{"id":"https://openalex.org/W2131150402","doi":"https://doi.org/10.14778/1687553.1687580","title":"Scalable web data extraction for online market intelligence","display_name":"Scalable web data extraction for online market intelligence","publication_year":2009,"publication_date":"2009-08-01","ids":{"openalex":"https://openalex.org/W2131150402","doi":"https://doi.org/10.14778/1687553.1687580","mag":"2131150402"},"language":"en","primary_location":{"id":"doi:10.14778/1687553.1687580","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1687553.1687580","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-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/A5055923468","display_name":"Robert Baumgartner","orcid":"https://orcid.org/0000-0003-0899-4903"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Robert Baumgartner","raw_affiliation_strings":["Lixto Software GmbH, Vienna, Austria"],"affiliations":[{"raw_affiliation_string":"Lixto Software GmbH, Vienna, Austria","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050151740","display_name":"Georg Gottlob","orcid":"https://orcid.org/0000-0002-2353-5230"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Georg Gottlob","raw_affiliation_strings":["Oxford University, Oxford, UK","Oxford University, Oxford, UK#TAB#"],"affiliations":[{"raw_affiliation_string":"Oxford University, Oxford, UK","institution_ids":["https://openalex.org/I40120149"]},{"raw_affiliation_string":"Oxford University, Oxford, UK#TAB#","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111482934","display_name":"Marcus Herzog","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marcus Herzog","raw_affiliation_strings":["Lixto Software GmbH, Vienna, Austria"],"affiliations":[{"raw_affiliation_string":"Lixto Software GmbH, Vienna, Austria","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5055923468"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":15.526,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.98796656,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"2","issue":"2","first_page":"1512","last_page":"1523"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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/T13976","display_name":"Web visibility and informetrics","score":0.9785000085830688,"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/T10742","display_name":"Peer-to-Peer Network Technologies","score":0.9750999808311462,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7807322144508362},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6834719181060791},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5984959602355957},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.5815161466598511},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5509690642356873},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.530713677406311},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4627407193183899},{"id":"https://openalex.org/keywords/data-warehouse","display_name":"Data warehouse","score":0.4483175277709961},{"id":"https://openalex.org/keywords/data-web","display_name":"Data Web","score":0.41317814588546753},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39518114924430847},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.37258124351501465},{"id":"https://openalex.org/keywords/web-service","display_name":"Web service","score":0.33680230379104614},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3208271563053131},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.239342600107193}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7807322144508362},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6834719181060791},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5984959602355957},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.5815161466598511},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5509690642356873},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.530713677406311},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4627407193183899},{"id":"https://openalex.org/C135572916","wikidata":"https://www.wikidata.org/wiki/Q193351","display_name":"Data warehouse","level":2,"score":0.4483175277709961},{"id":"https://openalex.org/C162005631","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Data Web","level":3,"score":0.41317814588546753},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39518114924430847},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.37258124351501465},{"id":"https://openalex.org/C35578498","wikidata":"https://www.wikidata.org/wiki/Q193424","display_name":"Web service","level":2,"score":0.33680230379104614},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3208271563053131},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.239342600107193},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.14778/1687553.1687580","is_oa":false,"landing_page_url":"https://doi.org/10.14778/1687553.1687580","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.151.4695","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.151.4695","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.vldb.org/pvldb/2/vldb09-1075.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":24,"referenced_works":["https://openalex.org/W11750719","https://openalex.org/W36024057","https://openalex.org/W1509288318","https://openalex.org/W1547917241","https://openalex.org/W1567298333","https://openalex.org/W1821155018","https://openalex.org/W1983736818","https://openalex.org/W2003304137","https://openalex.org/W2005646337","https://openalex.org/W2011027695","https://openalex.org/W2102189859","https://openalex.org/W2102218101","https://openalex.org/W2137235842","https://openalex.org/W2142809404","https://openalex.org/W2148210463","https://openalex.org/W2150035198","https://openalex.org/W2171574281","https://openalex.org/W3144770266","https://openalex.org/W6600454681","https://openalex.org/W6632840923","https://openalex.org/W6633884777","https://openalex.org/W6680366601","https://openalex.org/W6681973738","https://openalex.org/W6793280447"],"related_works":["https://openalex.org/W4287605407","https://openalex.org/W3097243301","https://openalex.org/W3171568351","https://openalex.org/W3180337491","https://openalex.org/W4200184607","https://openalex.org/W2080529815","https://openalex.org/W4214869855","https://openalex.org/W4324139823","https://openalex.org/W4233433221","https://openalex.org/W2549874377"],"abstract_inverted_index":{"Online":[0],"market":[1,92],"intelligence":[2,7,93],"(OMI),":[3],"in":[4,45,102,115],"particular":[5],"competitive":[6],"for":[8,17,134],"product":[9],"pricing,":[10],"is":[11,43,89,167],"a":[12,83,116,121,176],"very":[13],"important":[14],"application":[15],"area":[16],"Web":[18,75],"data":[19,27,41,61,71,81,84,88,114,124,157],"extraction.":[20],"However,":[21],"OMI":[22,132],"presents":[23],"non-trivial":[24],"challenges":[25,150],"to":[26,58,91,104,107],"extraction":[28,36,125,158],"technology.":[29],"Sophisticated":[30],"and":[31,35,66,77,109,127,153,182],"highly":[32,100],"parameterized":[33],"navigation":[34],"tasks":[37],"are":[38],"required.":[39],"On-the-fly":[40],"cleansing":[42],"necessary":[44],"order":[46,103],"two":[47],"identify":[48],"identical":[49],"products":[50],"from":[51,73,179],"different":[52],"suppliers.":[53],"It":[54],"must":[55,98],"be":[56,99,105],"possible":[57],"smoothly":[59],"define":[60],"flow":[62],"scenarios":[63],"that":[64],"merge":[65],"filter":[67],"streams":[68],"of":[69,113,147],"extracted":[70],"stemming":[72],"several":[74,135],"sites":[76],"store":[78],"the":[79,87,96,148,180],"resulting":[80],"into":[82],"warehouse,":[85],"where":[86],"subjected":[90],"analytics.":[94],"Finally,":[95],"system":[97],"scalable,":[101],"able":[106],"extract":[108],"process":[110],"massive":[111],"amounts":[112],"short":[117],"time.":[118],"Lixto":[119,143],"(www.lixto.com),":[120],"company":[122],"offering":[123],"tools":[126],"services,":[128],"has":[129,144],"been":[130],"providing":[131],"solutions":[133],"customers.":[136],"In":[137],"this":[138],"paper":[139,173],"we":[140,162],"show":[141,163],"how":[142,164],"tackled":[145],"each":[146],"above":[149],"by":[151],"improving":[152],"extending":[154],"its":[155],"original":[156],"software.":[159],"Most":[160],"importantly,":[161],"high":[165],"scalability":[166],"achieved":[168],"through":[169],"cloud":[170],"computing.":[171],"This":[172],"also":[174],"features":[175],"case":[177],"study":[178],"computers":[181],"electronics":[183],"market.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
