{"id":"https://openalex.org/W3008750864","doi":"https://doi.org/10.1109/ssci44817.2019.9002877","title":"Review of Deep Web Data Extraction","display_name":"Review of Deep Web Data Extraction","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3008750864","doi":"https://doi.org/10.1109/ssci44817.2019.9002877","mag":"3008750864"},"language":"en","primary_location":{"id":"doi:10.1109/ssci44817.2019.9002877","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci44817.2019.9002877","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Symposium Series on Computational Intelligence (SSCI)","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/A5101593027","display_name":"Shenglin Li","orcid":"https://orcid.org/0000-0003-3740-6250"},"institutions":[{"id":"https://openalex.org/I142108993","display_name":"Southwest University","ror":"https://ror.org/01kj4z117","country_code":"CN","type":"education","lineage":["https://openalex.org/I142108993"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shenglin Li","raw_affiliation_strings":["College of Artificial Intelligence, Southwest University, Chongqing, P. R China"],"affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence, Southwest University, Chongqing, P. R China","institution_ids":["https://openalex.org/I142108993"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100418485","display_name":"Chen Chen","orcid":"https://orcid.org/0000-0002-7099-7905"},"institutions":[{"id":"https://openalex.org/I52604927","display_name":"PLA Army Service Academy","ror":"https://ror.org/02syyrn67","country_code":"CN","type":"education","lineage":["https://openalex.org/I52604927"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Chen","raw_affiliation_strings":["Department of Military logistics, Army Logistics University of PLA, Chongqing, P. R China"],"affiliations":[{"raw_affiliation_string":"Department of Military logistics, Army Logistics University of PLA, Chongqing, P. R China","institution_ids":["https://openalex.org/I52604927"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064622140","display_name":"Kaiwen Luo","orcid":"https://orcid.org/0000-0001-5497-5186"},"institutions":[{"id":"https://openalex.org/I52604927","display_name":"PLA Army Service Academy","ror":"https://ror.org/02syyrn67","country_code":"CN","type":"education","lineage":["https://openalex.org/I52604927"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaiwen Luo","raw_affiliation_strings":["Department of Military logistics, Army Logistics University of PLA, Chongqing, P. R China"],"affiliations":[{"raw_affiliation_string":"Department of Military logistics, Army Logistics University of PLA, Chongqing, P. R China","institution_ids":["https://openalex.org/I52604927"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101812522","display_name":"Bo Song","orcid":"https://orcid.org/0000-0001-5296-4125"},"institutions":[{"id":"https://openalex.org/I52604927","display_name":"PLA Army Service Academy","ror":"https://ror.org/02syyrn67","country_code":"CN","type":"education","lineage":["https://openalex.org/I52604927"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Song","raw_affiliation_strings":["Department of Military logistics, Army Logistics University of PLA, Chongqing, P. R China"],"affiliations":[{"raw_affiliation_string":"Department of Military logistics, Army Logistics University of PLA, Chongqing, P. R China","institution_ids":["https://openalex.org/I52604927"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101593027"],"corresponding_institution_ids":["https://openalex.org/I142108993"],"apc_list":null,"apc_paid":null,"fwci":2.7131,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.92405438,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"18","issue":null,"first_page":"1068","last_page":"1070"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"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":0.9998999834060669,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.970300018787384,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/T13976","display_name":"Web visibility and informetrics","score":0.9099000096321106,"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":0.7505019903182983},{"id":"https://openalex.org/keywords/deep-web","display_name":"Deep Web","score":0.7064911127090454},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.6419140100479126},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5467008352279663},{"id":"https://openalex.org/keywords/data-web","display_name":"Data Web","score":0.5099364519119263},{"id":"https://openalex.org/keywords/web-standards","display_name":"Web standards","score":0.4853195548057556},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4585104286670685},{"id":"https://openalex.org/keywords/web-intelligence","display_name":"Web