{"id":"https://openalex.org/W3211490469","doi":"https://doi.org/10.3233/web-210465","title":"Trends in web data extraction using machine learning","display_name":"Trends in web data extraction using machine learning","publication_year":2021,"publication_date":"2021-06-01","ids":{"openalex":"https://openalex.org/W3211490469","doi":"https://doi.org/10.3233/web-210465","mag":"3211490469"},"language":"en","primary_location":{"id":"doi:10.3233/web-210465","is_oa":false,"landing_page_url":"https://doi.org/10.3233/web-210465","pdf_url":null,"source":{"id":"https://openalex.org/S4210183871","display_name":"Web Intelligence","issn_l":"2405-6456","issn":["2405-6456","2405-6464"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Web Intelligence","raw_type":"journal-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/A5081513560","display_name":"Sudhir Kumar Patnaik","orcid":"https://orcid.org/0000-0001-6069-1091"},"institutions":[{"id":"https://openalex.org/I302410947","display_name":"M S Ramaiah University of Applied Sciences","ror":"https://ror.org/02anh8x74","country_code":"IN","type":"education","lineage":["https://openalex.org/I302410947"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Sudhir Kumar Patnaik","raw_affiliation_strings":["Department of Computer Science, MS Ramaiah University of Applied Sciences, MSR Nagar, Bangalore, India. E-mails:\u00a0,\u00a0"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, MS Ramaiah University of Applied Sciences, MSR Nagar, Bangalore, India. E-mails:\u00a0,\u00a0","institution_ids":["https://openalex.org/I302410947"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112598534","display_name":"C. Narendra Babu","orcid":null},"institutions":[{"id":"https://openalex.org/I302410947","display_name":"M S Ramaiah University of Applied Sciences","ror":"https://ror.org/02anh8x74","country_code":"IN","type":"education","lineage":["https://openalex.org/I302410947"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"C. Narendra Babu","raw_affiliation_strings":["Department of Computer Science, MS Ramaiah University of Applied Sciences, MSR Nagar, Bangalore, India. E-mails:\u00a0,\u00a0"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, MS Ramaiah University of Applied Sciences, MSR Nagar, Bangalore, India. E-mails:\u00a0,\u00a0","institution_ids":["https://openalex.org/I302410947"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5081513560"],"corresponding_institution_ids":["https://openalex.org/I302410947"],"apc_list":null,"apc_paid":null,"fwci":0.5544,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.74360175,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"19","issue":"3","first_page":"169","last_page":"190"},"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/T11478","display_name":"Caching and Content Delivery","score":0.973800003528595,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.9671000242233276,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.7000526189804077},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6995032429695129},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5715783834457397},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.5027861595153809},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4580366611480713},{"id":"https://openalex.org/keywords/web-intelligence","display_name":"Web intelligence","score":0.4549420177936554},{"id":"https://openalex.org/keywords/data-web","display_name":"Data Web","score":0.4519557058811188},{"id":"https://openalex.org/keywords/web-standards","display_name":"Web standards","score":0.44207966327667236},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.42940765619277954},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4085859954357147},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31115901470184326}],"concepts":[{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.7000526189804077},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6995032429695129},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5715783834457397},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.5027861595153809},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4580366611480713},{"id":"https://openalex.org/C544335954","wikidata":"https://www.wikidata.org/wiki/Q2553348","display_name":"Web intelligence","level":4,"score":0.4549420177936554},{"id":"https://openalex.org/C162005631","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Data Web","level":3,"score":0.4519557058811188},{"id":"https://openalex.org/C182321512","wikidata":"https://www.wikidata.org/wiki/Q1153289","display_name":"Web standards","level":3,"score":0.44207966327667236},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.42940765619277954},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4085859954357147},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31115901470184326},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/web-210465","is_oa":false,"landing_page_url":"https://doi.org/10.3233/web-210465","pdf_url":null,"source":{"id":"https://openalex.org/S4210183871","display_name":"Web Intelligence","issn_l":"2405-6456","issn":["2405-6456","2405-6464"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Web Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Responsible