{"id":"https://openalex.org/W4212774669","doi":"https://doi.org/10.1145/3495008","title":"A Web Information Extraction Framework with Adaptive and Failure Prediction Feature","display_name":"A Web Information Extraction Framework with Adaptive and Failure Prediction Feature","publication_year":2022,"publication_date":"2022-02-18","ids":{"openalex":"https://openalex.org/W4212774669","doi":"https://doi.org/10.1145/3495008"},"language":"en","primary_location":{"id":"doi:10.1145/3495008","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3495008","pdf_url":null,"source":{"id":"https://openalex.org/S110189822","display_name":"Journal of Data and Information Quality","issn_l":"1936-1955","issn":["1936-1955","1936-1963"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Data and Information Quality","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":false,"raw_author_name":"Sudhir Kumar Patnaik","raw_affiliation_strings":["MS Ramiah University of Applied Sciences, Bangalore, Karnataka, India"],"raw_orcid":"https://orcid.org/0000-0001-6069-1091","affiliations":[{"raw_affiliation_string":"MS Ramiah University of Applied Sciences, Bangalore, Karnataka, India","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":["MS Ramiah University of Applied Sciences, Bangalore, Karnataka, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MS Ramiah University of Applied Sciences, Bangalore, Karnataka, India","institution_ids":["https://openalex.org/I302410947"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I302410947"],"apc_list":null,"apc_paid":null,"fwci":3.0974,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.92521232,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"14","issue":"2","first_page":"1","last_page":"21"},"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9697999954223633,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.9679999947547913,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8836660385131836},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.6733804941177368},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5603520274162292},{"id":"https://openalex.org/keywords/document-object-model","display_name":"Document Object Model","score":0.4854646325111389},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4676750600337982},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.46590834856033325},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43032971024513245},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.42948079109191895},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.40391695499420166},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.37054675817489624},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33544906973838806},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2548438608646393}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8836660385131836},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.6733804941177368},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5603520274162292},{"id":"https://openalex.org/C137922610","wikidata":"https://www.wikidata.org/wiki/Q2093","display_name":"Document Object Model","level":3,"score":0.4854646325111389},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4676750600337982},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.46590834856033325},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43032971024513245},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.42948079109191895},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.40391695499420166},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.37054675817489624},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33544906973838806},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2548438608646393}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3495008","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3495008","pdf_url":null,"source":{"id":"https://openalex.org/S110189822","display_name":"Journal of Data and Information Quality","issn_l":"1936-1955","issn":["1936-1955","1936-1963"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Data and Information Quality","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W6578894","https://openalex.org/W1556616930","https://openalex.org/W1847465294","https://openalex.org/W1927338256","https://openalex.org/W1970841368","https://openalex.org/W1971113501","https://openalex.org/W2053045757","https://openalex.org/W2065568440","https://openalex.org/W2096938851","https://openalex.org/W2114739461","https://openalex.org/W2123883612","https://openalex.org/W2136072238","https://openalex.org/W2137235842","https://openalex.org/W2145071552","https://openalex.org/W2145404631","https://openalex.org/W2148931201","https://openalex.org/W2153635508","https://openalex.org/W2162340487","https://openalex.org/W2164463086","https://openalex.org/W2394650700","https://openalex.org/W2517903345","https://openalex.org/W2585367509","https://openalex.org/W2738710562","https://openalex.org/W2800713582","https://openalex.org/W2811122304","https://openalex.org/W2950939190","https://openalex.org/W2963446712","https://openalex.org/W2976134045","https://openalex.org/W3008750864","https://openalex.org/W3025035827","https://openalex.org/W3035667192","https://openalex.org/W3178076956","https://openalex.org/W3200450977","https://openalex.org/W3205259184"],"related_works":["https://openalex.org/W2031790754","https://openalex.org/W2373402338","https://openalex.org/W3144508074","https://openalex.org/W2951920527","https://openalex.org/W2998827288","https://openalex.org/W36911888","https://openalex.org/W2076910790","https://openalex.org/W2275993472","https://openalex.org/W2155199173","https://openalex.org/W2185387300"],"abstract_inverted_index":{"The":[0,51,94,138],"amount":[1],"of":[2,53,96,146,158,160,198],"information":[3,11,23,57,63,91,106,123,159,173,202],"available":[4],"on":[5,62],"the":[6,42,110,147,161],"internet":[7],"today":[8],"requires":[9],"effective":[10],"extraction":[12,58,64,68,92,107,157,174,189],"and":[13,27,89,104,132,154,175,187,196,201],"processing":[14],"to":[15,21,32,41,45,73,84,100,114,151,182],"offer":[16],"hyper-personalized":[17],"user":[18],"experiences.":[19],"Inability":[20],"extract":[22,122],"by":[24,65],"using":[25,66,124,127,141],"traditional":[26],"machine":[28,55],"learning":[29],"techniques":[30,126],"due":[31,150],"dynamic":[33],"changes":[34,153],"in":[35,191],"website":[36,74,117,170],"layout":[37,152],"pose":[38],"significant":[39],"challenges":[40],"technical":[43],"community":[44],"keep":[46],"up":[47],"with":[48,109,168],"such":[49,81],"changes.":[50],"focus":[52],"existing":[54],"learning-based":[56],"framework":[59,108],"is":[60,71,99,180],"only":[61,113],"core":[67,79],"logic":[69],"that":[70],"susceptible":[72],"changes,":[75],"thus":[76],"missing":[77],"out":[78],"features":[80],"as":[82],"ability":[83,111],"handle":[85],"proactive":[86,139,184],"failure":[87,118,185,193],"prediction":[88,186],"intelligent":[90,105,172],"capabilities.":[93],"aim":[95],"this":[97],"article":[98],"build":[101],"a":[102],"robust":[103],"not":[112],"proactively":[115],"predict":[116],"but":[119],"also":[120],"automatically":[121],"deep-learning":[125],"You":[128],"Only":[129],"Look":[130],"Once":[131],"Long":[133],"Short-term":[134],"Memory":[135],"(LSTM)":[136],"networks.":[137],"detection":[140,200],"LSTM":[142],"detects":[143],"new":[144,162],"location":[145],"web":[148,163],"page":[149],"enables":[155],"automatic":[156,188],"page.":[164],"A":[165],"real-world":[166],"case":[167],"retail":[169],"for":[171],"an":[176],"offline":[177],"experimentation":[178],"environment":[179],"setup":[181],"demonstrate":[183],"resulting":[190],"high":[192],"prediction,":[194],"precision":[195],"recall":[197],"object":[199],"extraction.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":4},{"year":2023,"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"}