{"id":"https://openalex.org/W2083330748","doi":"https://doi.org/10.1016/s0167-9236(02)00100-8","title":"Automatic information extraction from semi-structured Web pages by pattern discovery","display_name":"Automatic information extraction from semi-structured Web pages by pattern discovery","publication_year":2002,"publication_date":"2002-12-28","ids":{"openalex":"https://openalex.org/W2083330748","doi":"https://doi.org/10.1016/s0167-9236(02)00100-8","mag":"2083330748"},"language":"en","primary_location":{"id":"doi:10.1016/s0167-9236(02)00100-8","is_oa":false,"landing_page_url":"https://doi.org/10.1016/s0167-9236(02)00100-8","pdf_url":null,"source":{"id":"https://openalex.org/S11479521","display_name":"Decision Support Systems","issn_l":"0167-9236","issn":["0167-9236","1873-5797"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Decision Support 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/A5078524542","display_name":"Chia\u2010Hui Chang","orcid":"https://orcid.org/0000-0002-1101-6337"},"institutions":[{"id":"https://openalex.org/I22265921","display_name":"National Central University","ror":"https://ror.org/00944ve71","country_code":"TW","type":"education","lineage":["https://openalex.org/I22265921"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Chia-Hui Chang","raw_affiliation_strings":["Department of Computer Science and Information Engineering, National Central University, Chungli, Tauyuan 320, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Information Engineering, National Central University, Chungli, Tauyuan 320, Taiwan","institution_ids":["https://openalex.org/I22265921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040580626","display_name":"Chun\u2010Nan Hsu","orcid":"https://orcid.org/0000-0002-5240-4707"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chun-Nan Hsu","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Nankang, Taipei 115, Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Nankang, Taipei 115, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020760248","display_name":"Shao-Cheng Lui","orcid":null},"institutions":[{"id":"https://openalex.org/I92172085","display_name":"Chunghwa Telecom (Taiwan)","ror":"https://ror.org/04f786589","country_code":"TW","type":"company","lineage":["https://openalex.org/I92172085"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shao-Cheng Lui","raw_affiliation_strings":["ChungHwa Telecommunication Laboratories, Yangmei, Tauyuan 326, Taiwan","ChungHwa Telecommunication Laboratories, Yangmei, Tauyuan 326, Taiwan#TAB#"],"affiliations":[{"raw_affiliation_string":"ChungHwa Telecommunication Laboratories, Yangmei, Tauyuan 326, Taiwan","institution_ids":["https://openalex.org/I92172085"]},{"raw_affiliation_string":"ChungHwa Telecommunication Laboratories, Yangmei, Tauyuan 326, Taiwan#TAB#","institution_ids":["https://openalex.org/I92172085"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5078524542"],"corresponding_institution_ids":["https://openalex.org/I22265921"],"apc_list":{"value":3280,"currency":"USD","value_usd":3280},"apc_paid":null,"fwci":12.5234,"has_fulltext":false,"cited_by_count":101,"citation_normalized_percentile":{"value":0.98411754,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"35","issue":"1","first_page":"129","last_page":"147"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9891999959945679,"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":0.8319104909896851},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6712218523025513},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6302354335784912},{"id":"https://openalex.org/keywords/information-extraction","display_name":"Information extraction","score":0.5888336896896362},{"id":"https://openalex.org/keywords/data-extraction","display_name":"Data extraction","score":0.4368714392185211},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.4339887499809265},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.43138229846954346},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.42847371101379395},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.42761123180389404},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41697633266448975},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.40871068835258484},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2714872360229492},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0750947892665863}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8319104909896851},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6712218523025513},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6302354335784912},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.5888336896896362},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.4368714392185211},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.4339887499809265},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.43138229846954346},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.42847371101379395},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.42761123180389404},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41697633266448975},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.40871068835258484},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2714872360229492},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0750947892665863},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","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},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/s0167-9236(02)00100-8","is_oa":false,"landing_page_url":"https://doi.org/10.1016/s0167-9236(02)00100-8","pdf_url":null,"source":{"id":"https://openalex.org/S11479521","display_name":"Decision Support Systems","issn_l":"0167-9236","issn":["0167-9236","1873-5797"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Decision Support Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321040","display_name":"National Science Council","ror":"https://ror.org/02kv4zf79"},{"id":"https://openalex.org/F4320323229","display_name":"National Central University","ror":"https://ror.org/00944ve71"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W26772505","https://openalex.org/W938539187","https://openalex.org/W1550771877","https://openalex.org/W1553019137","https://openalex.org/W1573714593","https://openalex.org/W1842945429","https://openalex.org/W1982547887","https://openalex.org/W1985108724","https://openalex.org/W1990061958","https://openalex.org/W1996034123","https://openalex.org/W1997841190","https://openalex.org/W2026080185","https://openalex.org/W2037600449","https://openalex.org/W2052522161","https://openalex.org/W2065568440","https://openalex.org/W2100985186","https://openalex.org/W2116628377","https://openalex.org/W2134826720","https://openalex.org/W2137096228","https://openalex.org/W2153072229","https://openalex.org/W2153752143","https://openalex.org/W2154749666","https://openalex.org/W2155512447","https://openalex.org/W2160196229","https://openalex.org/W2161424795","https://openalex.org/W2162340487","https://openalex.org/W2164235596","https://openalex.org/W2166407869","https://openalex.org/W2172549414","https://openalex.org/W2291813680","https://openalex.org/W2301435905","https://openalex.org/W2610179052","https://openalex.org/W4239696231","https://openalex.org/W4285719527","https://openalex.org/W6633007531","https://openalex.org/W6633154970","https://openalex.org/W6634457518","https://openalex.org/W6638843515","https://openalex.org/W6649460998","https://openalex.org/W6656961977","https://openalex.org/W6659708835","https://openalex.org/W6675230469","https://openalex.org/W6682468365","https://openalex.org/W6682560834","https://openalex.org/W6683708266","https://openalex.org/W6684283249","https://openalex.org/W6684399550","https://openalex.org/W6685410571"],"related_works":["https://openalex.org/W36911888","https://openalex.org/W2083329789","https://openalex.org/W2016355461","https://openalex.org/W2376574812","https://openalex.org/W2351142401","https://openalex.org/W4385731361","https://openalex.org/W2051525169","https://openalex.org/W2386938185","https://openalex.org/W2068844411","https://openalex.org/W1986386500"],"abstract_inverted_index":null,"counts_by_year":[{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":7},{"year":2014,"cited_by_count":10},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":9}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
