{"id":"https://openalex.org/W2001602177","doi":"https://doi.org/10.1108/17440081011090239","title":"A strategy for extracting information from semi\u2010structured web pages","display_name":"A strategy for extracting information from semi\u2010structured web pages","publication_year":2010,"publication_date":"2010-11-20","ids":{"openalex":"https://openalex.org/W2001602177","doi":"https://doi.org/10.1108/17440081011090239","mag":"2001602177"},"language":"en","primary_location":{"id":"doi:10.1108/17440081011090239","is_oa":false,"landing_page_url":"https://doi.org/10.1108/17440081011090239","pdf_url":null,"source":{"id":"https://openalex.org/S145159096","display_name":"International Journal of Web Information Systems","issn_l":"1744-0084","issn":["1744-0084","1744-0092"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319811","host_organization_name":"Emerald Publishing Limited","host_organization_lineage":["https://openalex.org/P4310319811"],"host_organization_lineage_names":["Emerald Publishing Limited"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Web Information Systems","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/A5013795150","display_name":"Mahmoud Shaker","orcid":"https://orcid.org/0000-0002-9501-1014"},"institutions":[{"id":"https://openalex.org/I130343225","display_name":"Universiti Putra Malaysia","ror":"https://ror.org/02e91jd64","country_code":"MY","type":"education","lineage":["https://openalex.org/I130343225"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Mahmoud Shaker","raw_affiliation_strings":["Department of Computer Science, Faculty of Computer Science and Information Technology, Universiti Putra Malaysia, Serdang, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Faculty of Computer Science and Information Technology, Universiti Putra Malaysia, Serdang, Malaysia","institution_ids":["https://openalex.org/I130343225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000398352","display_name":"Hamidah Ibrahim","orcid":"https://orcid.org/0000-0002-9900-0531"},"institutions":[{"id":"https://openalex.org/I130343225","display_name":"Universiti Putra Malaysia","ror":"https://ror.org/02e91jd64","country_code":"MY","type":"education","lineage":["https://openalex.org/I130343225"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Hamidah Ibrahim","raw_affiliation_strings":["Department of Computer Science, Faculty of Computer Science and Information Technology, Universiti Putra Malaysia, Serdang, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Faculty of Computer Science and Information Technology, Universiti Putra Malaysia, Serdang, Malaysia","institution_ids":["https://openalex.org/I130343225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032045434","display_name":"Aida Mustapha","orcid":"https://orcid.org/0000-0002-9077-4995"},"institutions":[{"id":"https://openalex.org/I130343225","display_name":"Universiti Putra Malaysia","ror":"https://ror.org/02e91jd64","country_code":"MY","type":"education","lineage":["https://openalex.org/I130343225"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Aida Mustapha","raw_affiliation_strings":["Department of Computer Science, Faculty of Computer Science and Information Technology, Universiti Putra Malaysia, Serdang, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Faculty of Computer Science and Information Technology, Universiti Putra Malaysia, Serdang, Malaysia","institution_ids":["https://openalex.org/I130343225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019058734","display_name":"Lili Nurliyana Abdullah","orcid":"https://orcid.org/0000-0001-8704-2390"},"institutions":[{"id":"https://openalex.org/I130343225","display_name":"Universiti Putra Malaysia","ror":"https://ror.org/02e91jd64","country_code":"MY","type":"education","lineage":["https://openalex.org/I130343225"]}],"countries":["MY"],"is_corresponding":false,"raw_author_name":"Lili Nurliyana Abdullah","raw_affiliation_strings":["Department of Computer Science, Faculty of Computer Science and Information Technology, Universiti Putra Malaysia, Serdang, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Faculty of Computer Science and Information Technology, Universiti Putra Malaysia, Serdang, Malaysia","institution_ids":["https://openalex.org/I130343225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130343225"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13600297,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"6","issue":"4","first_page":"304","last_page":"318"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.964900016784668,"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/T13976","display_name":"Web visibility and informetrics","score":0.9549999833106995,"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":0.880018413066864},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5663335919380188},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5157699584960938},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4810202717781067}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.880018413066864},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5663335919380188},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5157699584960938},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4810202717781067}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1108/17440081011090239","is_oa":false,"landing_page_url":"https://doi.org/10.1108/17440081011090239","pdf_url":null,"source":{"id":"https://openalex.org/S145159096","display_name":"International Journal of Web Information Systems","issn_l":"1744-0084","issn":["1744-0084","1744-0092"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319811","host_organization_name":"Emerald Publishing Limited","host_organization_lineage":["https://openalex.org/P4310319811"],"host_organization_lineage_names":["Emerald Publishing Limited"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Web Information Systems","raw_type":"journal-article"},{"id":"pmh:oai:psasir.upm.edu.my:12868","is_oa":false,"landing_page_url":"http://psasir.upm.edu.my/id/eprint/12868/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196260","display_name":"Universiti Putra Malaysia Institutional Repository (Universiti Putra Malaysia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I130343225","host_organization_name":"Universiti Putra Malaysia","host_organization_lineage":["https://openalex.org/I130343225"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W180206698","https://openalex.org/W1504653293","https://openalex.org/W1545319039","https://openalex.org/W1553137647","https://openalex.org/W1822702654","https://openalex.org/W2005970231","https://openalex.org/W2014957610","https://openalex.org/W2046817824","https://openalex.org/W2102189859","https://openalex.org/W2102966069","https://openalex.org/W2108770713","https://openalex.org/W2119577990","https://openalex.org/W2155067355","https://openalex.org/W2159240506","https://openalex.org/W2162611262","https://openalex.org/W2546543898","https://openalex.org/W6729612466"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W1488511360","https://openalex.org/W1781894645","https://openalex.org/W2894902932","https://openalex.org/W569715723","https://openalex.org/W188332989","https://openalex.org/W2982387199","https://openalex.org/W2000745862","https://openalex.org/W2120930843","https://openalex.org/W4247875831"],"abstract_inverted_index":{"Purpose":[0],"\u2013":[1,19,60,91,117],"The":[2,20,61],"aim":[3],"of":[4,31,40,86],"this":[5,65],"paper":[6,21,62,119],"is":[7,113],"to":[8,54,121],"propose":[9],"a":[10,23],"strategy":[11,24,66,103],"for":[12,25],"extracting":[13,26,125],"information":[14,27,68,105],"from":[15,28,106],"web":[16,29,33,107],"tables.":[17],"Design/methodology/approach":[18],"presents":[22],"tables":[30,108],"semi-structured":[32],"pages":[34],"(WPs)":[35],"by":[36],"handling":[37],"the":[38,74,77,81,87,95,101,122],"issue":[39],"synonym":[41],"which":[42,112],"emerges":[43],"as":[44],"these":[45],"WPs":[46],"have":[47],"been":[48],"designed":[49],"and":[50,72,84],"created":[51],"without":[52],"referring":[53],"any":[55],"standards":[56],"or":[57],"guidelines.":[58],"Findings":[59],"finds":[63],"that":[64,79,100],"extracts":[67,73,104],"with":[69,109],"high":[70,110],"precision,":[71],"attributes":[75,83],"besides":[76],"sub-attributes":[78],"describe":[80],"extracted":[82],"values":[85],"sub-attributes.":[88],"Practical":[89],"implications":[90],"Experiment":[92],"conducted":[93],"on":[94,124],"Nokia":[96],"products":[97],"domain":[98],"demonstrated":[99],"proposed":[102],"precision":[111],"98.98":[114],"percent.":[115],"Originality/value":[116],"This":[118],"contributes":[120],"research":[123],"information.":[126]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