consumption and production","id":"https://metadata.un.org/sdg/12"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":73,"referenced_works":["https://openalex.org/W55738326","https://openalex.org/W935072310","https://openalex.org/W1536680647","https://openalex.org/W1553229631","https://openalex.org/W1589784026","https://openalex.org/W1847465294","https://openalex.org/W1927338256","https://openalex.org/W1980773778","https://openalex.org/W1989993068","https://openalex.org/W2000870658","https://openalex.org/W2015551056","https://openalex.org/W2027864253","https://openalex.org/W2037504378","https://openalex.org/W2053045757","https://openalex.org/W2065568440","https://openalex.org/W2069388662","https://openalex.org/W2071628657","https://openalex.org/W2072936489","https://openalex.org/W2085016361","https://openalex.org/W2104086170","https://openalex.org/W2123354009","https://openalex.org/W2128308739","https://openalex.org/W2134150392","https://openalex.org/W2134172329","https://openalex.org/W2136072238","https://openalex.org/W2137235842","https://openalex.org/W2138396769","https://openalex.org/W2138405339","https://openalex.org/W2143309843","https://openalex.org/W2144951274","https://openalex.org/W2145404631","https://openalex.org/W2150721933","https://openalex.org/W2153072229","https://openalex.org/W2157008472","https://openalex.org/W2160189941","https://openalex.org/W2160196229","https://openalex.org/W2162340487","https://openalex.org/W2169818249","https://openalex.org/W2181195194","https://openalex.org/W2310425190","https://openalex.org/W2475668412","https://openalex.org/W2517903345","https://openalex.org/W2546526751","https://openalex.org/W2548485934","https://openalex.org/W2570343428","https://openalex.org/W2587580284","https://openalex.org/W2587782381","https://openalex.org/W2753202191","https://openalex.org/W2783940359","https://openalex.org/W2789729750","https://openalex.org/W2792709517","https://openalex.org/W2806541439","https://openalex.org/W2811122304","https://openalex.org/W2891638255","https://openalex.org/W2898256678","https://openalex.org/W2945125411","https://openalex.org/W2946615908","https://openalex.org/W2950939190","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W2972149141","https://openalex.org/W3008479101","https://openalex.org/W3008750864","https://openalex.org/W3014183340","https://openalex.org/W3025120288","https://openalex.org/W3041046342","https://openalex.org/W3115639172","https://openalex.org/W3165425482","https://openalex.org/W3200450977","https://openalex.org/W3205259184","https://openalex.org/W4230980612","https://openalex.org/W4285719527","https://openalex.org/W4292122152"],"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/W2542140006","https://openalex.org/W2622968908","https://openalex.org/W4319156738","https://openalex.org/W2729360854"],"abstract_inverted_index":{"Web":[0],"data":[1,28,62,69,80,99,121,141,157,179,217],"extraction":[2,36,40,49,63,81,100,122,142,158,180],"has":[3,19],"seen":[4],"significant":[5],"development":[6],"in":[7,14,60,119,155,159,164,177,185,190,209],"the":[8,15,53,76,83,117,153,160,165,186,211],"last":[9,84],"decade":[10],"since":[11],"its":[12],"inception":[13],"early":[16],"nineties.":[17],"It":[18],"evolved":[20],"from":[21,29],"a":[22],"simple":[23],"manual":[24,137],"way":[25],"of":[26,52,56,78,89,162,188,196,215],"extracting":[27],"web":[30,61,79,98,120,140,156,178,216],"page":[31],"and":[32,46,71,93,113,132,138,145,181,213],"documents":[33],"to":[34,37,136,205,210],"automated":[35,139],"an":[38,194],"intelligent":[39,97],"using":[41],"machine":[42,127,133],"learning":[43,128,134],"algorithms,":[44],"tools":[45],"techniques.":[47,129],"Data":[48],"is":[50],"one":[51],"key":[54],"components":[55],"end-to-end":[57],"life":[58],"cycle":[59],"process":[64],"that":[65],"includes":[66],"navigation,":[67],"extraction,":[68],"enrichment":[70],"visualization.":[72],"This":[73,168,199],"paper":[74,103,169],"presents":[75],"journey":[77],"over":[82,116],"many":[85],"years":[86,118],"highlighting":[87],"evolution":[88],"tools,":[90],"techniques,":[91],"frameworks":[92],"algorithms":[94],"for":[95,110],"building":[96],"systems.":[101],"The":[102],"also":[104],"throws":[105],"light":[106],"into":[107],"challenges,":[108],"opportunities":[109],"future":[111,197,214],"research":[112],"emerging":[114],"trends":[115],"with":[123,148],"specific":[124],"focus":[125],"on":[126],"Both":[130],"traditional":[131],"approaches":[135],"are":[143],"experimented":[144],"results":[146],"published":[147],"few":[149],"use":[150],"cases":[151],"demonstrating":[152],"challenges":[154],"event":[161,187],"changes":[163,189],"website":[166,191],"layout.":[167],"introduces":[170],"novel":[171],"ideas":[172],"such":[173],"as":[174,193],"self-healing":[175],"capability":[176],"proactive":[182],"error":[183],"detection":[184],"layout":[192],"area":[195],"research.":[198],"unique":[200],"perspective":[201],"will":[202],"help":[203],"readers":[204],"get":[206],"deeper":[207],"insights":[208],"present":[212],"extraction.":[218]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}