intelligence","score":0.4577668011188507},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43893128633499146},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.39257514476776123},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3610963225364685},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3516312837600708},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.3276141285896301},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19375941157341003},{"id":"https://openalex.org/keywords/medline","display_name":"MEDLINE","score":0.07230564951896667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7505019903182983},{"id":"https://openalex.org/C46721378","wikidata":"https://www.wikidata.org/wiki/Q221989","display_name":"Deep Web","level":3,"score":0.7064911127090454},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.6419140100479126},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5467008352279663},{"id":"https://openalex.org/C162005631","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Data Web","level":3,"score":0.5099364519119263},{"id":"https://openalex.org/C182321512","wikidata":"https://www.wikidata.org/wiki/Q1153289","display_name":"Web standards","level":3,"score":0.4853195548057556},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4585104286670685},{"id":"https://openalex.org/C544335954","wikidata":"https://www.wikidata.org/wiki/Q2553348","display_name":"Web intelligence","level":4,"score":0.4577668011188507},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43893128633499146},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.39257514476776123},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3610963225364685},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3516312837600708},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.3276141285896301},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19375941157341003},{"id":"https://openalex.org/C2779473830","wikidata":"https://www.wikidata.org/wiki/Q1540899","display_name":"MEDLINE","level":2,"score":0.07230564951896667},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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:10.1109/ssci44817.2019.9002877","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ssci44817.2019.9002877","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Symposium Series on Computational Intelligence (SSCI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W796746","https://openalex.org/W153030323","https://openalex.org/W177694873","https://openalex.org/W243181951","https://openalex.org/W343945789","https://openalex.org/W1494806383","https://openalex.org/W1570239086","https://openalex.org/W1873122351","https://openalex.org/W1944937980","https://openalex.org/W1964698713","https://openalex.org/W1965431576","https://openalex.org/W1969831559","https://openalex.org/W1997402015","https://openalex.org/W2003975698","https://openalex.org/W2004441230","https://openalex.org/W2013970953","https://openalex.org/W2075786297","https://openalex.org/W2094930182","https://openalex.org/W2106568316","https://openalex.org/W2158253104","https://openalex.org/W2170188121","https://openalex.org/W2251214202","https://openalex.org/W2258702702","https://openalex.org/W2283375289","https://openalex.org/W2315382528","https://openalex.org/W2329749260","https://openalex.org/W2349213514","https://openalex.org/W2350480420","https://openalex.org/W2365094942","https://openalex.org/W2806151536","https://openalex.org/W3009454296","https://openalex.org/W6629549909","https://openalex.org/W6634163794","https://openalex.org/W6685116542","https://openalex.org/W6695369088","https://openalex.org/W7043520489"],"related_works":["https://openalex.org/W2184421161","https://openalex.org/W2182629206","https://openalex.org/W2184263241","https://openalex.org/W1523783981","https://openalex.org/W2945931694","https://openalex.org/W4385950365","https://openalex.org/W2622968908","https://openalex.org/W2729360854","https://openalex.org/W3174726539","https://openalex.org/W2542140006"],"abstract_inverted_index":{"The":[0],"Web":[1,9,44,57],"has":[2],"rich":[3],"and":[4,22,41,46,52],"comprehensive":[5],"data":[6,18,29,58],"resources.":[7],"Deep":[8,33,43,56],"is":[10],"larger":[11],"than":[12],"the":[13,28,36,50],"surface":[14],"web,":[15],"with":[16],"wider":[17],"coverage,":[19],"higher":[20],"quality":[21],"stronger":[23],"structure.":[24],"This":[25],"paper":[26],"summarizes":[27],"extraction":[30],"technology":[31],"in":[32],"Web,":[34],"expounds":[35],"collection":[37,59],"method":[38],"of":[39,55],"structured":[40],"unstructured":[42],"data,":[45],"looks":[47],"forward":[48],"to":[49],"challenges":[51],"development":[53],"direction":[54],"research.":[60]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
