{"id":"https://openalex.org/W2013737552","doi":"https://doi.org/10.1145/2254129.2254209","title":"Automated internal web page clustering for improved data extraction","display_name":"Automated internal web page clustering for improved data extraction","publication_year":2012,"publication_date":"2012-06-13","ids":{"openalex":"https://openalex.org/W2013737552","doi":"https://doi.org/10.1145/2254129.2254209","mag":"2013737552"},"language":"en","primary_location":{"id":"doi:10.1145/2254129.2254209","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2254129.2254209","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Conference on Web Intelligence, Mining and Semantics","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/A5054934597","display_name":"Cornelia Gy\u0151r\u00f6di","orcid":"https://orcid.org/0000-0002-7815-4355"},"institutions":[{"id":"https://openalex.org/I162871001","display_name":"University of Oradea","ror":"https://ror.org/00wzhv093","country_code":"RO","type":"education","lineage":["https://openalex.org/I162871001"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Cornelia Gy\u0151r\u00f6di","raw_affiliation_strings":["University of Oradea"],"affiliations":[{"raw_affiliation_string":"University of Oradea","institution_ids":["https://openalex.org/I162871001"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064026642","display_name":"Robert Gy\u0151r\u00f6di","orcid":"https://orcid.org/0000-0002-7027-5750"},"institutions":[{"id":"https://openalex.org/I162871001","display_name":"University of Oradea","ror":"https://ror.org/00wzhv093","country_code":"RO","type":"education","lineage":["https://openalex.org/I162871001"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Robert Gy\u0151r\u00f6di","raw_affiliation_strings":["University of Oradea"],"affiliations":[{"raw_affiliation_string":"University of Oradea","institution_ids":["https://openalex.org/I162871001"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059011568","display_name":"Mihai Cornea","orcid":null},"institutions":[{"id":"https://openalex.org/I162871001","display_name":"University of Oradea","ror":"https://ror.org/00wzhv093","country_code":"RO","type":"education","lineage":["https://openalex.org/I162871001"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Mihai Cornea","raw_affiliation_strings":["University of Oradea"],"affiliations":[{"raw_affiliation_string":"University of Oradea","institution_ids":["https://openalex.org/I162871001"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067328243","display_name":"George Pecherle","orcid":"https://orcid.org/0000-0002-0855-5727"},"institutions":[{"id":"https://openalex.org/I162871001","display_name":"University of Oradea","ror":"https://ror.org/00wzhv093","country_code":"RO","type":"education","lineage":["https://openalex.org/I162871001"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"George Pecherle","raw_affiliation_strings":["University of Oradea"],"affiliations":[{"raw_affiliation_string":"University of Oradea","institution_ids":["https://openalex.org/I162871001"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5054934597"],"corresponding_institution_ids":["https://openalex.org/I162871001"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15332318,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"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":0.9732999801635742,"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/T11644","display_name":"Spam and Phishing Detection","score":0.9611999988555908,"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/web-page","display_name":"Web page","score":0.8558622002601624},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8100554943084717},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6940558552742004},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.6318667531013489},{"id":"https://openalex.org/keywords/document-object-model","display_name":"Document Object Model","score":0.6179717779159546},{"id":"https://openalex.org/keywords/site-map","display_name":"Site map","score":0.4835326671600342},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.43132147192955017},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4018528461456299},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3564947843551636},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.2668517827987671},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1193433403968811}],"concepts":[{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.8558622002601624},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8100554943084717},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6940558552742004},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.6318667531013489},{"id":"https://openalex.org/C137922610","wikidata":"https://www.wikidata.org/wiki/Q2093","display_name":"Document Object Model","level":3,"score":0.6179717779159546},{"id":"https://openalex.org/C67617509","wikidata":"https://www.wikidata.org/wiki/Q1503327","display_name":"Site map","level":5,"score":0.4835326671600342},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.43132147192955017},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4018528461456299},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3564947843551636},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.2668517827987671},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1193433403968811}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2254129.2254209","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2254129.2254209","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2nd International Conference on Web Intelligence, Mining and Semantics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W8138659","https://openalex.org/W1989993068","https://openalex.org/W2015551056","https://openalex.org/W2019264297","https://openalex.org/W2049781914","https://openalex.org/W2104086170"],"related_works":["https://openalex.org/W2031790754","https://openalex.org/W2185387300","https://openalex.org/W2155199173","https://openalex.org/W1821340588","https://openalex.org/W2064945795","https://openalex.org/W2156420263","https://openalex.org/W2088345472","https://openalex.org/W2008577673","https://openalex.org/W2104619428","https://openalex.org/W2013737552"],"abstract_inverted_index":{"In":[0],"this":[1,24],"paper,":[2],"we":[3,25],"would":[4],"like":[5],"to":[6,10,47],"present":[7],"an":[8],"algorithm":[9,90],"determine":[11],"the":[12,16,28,62,68],"repeating":[13],"patterns":[14],"inside":[15,30],"DOM":[17,42],"tree":[18],"of":[19],"a":[20,31],"webpage.":[21],"By":[22],"doing":[23],"can":[26,44],"cluster":[27],"content":[29],"web":[32,50,65,98],"page":[33],"and":[34,57,77],"obtain":[35],"more":[36],"relevant":[37],"structured":[38],"data.":[39],"The":[40],"determined":[41],"structure":[43,56,73],"be":[45],"used":[46],"mine":[48],"other":[49],"pages":[51],"that":[52,94],"are":[53,70],"similar":[54,71,92],"in":[55,72,75],"one":[58],"hop":[59],"away":[60],"from":[61,91],"initial":[63],"targeted":[64],"page.":[66],"Also,":[67],"clusters":[69],"not":[74],"contents,":[76],"our":[78,89],"method":[79],"is":[80,86],"based":[81],"on":[82,96],"in-page":[83],"clustering.":[84],"This":[85],"what":[87],"differentiates":[88],"technologies":[93],"work":[95],"entire":[97],"pages.":[99]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}