{"id":"https://openalex.org/W1968053850","doi":"https://doi.org/10.1145/2187980.2187991","title":"Data extraction from web pages based on structural-semantic entropy","display_name":"Data extraction from web pages based on structural-semantic entropy","publication_year":2012,"publication_date":"2012-04-16","ids":{"openalex":"https://openalex.org/W1968053850","doi":"https://doi.org/10.1145/2187980.2187991","mag":"1968053850"},"language":"en","primary_location":{"id":"doi:10.1145/2187980.2187991","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2187980.2187991","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 International Conference on World Wide Web","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/A5017835517","display_name":"Xiaoqing Zheng","orcid":"https://orcid.org/0000-0003-4430-5036"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoqing Zheng","raw_affiliation_strings":["Fudan University, Shanghai, China","Fudan University Shanghai, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Fudan University Shanghai, China#TAB#","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076446878","display_name":"Yi-Ling Gu","orcid":null},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiling Gu","raw_affiliation_strings":["Fudan University, Shanghai, China","Fudan University Shanghai, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Fudan University Shanghai, China#TAB#","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101658475","display_name":"Yinsheng Li","orcid":"https://orcid.org/0000-0002-1805-2445"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinsheng Li","raw_affiliation_strings":["Fudan University, Shanghai, China","Fudan University Shanghai, China#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Fudan University Shanghai, China#TAB#","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24943067"],"apc_list":null,"apc_paid":null,"fwci":2.8828,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.91405192,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"93","last_page":"102"},"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/T11644","display_name":"Spam and Phishing Detection","score":0.9528999924659729,"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":0.9516000151634216,"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":0.829258918762207},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7184441089630127},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6190624833106995},{"id":"https://openalex.org/keywords/semantic-web-stack","display_name":"Semantic Web Stack","score":0.5114463567733765},{"id":"https://openalex.org/keywords/social-semantic-web","display_name":"Social Semantic Web","score":0.48307040333747864},{"id":"https://openalex.org/keywords/data-web","display_name":"Data Web","score":0.47341495752334595},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.47171303629875183},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.4692758619785309},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.463293194770813},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.4410642385482788},{"id":"https://openalex.org/keywords/web-intelligence","display_name":"Web intelligence","score":0.4321644902229309},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.41699185967445374},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3760955333709717},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.34884679317474365}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.829258918762207},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7184441089630127},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6190624833106995},{"id":"https://openalex.org/C167379230","wikidata":"https://www.wikidata.org/wiki/Q1026884","display_name":"Semantic Web Stack","level":3,"score":0.5114463567733765},{"id":"https://openalex.org/C534406577","wikidata":"https://www.wikidata.org/wiki/Q7550843","display_name":"Social Semantic Web","level":3,"score":0.48307040333747864},{"id":"https://openalex.org/C162005631","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Data Web","level":3,"score":0.47341495752334595},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.47171303629875183},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.4692758619785309},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.463293194770813},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.4410642385482788},{"id":"https://openalex.org/C544335954","wikidata":"https://www.wikidata.org/wiki/Q2553348","display_name":"Web intelligence","level":4,"score":0.4321644902229309},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.41699185967445374},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3760955333709717},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.34884679317474365}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2187980.2187991","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2187980.2187991","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 International Conference on World Wide Web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.309.7276","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.309.7276","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www2012.wwwconference.org/proceedings/companion/p93.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1489992655","https://openalex.org/W1503682011","https://openalex.org/W1965913940","https://openalex.org/W1977598562","https://openalex.org/W2005646337","https://openalex.org/W2008272135","https://openalex.org/W2022158118","https://openalex.org/W2037504378","https://openalex.org/W2067416210","https://openalex.org/W2069388662","https://openalex.org/W2071628657","https://openalex.org/W2093559286","https://openalex.org/W2099283723","https://openalex.org/W2102966069","https://openalex.org/W2104086170","https://openalex.org/W2134150392","https://openalex.org/W2136072238","https://openalex.org/W2148540243","https://openalex.org/W2150721933","https://openalex.org/W2160196229","https://openalex.org/W2168358004","https://openalex.org/W2561675875","https://openalex.org/W3004954992"],"related_works":["https://openalex.org/W2415191659","https://openalex.org/W132269582","https://openalex.org/W2800499880","https://openalex.org/W2744329849","https://openalex.org/W2567626003","https://openalex.org/W163338125","https://openalex.org/W3139873369","https://openalex.org/W2563863560","https://openalex.org/W2472862012","https://openalex.org/W2520851676"],"abstract_inverted_index":{"Most":[0],"of":[1,73,82,84,92,113,124,148],"today's":[2],"web":[3,22,76,93,115,139],"content":[4,23],"is":[5,25,31,67,97],"designed":[6],"for":[7,14],"human":[8],"consumption,":[9],"which":[10,78,127],"makes":[11],"it":[12],"difficult":[13],"software":[15],"tools":[16],"to":[17,69,102,132,141],"access":[18],"them":[19],"readily.":[20],"Even":[21],"that":[24,49],"automatically":[26],"generated":[27],"from":[28,56],"back-end":[29],"databases":[30],"usually":[32],"presented":[33],"without":[34],"the":[35,52,71,80,88,122,125,138,146],"original":[36],"structural":[37],"information.":[38],"In":[39],"this":[40],"paper,":[41],"we":[42],"present":[43],"an":[44],"automated":[45],"information":[46,86],"extraction":[47],"algorithm":[48],"can":[50],"extract":[51],"relevant":[53,85],"attribute-value":[54],"pairs":[55],"product":[57],"descriptions":[58],"across":[59],"different":[60],"sites.":[61],"A":[62],"notion,":[63],"called":[64],"structural-semantic":[65],"entropy,":[66],"used":[68],"locate":[70],"data":[72],"interest":[74],"on":[75,87,109,137],"pages,":[77],"measures":[79],"density":[81],"occurrence":[83],"DOM":[89],"tree":[90],"representation":[91],"pages.":[94],"Our":[95],"approach":[96],"less":[98],"labor-intensive":[99],"and":[100,120],"insensitive":[101],"changes":[103],"in":[104,144],"web-page":[105],"format.":[106],"Experimental":[107],"results":[108],"a":[110],"large":[111],"number":[112],"real-life":[114],"page":[116],"collections":[117],"are":[118],"encouraging":[119],"confirm":[121],"feasibility":[123],"approach,":[126],"has":[128],"been":[129],"successfully":[130],"applied":[131],"detect":[133],"false":[134],"drug":[135],"advertisements":[136],"due":[140],"its":[142],"capacity":[143],"associating":[145],"attributes":[147],"records":[149],"with":[150],"their":[151],"respective":[152],"values.":[153]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
