784-8148"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Li","raw_affiliation_strings":["Department of Information and Computer Science, University of California, Irvine, CA, USA","Department of Information and Computer Science, University of California, Irvine, Irvine, CA 92697, USA. chenli@uci.edu"],"affiliations":[{"raw_affiliation_string":"Department of Information and Computer Science, University of California, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]},{"raw_affiliation_string":"Department of Information and Computer Science, University of California, Irvine, Irvine, CA 92697, USA. chenli@uci.edu","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100512909","display_name":"Liang Gang","orcid":null},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gang Liang","raw_affiliation_strings":["Department of Information and Computer Science, University of California, Irvine, CA, USA","Department of Information and Computer Science, University of California, Irvine, Irvine, CA 92697, USA. liang@uci.edu"],"affiliations":[{"raw_affiliation_string":"Department of Information and Computer Science, University of California, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]},{"raw_affiliation_string":"Department of Information and Computer Science, University of California, Irvine, Irvine, CA 92697, USA. liang@uci.edu","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051536706","display_name":"Michal Shmueli-Scheuer","orcid":"https://orcid.org/0000-0002-6386-8726"},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michal Shmueli-Scheuer","raw_affiliation_strings":["Department of Information and Computer Science, University of California, Irvine, CA, USA","Department of Information and Computer Science, University of California, Irvine, Irvine, CA 92697, USA. mshmueli@uci.edu#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Information and Computer Science, University of California, Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]},{"raw_affiliation_string":"Department of Information and Computer Science, University of California, Irvine, Irvine, CA 92697, USA. mshmueli@uci.edu#TAB#","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5089245564"],"corresponding_institution_ids":["https://openalex.org/I204250578"],"apc_list":null,"apc_paid":null,"fwci":0.8748,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.83866418,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1492","last_page":"1494"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994999766349792,"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":0.9994999766349792,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9976000189781189,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.984499990940094,"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":0.80557781457901},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.6388013958930969},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5320179462432861},{"id":"https://openalex.org/keywords/theme","display_name":"Theme (computing)","score":0.4983561038970947},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4907115697860718},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3793914020061493}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.80557781457901},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.6388013958930969},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5320179462432861},{"id":"https://openalex.org/C33566652","wikidata":"https://www.wikidata.org/wiki/Q1065927","display_name":"Theme (computing)","level":2,"score":0.4983561038970947},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4907115697860718},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3793914020061493},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icde.2008.4497600","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2008.4497600","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE 24th International Conference on Data Engineering","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.144.7663","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.144.7663","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ics.uci.edu/~chenli/pub/icde08-crawling.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1987272746","https://openalex.org/W2069508080","https://openalex.org/W2120176508","https://openalex.org/W2140971281","https://openalex.org/W2171515720","https://openalex.org/W2313953460","https://openalex.org/W2481970566","https://openalex.org/W4206316875","https://openalex.org/W4251434705","https://openalex.org/W4292963524"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W1876039949","https://openalex.org/W2351167057","https://openalex.org/W570509144","https://openalex.org/W2356772582","https://openalex.org/W1499778516","https://openalex.org/W4200264008","https://openalex.org/W2739095861","https://openalex.org/W1992606257","https://openalex.org/W2356359262"],"abstract_inverted_index":{"The":[0,18],"goal":[1],"of":[2,21,57],"this":[3],"paper":[4],"is":[5,24],"to":[6,25,29,39,53],"develop":[7],"a":[8,55],"framework":[9],"for":[10,15],"designing":[11],"good":[12],"data":[13],"repositories":[14],"Web":[16],"applications.":[17],"central":[19],"theme":[20],"our":[22],"approach":[23],"employ":[26],"statistical":[27],"methods":[28],"predict":[30],"quality":[31,56],"metrics.":[32],"These":[33],"prediction":[34],"quantities":[35],"can":[36],"be":[37,51],"used":[38],"answer":[40],"important":[41],"questions":[42],"such":[43],"as:":[44],"How":[45],"soon":[46],"should":[47],"the":[48,67,83],"local":[49,68],"repository":[50,69],"synchronized":[52,71],"have":[54,79],"at":[58,82],"least":[59],"90%":[60],"precision":[61],"with":[62],"certain":[63],"confidence":[64],"level?":[65],"Suppose":[66],"was":[70],"three":[72],"days":[73],"ago,":[74],"how":[75],"many":[76],"objects":[77],"could":[78],"been":[80],"deleted":[81],"remote":[84],"source":[85],"since":[86],"then?":[87]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
