{"id":"https://openalex.org/W2167435152","doi":"https://doi.org/10.1145/1242572.1242838","title":"Adaptive record extraction from web pages","display_name":"Adaptive record extraction from web pages","publication_year":2007,"publication_date":"2007-05-08","ids":{"openalex":"https://openalex.org/W2167435152","doi":"https://doi.org/10.1145/1242572.1242838","mag":"2167435152"},"language":"en","primary_location":{"id":"doi:10.1145/1242572.1242838","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1242572.1242838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th international conference on World Wide Web","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/A5080074211","display_name":"Justin Park","orcid":"https://orcid.org/0000-0002-2421-608X"},"institutions":[{"id":"https://openalex.org/I168635309","display_name":"University of Calgary","ror":"https://ror.org/03yjb2x39","country_code":"CA","type":"education","lineage":["https://openalex.org/I168635309"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Justin Park","raw_affiliation_strings":["University of Calgary, Calgary, AB, Canada"],"affiliations":[{"raw_affiliation_string":"University of Calgary, Calgary, AB, Canada","institution_ids":["https://openalex.org/I168635309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061046432","display_name":"Denilson Barbosa","orcid":"https://orcid.org/0000-0002-6104-1987"},"institutions":[{"id":"https://openalex.org/I168635309","display_name":"University of Calgary","ror":"https://ror.org/03yjb2x39","country_code":"CA","type":"education","lineage":["https://openalex.org/I168635309"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Denilson Barbosa","raw_affiliation_strings":["University of Calgary, Calgary, AB, Canada"],"affiliations":[{"raw_affiliation_string":"University of Calgary, Calgary, AB, Canada","institution_ids":["https://openalex.org/I168635309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5080074211"],"corresponding_institution_ids":["https://openalex.org/I168635309"],"apc_list":null,"apc_paid":null,"fwci":3.956,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.94411059,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1335","last_page":"1336"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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":0.9764999747276306,"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/T10317","display_name":"Advanced Database Systems and Queries","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7962961196899414},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7024451494216919},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6426475644111633},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5792767405509949},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5538003444671631},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5154348611831665},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.49232399463653564},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.48778802156448364},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2646360993385315},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.239482581615448},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09246969223022461},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0880846381187439}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7962961196899414},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7024451494216919},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6426475644111633},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5792767405509949},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5538003444671631},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5154348611831665},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.49232399463653564},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48778802156448364},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2646360993385315},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.239482581615448},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09246969223022461},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0880846381187439},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1242572.1242838","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1242572.1242838","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th international conference on World Wide Web","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W93804029","https://openalex.org/W1660390307","https://openalex.org/W2005646337","https://openalex.org/W2015551056","https://openalex.org/W2104086170","https://openalex.org/W2128341918","https://openalex.org/W2129595335","https://openalex.org/W2143309843","https://openalex.org/W4210295937"],"related_works":["https://openalex.org/W4298130764","https://openalex.org/W2804364458","https://openalex.org/W2132641928","https://openalex.org/W4310225030","https://openalex.org/W2090259340","https://openalex.org/W2393816671","https://openalex.org/W2158836806","https://openalex.org/W2083665254","https://openalex.org/W1926736923","https://openalex.org/W2942177010"],"abstract_inverted_index":{"We":[0],"describe":[1],"an":[2],"adaptive":[3],"method":[4,28],"for":[5,21,41,51],"extracting":[6],"records":[7,43,53],"from":[8],"web":[9],"pages.":[10],"Our":[11],"algorithm":[12],"combines":[13],"a":[14],"weighted":[15],"tree":[16],"matching":[17],"metric":[18],"with":[19],"clustering":[20],"obtaining":[22],"data":[23],"extraction":[24],"patterns.We":[25],"compare":[26],"our":[27,36],"experimentally":[29],"to":[30],"the":[31],"state-of-the-art,":[32],"and":[33,48],"show":[34],"that":[35],"approach":[37],"is":[38],"very":[39],"competitive":[40],"rigidly-structured":[42],"(such":[44,54],"as":[45,55],"product":[46],"descriptions)":[47],"far":[49],"superior":[50],"loosely-structured":[52],"entrieson":[56],"blogs).":[57]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
