{"id":"https://openalex.org/W2017231497","doi":"https://doi.org/10.1145/2396761.2398647","title":"An unsupervised method for author extraction from web pages containing user-generated content","display_name":"An unsupervised method for author extraction from web pages containing user-generated content","publication_year":2012,"publication_date":"2012-10-29","ids":{"openalex":"https://openalex.org/W2017231497","doi":"https://doi.org/10.1145/2396761.2398647","mag":"2017231497"},"language":"en","primary_location":{"id":"doi:10.1145/2396761.2398647","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2396761.2398647","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st 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/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/A5102246878","display_name":"Xinying Song","orcid":"https://orcid.org/0009-0002-9445-0717"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinying Song","raw_affiliation_strings":["Microsoft Research, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040999303","display_name":"Jingtian Jiang","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":"Jingtian Jiang","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/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"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2387","last_page":"2390"},"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/T11719","display_name":"Data Quality and Management","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10286","display_name":"Information Retrieval and Search Behavior","score":0.992900013923645,"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/computer-science","display_name":"Computer science","score":0.8280611038208008},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7137430906295776},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6714133024215698},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.614228367805481},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5770268440246582},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.4630603492259979},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.444919228553772},{"id":"https://openalex.org/keywords/user-generated-content","display_name":"User-generated content","score":0.44417035579681396},{"id":"https://openalex.org/keywords/f1-score","display_name":"F1 score","score":0.41977035999298096},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41966167092323303},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.36890536546707153},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.2394610047340393},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06773257255554199}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8280611038208008},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7137430906295776},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6714133024215698},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.614228367805481},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5770268440246582},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.4630603492259979},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.444919228553772},{"id":"https://openalex.org/C101293273","wikidata":"https://www.wikidata.org/wiki/Q579716","display_name":"User-generated content","level":3,"score":0.44417035579681396},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.41977035999298096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41966167092323303},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.36890536546707153},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.2394610047340393},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06773257255554199},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2396761.2398647","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2396761.2398647","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st 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":13,"referenced_works":["https://openalex.org/W1601308271","https://openalex.org/W1973483159","https://openalex.org/W2008733342","https://openalex.org/W2021314079","https://openalex.org/W2029331575","https://openalex.org/W2083563309","https://openalex.org/W2101580881","https://openalex.org/W2113889316","https://openalex.org/W2143309843","https://openalex.org/W2145833060","https://openalex.org/W2153635508","https://openalex.org/W2154445423","https://openalex.org/W2158551114"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2358755282","https://openalex.org/W2625833328","https://openalex.org/W36911888","https://openalex.org/W4385731361","https://openalex.org/W2489933339"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"address":[4],"the":[5,163],"problem":[6],"of":[7,52,99,114,130,165],"author":[8,53,117],"extraction":[9],"(AE)":[10],"from":[11,82,93,103,172],"user":[12],"generated":[13],"content":[14],"(UGC)":[15],"pages.":[16,106],"Most":[17],"existing":[18],"solutions":[19],"for":[20,40],"web":[21],"information":[22],"extraction,":[23],"including":[24],"AE,":[25],"adopt":[26],"supervised":[27,137],"approaches,":[28],"which":[29,132],"require":[30],"expensive":[31],"manual":[32],"annotation.":[33],"We":[34,107,160],"propose":[35],"a":[36,60,94,135,148],"novel":[37],"unsupervised":[38],"approach":[39,138,167],"automatically":[41,115],"collecting":[42],"and":[43,146,174,177],"labeling":[44],"training":[45],"data":[46,119],"based":[47],"on":[48,101,168],"two":[49],"key":[50],"observations":[51],"names:":[54],"(1)":[55,111],"people":[56,72],"tend":[57,73],"to":[58,74,78,151],"use":[59],"single":[61,95,140],"name":[62],"across":[63],"sites":[64],"if":[65],"their":[66],"preferred":[67],"names":[68],"are":[69],"available;":[70],"(2)":[71,123],"create":[75],"unique":[76],"usernames":[77],"easily":[79],"distinguish":[80],"themselves":[81],"others,":[83],"e.g.":[84],"travelbug61.":[85],"Our":[86,124],"AE":[87],"solution":[88,155],"only":[89],"requires":[90],"features":[91,142],"extracted":[92],"UGC":[96,105,170],"page":[97,141,154],"instead":[98],"relying":[100],"clues":[102],"multiple":[104,153],"conducted":[108],"extensive":[109],"experiments.":[110],"The":[112],"evaluation":[113],"labeled":[116],"field":[118],"shows":[120],"95.0%":[121],"precision.":[122],"method":[125],"achieves":[126],"an":[127],"F1":[128],"score":[129],"96.1%,":[131],"significantly":[133],"outperforms":[134],"state-of-the-art":[136],"with":[139],"(F1":[143,156],"score:":[144,157],"68.4%)":[145],"has":[147],"comparable":[149],"performance":[150],"its":[152],"95.4%).":[158],"(3)":[159],"also":[161],"examine":[162],"robustness":[164],"our":[166],"various":[169],"pages":[171],"forums":[173],"review":[175],"sites,":[176],"achieve":[178],"promising":[179],"results":[180],"as":[181],"well.":[182]},"counts_by_year":[{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}