{"id":"https://openalex.org/W2088750139","doi":"https://doi.org/10.1145/502512.502534","title":"Discovering unexpected information from your competitors' web sites","display_name":"Discovering unexpected information from your competitors' web sites","publication_year":2001,"publication_date":"2001-08-26","ids":{"openalex":"https://openalex.org/W2088750139","doi":"https://doi.org/10.1145/502512.502534","mag":"2088750139"},"language":"en","primary_location":{"id":"doi:10.1145/502512.502534","is_oa":false,"landing_page_url":"https://doi.org/10.1145/502512.502534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining","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/A5100339927","display_name":"Bing Liu","orcid":"https://orcid.org/0000-0002-4096-6980"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Bing Liu","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore 117543","School of Computing, National University of Singapore, Singapore 117543,"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore 117543","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore 117543,","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077333251","display_name":"Yiming Ma","orcid":"https://orcid.org/0000-0003-2099-8077"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yiming Ma","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore 117543","School of Computing, National University of Singapore, Singapore 117543,"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore 117543","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore 117543,","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036357902","display_name":"Philip S. Yu","orcid":"https://orcid.org/0000-0002-3491-5968"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Philip S. Yu","raw_affiliation_strings":["IBM T. J. Watson Research Center, Yorktown Heights, NY","IBM -- T. J. Watson Research Center, Yorktown Heights, NY"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"IBM -- T. J. Watson Research Center, Yorktown Heights, NY","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100339927"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":19.2229,"has_fulltext":false,"cited_by_count":85,"citation_normalized_percentile":{"value":0.98927757,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"144","last_page":"153"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9997000098228455,"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":0.9997000098228455,"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/T11106","display_name":"Data Management and Algorithms","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9955999851226807,"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/competitor-analysis","display_name":"Competitor analysis","score":0.9617940187454224},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7699991464614868},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.587620735168457},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4583766460418701},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.13339832425117493},{"id":"https://openalex.org/keywords/marketing","display_name":"Marketing","score":0.06848651170730591}],"concepts":[{"id":"https://openalex.org/C127576917","wikidata":"https://www.wikidata.org/wiki/Q624630","display_name":"Competitor analysis","level":2,"score":0.9617940187454224},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7699991464614868},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.587620735168457},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4583766460418701},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.13339832425117493},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.06848651170730591}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/502512.502534","is_oa":false,"landing_page_url":"https://doi.org/10.1145/502512.502534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:scholarbank.nus.edu.sg:10635/40333","is_oa":false,"landing_page_url":"http://scholarbank.nus.edu.sg/handle/10635/40333","pdf_url":null,"source":{"id":"https://openalex.org/S7407052290","display_name":"National University of Singapore","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scopus","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W157477790","https://openalex.org/W1484413656","https://openalex.org/W1489992655","https://openalex.org/W1506285740","https://openalex.org/W1660390307","https://openalex.org/W1956559956","https://openalex.org/W1971954723","https://openalex.org/W1978394996","https://openalex.org/W1987777228","https://openalex.org/W1994301758","https://openalex.org/W2020423193","https://openalex.org/W2024114145","https://openalex.org/W2030406093","https://openalex.org/W2033709196","https://openalex.org/W2038281398","https://openalex.org/W2042970816","https://openalex.org/W2066636486","https://openalex.org/W2072881690","https://openalex.org/W2109272824","https://openalex.org/W2136500370","https://openalex.org/W2136663836","https://openalex.org/W2138621811","https://openalex.org/W2141115288","https://openalex.org/W2562755098","https://openalex.org/W3007065685"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2358804928","https://openalex.org/W4225710828","https://openalex.org/W1998528887","https://openalex.org/W2965538880","https://openalex.org/W2143282039","https://openalex.org/W2528370785","https://openalex.org/W4200335562","https://openalex.org/W2861933770"],"abstract_inverted_index":{"Ever":[0],"since":[1],"the":[2,5,11,38,68,105,121,155,173],"beginning":[3],"of":[4,53,58,123,125,169,178],"Web,":[6],"finding":[7],"useful":[8,74,82,194],"information":[9,24,35,54,72,89,180],"from":[10,109,181],"Web":[12,26,184],"has":[13],"been":[14],"an":[15],"important":[16],"problem.":[17],"Existing":[18],"approaches":[19,32],"include":[20],"keyword-based":[21],"search,":[22],"wrapper-based":[23],"extraction,":[25],"query":[27],"and":[28,96,133,197],"user":[29,148,174],"preferences.":[30],"These":[31],"essentially":[33],"find":[34,87,175],"that":[36,45,55,98,189],"matches":[37],"user's":[39],"explicit":[40],"specifications.":[41],"This":[42],"paper":[43],"argues":[44],"this":[46,103,163],"is":[47,50,56,65,73,81,130,142,160],"insufficient.":[48],"There":[49],"another":[51],"type":[52],"also":[57,136,198],"great":[59],"interest,":[60],"i.e.,":[61],"unexpected":[62,71,88,94,156,179],"information,":[63,104],"which":[64],"unanticipated":[66],"by":[67],"user.":[69],"Finding":[70],"in":[75,195],"many":[76,137],"applications.":[77],"For":[78],"example,":[79],"it":[80,141],"for":[83,145],"a":[84,126,146,167],"company":[85,106],"to":[86,116,149,153,171],"bout":[90],"its":[91,99,110,118],"competitors,":[92],"e.g.,":[93],"services":[95],"products":[97],"competitors":[100,111],"offer.":[101],"With":[102],"can":[107],"learn":[108],"and/or":[112],"design":[113],"counter":[114],"measures":[115],"improve":[117],"competitiveness.":[119],"Since":[120],"number":[122,168],"pages":[124],"typical":[127],"commercial":[128],"site":[129],"very":[131,143,193],"large":[132],"there":[134],"are":[135,192],"relevant":[138],"sites":[139],"(competitors),":[140],"difficult":[144],"human":[147],"view":[150],"each":[151],"page":[152],"discover":[154],"information.":[157],"Automated":[158],"assistance":[159],"needed.":[161],"In":[162],"paper,":[164],"we":[165],"propose":[166],"methods":[170],"help":[172],"various":[176],"types":[177],"his/her":[182],"competitors'":[183],"sites.":[185],"Experiment":[186],"results":[187],"show":[188],"these":[190],"techniques":[191],"practice":[196],"efficient.":[199]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
