{"id":"https://openalex.org/W2031517079","doi":"https://doi.org/10.1145/1458082.1458295","title":"Coreex","display_name":"Coreex","publication_year":2008,"publication_date":"2008-10-26","ids":{"openalex":"https://openalex.org/W2031517079","doi":"https://doi.org/10.1145/1458082.1458295","mag":"2031517079"},"language":"en","primary_location":{"id":"doi:10.1145/1458082.1458295","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458082.1458295","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM conference on Information and knowledge management","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/A5102108559","display_name":"Jyotika Prasad","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jyotika Prasad","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071755113","display_name":"Andreas Paepcke","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andreas Paepcke","raw_affiliation_strings":["Stanford University, Stanford, CA, USA"],"affiliations":[{"raw_affiliation_string":"Stanford University, Stanford, CA, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102108559"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":7.6138,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.96838134,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1391","last_page":"1392"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9711999893188477,"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/T13976","display_name":"Web visibility and informetrics","score":0.9685999751091003,"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":0.7988593578338623},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.706822395324707},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.562890887260437},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.515673041343689},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5063158273696899},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4878961741924286},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.48584839701652527},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.4713199734687805},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38096314668655396},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37355953454971313},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.359188973903656},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.22213372588157654},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09717234969139099}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7988593578338623},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.706822395324707},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.562890887260437},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.515673041343689},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5063158273696899},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4878961741924286},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.48584839701652527},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4713199734687805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38096314668655396},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37355953454971313},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.359188973903656},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.22213372588157654},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09717234969139099},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1458082.1458295","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458082.1458295","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM conference on Information and knowledge management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W102858063","https://openalex.org/W1500874501","https://openalex.org/W1506984360","https://openalex.org/W2005646337","https://openalex.org/W2007442002","https://openalex.org/W2019264297","https://openalex.org/W2034607275","https://openalex.org/W2038124402","https://openalex.org/W2064818667","https://openalex.org/W2087406717","https://openalex.org/W2102261150","https://openalex.org/W2109803107","https://openalex.org/W2135479443","https://openalex.org/W2153072229","https://openalex.org/W2155199173","https://openalex.org/W2735074951"],"related_works":["https://openalex.org/W2366107444","https://openalex.org/W2280422768","https://openalex.org/W3177062893","https://openalex.org/W3125143773","https://openalex.org/W2007032764","https://openalex.org/W803550684","https://openalex.org/W2483226803","https://openalex.org/W4352977312","https://openalex.org/W1536056491","https://openalex.org/W2041180560"],"abstract_inverted_index":{"We":[0,17,55],"developed":[1],"and":[2,25,41,48,76,79],"tested":[3,56],"a":[4,60],"heuristic":[5],"technique":[6],"for":[7],"extracting":[8],"the":[9,19,23,31,35],"main":[10],"article":[11,65],"from":[12,67],"news":[13,64],"site":[14],"Web":[15],"pages.":[16],"construct":[18],"DOM":[20],"tree":[21],"of":[22,33,37,62,84],"page":[24],"score":[26],"every":[27],"node":[28],"based":[29],"on":[30,59],"amount":[32],"text,":[34],"number":[36],"links":[38],"it":[39],"contains":[40],"additional":[42],"heuristics.":[43],"The":[44],"method":[45],"is":[46],"site-independent":[47],"does":[49],"not":[50],"use":[51],"any":[52],"language-based":[53],"features.":[54],"our":[57],"algorithm":[58,71],"set":[61],"1120":[63],"pages":[66],"27":[68],"domains.":[69],"Our":[70],"achieved":[72],"over":[73],"97%":[74],"precision":[75],"98%":[77],"recall,":[78],"an":[80],"average":[81],"processing":[82],"speed":[83],"under":[85],"15ms":[86],"per":[87],"page.":[88]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}