{"id":"https://openalex.org/W2083563309","doi":"https://doi.org/10.1145/1871437.1871447","title":"Automatic extraction of web data records containing user-generated content","display_name":"Automatic extraction of web data records containing user-generated content","publication_year":2010,"publication_date":"2010-10-26","ids":{"openalex":"https://openalex.org/W2083563309","doi":"https://doi.org/10.1145/1871437.1871447","mag":"2083563309"},"language":"en","primary_location":{"id":"doi:10.1145/1871437.1871447","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1871437.1871447","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"},"type":"conference-paper","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/A5102246878","display_name":"Xinying Song","orcid":"https://orcid.org/0009-0002-9445-0717"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinying Song","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China","Harbin Institute of Technology Harbin, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology Harbin, China#TAB#","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375136","display_name":"Jing Liu","orcid":"https://orcid.org/0000-0003-4690-1886"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Liu","raw_affiliation_strings":["Harbin Institute of Technology, Harbin, China","Harbin Institute of Technology Harbin, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology, Harbin, China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"Harbin Institute of Technology Harbin, China#TAB#","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011542448","display_name":"Yunbo Cao","orcid":"https://orcid.org/0009-0005-2558-5206"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunbo Cao","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090151187","display_name":"Chin-Yew Lin","orcid":"https://orcid.org/0000-0002-0798-6365"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chin-Yew Lin","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109215896","display_name":"Hsiao-Wuen Hon","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hsiao-Wuen Hon","raw_affiliation_strings":["Microsoft Research Asia, Beijing, China","Microsoft research Asia, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft research Asia, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"39","last_page":"48"},"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/T11550","display_name":"Text and Document Classification Technologies","score":0.973800003528595,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9732000231742859,"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":0.8241379261016846},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.607596755027771},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5287296772003174},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5255459547042847},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.49518147110939026},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4640367031097412},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.45461001992225647},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4212256073951721},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3874626159667969},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21860048174858093},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08085179328918457}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8241379261016846},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.607596755027771},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5287296772003174},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5255459547042847},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.49518147110939026},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4640367031097412},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.45461001992225647},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4212256073951721},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3874626159667969},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21860048174858093},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08085179328918457},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1871437.1871447","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1871437.1871447","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th ACM international conference on Information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1515087027","https://openalex.org/W1519606823","https://openalex.org/W1973483159","https://openalex.org/W1973763998","https://openalex.org/W1975009259","https://openalex.org/W2005646337","https://openalex.org/W2015551056","https://openalex.org/W2023094000","https://openalex.org/W2048001624","https://openalex.org/W2049461910","https://openalex.org/W2069388662","https://openalex.org/W2104086170","https://openalex.org/W2121751007","https://openalex.org/W2128341918","https://openalex.org/W2128836931","https://openalex.org/W2129595335","https://openalex.org/W2132022450","https://openalex.org/W2133669904","https://openalex.org/W2134150392","https://openalex.org/W2143309843","https://openalex.org/W2150721933","https://openalex.org/W2154445423","https://openalex.org/W2160196229","https://openalex.org/W2160660844","https://openalex.org/W2166407869","https://openalex.org/W2171364811","https://openalex.org/W2519011775","https://openalex.org/W4233527139"],"related_works":["https://openalex.org/W2611741382","https://openalex.org/W2375480909","https://openalex.org/W3135843367","https://openalex.org/W2353314428","https://openalex.org/W2613685774","https://openalex.org/W3112355890","https://openalex.org/W2012019886","https://openalex.org/W2166090428","https://openalex.org/W2327130486","https://openalex.org/W2387801216"],"abstract_inverted_index":{"In":[0,20,75,101],"this":[1],"paper,":[2],"we":[3,78,103],"are":[4,26,145],"concerned":[5],"with":[6,32,169],"the":[7,61,97,110,115],"problem":[8],"of":[9,36,58,95,99,140,162,167,182],"automatically":[10],"extracting":[11,185],"web":[12,23,51],"data":[13,24,52,126],"records":[14,25,65,127],"that":[15,80,150],"contain":[16],"user-generated":[17],"content":[18],"(UGC).":[19],"previous":[21],"work,":[22,77],"usually":[27],"assumed":[28],"to":[29,89,113,171,199],"be":[30,41,87],"well-formed":[31],"a":[33,50,55,137,160,165],"limited":[34],"amount":[35],"UGC,":[37,60],"and":[38,164,202],"thus":[39],"can":[40,86],"extracted":[42],"by":[43,109],"testing":[44],"repetitive":[45],"structure":[46],"similarity.":[47],"However,":[48],"when":[49],"record":[53,173],"includes":[54],"large":[56],"portion":[57],"free-format":[59],"similarity":[62,92],"test":[63],"between":[64],"may":[66],"fail,":[67],"which":[68,118,144],"in":[69,72,120],"turn":[70],"results":[71,205],"lower":[73],"performance.":[74],"our":[76,197],"find":[79],"certain":[81],"domain":[82,111],"constraints":[83,112],"(e.g.,":[84],"post-date)":[85],"used":[88],"design":[90],"better":[91],"measures":[93],"capable":[94],"circumventing":[96],"influence":[98],"UGC.":[100],"addition,":[102],"also":[104,195],"use":[105],"anchor":[106],"points":[107],"provided":[108],"improve":[114],"extraction":[116,201],"process,":[117],"ends":[119],"an":[121],"algorithm":[122],"called":[123],"MiBAT":[124],"(Mining":[125],"Based":[128],"on":[129,136],"Anchor":[130],"Trees).":[131],"We":[132,194],"conduct":[133],"extensive":[134],"experiments":[135],"dataset":[138],"consisting":[139],"forum":[141,154],"thread":[142],"pages":[143,183],"collected":[146],"from":[147],"307":[148],"sites":[149],"cover":[151],"219":[152],"different":[153],"software":[155],"packages.":[156],"Our":[157],"approach":[158,198],"achieves":[159],"precision":[161],"98.9%":[163],"recall":[166],"97.3%":[168],"respect":[170],"post":[172],"extraction.":[174],"On":[175],"page":[176],"level,":[177],"it":[178],"perfectly":[179],"handles":[180],"91.7%":[181],"without":[184],"any":[186,191],"wrong":[187],"posts":[188],"or":[189],"missing":[190],"golden":[192],"posts.":[193],"apply":[196],"comment":[200],"achieve":[203],"good":[204],"as":[206],"well.":[207]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":4}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}