{"id":"https://openalex.org/W2045136577","doi":"https://doi.org/10.1145/956699.956703","title":"Fine-grain web site structure discovery","display_name":"Fine-grain web site structure discovery","publication_year":2003,"publication_date":"2003-11-07","ids":{"openalex":"https://openalex.org/W2045136577","doi":"https://doi.org/10.1145/956699.956703","mag":"2045136577"},"language":"en","primary_location":{"id":"doi:10.1145/956699.956703","is_oa":false,"landing_page_url":"https://doi.org/10.1145/956699.956703","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th ACM international workshop on Web information and data 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/A5030700727","display_name":"Valter Crescenzi","orcid":null},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Valter Crescenzi","raw_affiliation_strings":["Universit\u00e0 Roma Tre, Roma, Italy"],"affiliations":[{"raw_affiliation_string":"Universit\u00e0 Roma Tre, Roma, Italy","institution_ids":["https://openalex.org/I119003972"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022736687","display_name":"Paolo Merialdo","orcid":"https://orcid.org/0000-0002-3852-8092"},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paolo Merialdo","raw_affiliation_strings":["Universit\u00e0 Roma Tre, Roma, Italy"],"affiliations":[{"raw_affiliation_string":"Universit\u00e0 Roma Tre, Roma, Italy","institution_ids":["https://openalex.org/I119003972"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018918066","display_name":"Paolo Missier","orcid":"https://orcid.org/0000-0002-0978-2446"},"institutions":[{"id":"https://openalex.org/I119003972","display_name":"Roma Tre University","ror":"https://ror.org/05vf0dg29","country_code":"IT","type":"education","lineage":["https://openalex.org/I119003972"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paolo Missier","raw_affiliation_strings":["Universit\u00e0 Roma Tre, Roma, Italy"],"affiliations":[{"raw_affiliation_string":"Universit\u00e0 Roma Tre, Roma, Italy","institution_ids":["https://openalex.org/I119003972"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5030700727"],"corresponding_institution_ids":["https://openalex.org/I119003972"],"apc_list":null,"apc_paid":null,"fwci":5.3659,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.95612802,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"15","last_page":"22"},"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":0.9857000112533569,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9821000099182129,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.836154580116272},{"id":"https://openalex.org/keywords/site-map","display_name":"Site map","score":0.7560164928436279},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.6151149272918701},{"id":"https://openalex.org/keywords/web-site","display_name":"Web site","score":0.6096780300140381},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6019480228424072},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.545255184173584},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.49563634395599365},{"id":"https://openalex.org/keywords/html-element","display_name":"HTML element","score":0.4816928803920746},{"id":"https://openalex.org/keywords/document-object-model","display_name":"Document Object Model","score":0.4617595374584198},{"id":"https://openalex.org/keywords/syntax","display_name":"Syntax","score":0.44391611218452454},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42980632185935974},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.42082154750823975},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.41174525022506714},{"id":"https://openalex.org/keywords/html","display_name":"HTML","score":0.4112110733985901},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.3448346257209778},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33063897490501404},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.21996143460273743},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2194887399673462},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.21695265173912048},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21105262637138367}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.836154580116272},{"id":"https://openalex.org/C67617509","wikidata":"https://www.wikidata.org/wiki/Q1503327","display_name":"Site map","level":5,"score":0.7560164928436279},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.6151149272918701},{"id":"https://openalex.org/C2984519610","wikidata":"https://www.wikidata.org/wiki/Q35127","display_name":"Web site","level":3,"score":0.6096780300140381},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6019480228424072},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.545255184173584},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.49563634395599365},{"id":"https://openalex.org/C81639021","wikidata":"https://www.wikidata.org/wiki/Q179551","display_name":"HTML element","level":3,"score":0.4816928803920746},{"id":"https://openalex.org/C137922610","wikidata":"https://www.wikidata.org/wiki/Q2093","display_name":"Document Object Model","level":3,"score":0.4617595374584198},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.44391611218452454},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42980632185935974},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.42082154750823975},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.41174525022506714},{"id":"https://openalex.org/C138708601","wikidata":"https://www.wikidata.org/wiki/Q8811","display_name":"HTML","level":3,"score":0.4112110733985901},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.3448346257209778},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33063897490501404},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.21996143460273743},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2194887399673462},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.21695265173912048},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21105262637138367}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/956699.956703","is_oa":false,"landing_page_url":"https://doi.org/10.1145/956699.956703","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th ACM international workshop on Web information and data management","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.uniroma3.it:11590/162000","is_oa":false,"landing_page_url":"http://hdl.handle.net/11590/162000","pdf_url":null,"source":{"id":"https://openalex.org/S4377196120","display_name":"Iris (Roma Tre University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119003972","host_organization_name":"Roma Tre University","host_organization_lineage":["https://openalex.org/I119003972"],"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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W22683294","https://openalex.org/W1489992655","https://openalex.org/W1503682011","https://openalex.org/W2043440779","https://openalex.org/W2054658115","https://openalex.org/W2069388662","https://openalex.org/W2092269560","https://openalex.org/W2104086170","https://openalex.org/W2112546875","https://openalex.org/W2116493296","https://openalex.org/W2150721933","https://openalex.org/W2588004859","https://openalex.org/W4248809068"],"related_works":["https://openalex.org/W4255056669","https://openalex.org/W2772885702","https://openalex.org/W2393053995","https://openalex.org/W2489312077","https://openalex.org/W2108349423","https://openalex.org/W563028160","https://openalex.org/W2013737552","https://openalex.org/W2088188470","https://openalex.org/W2045136577","https://openalex.org/W4236419441"],"abstract_inverted_index":{"Several":[0],"techniques":[1,32],"have":[2,141,186],"been":[3],"recently":[4],"proposed":[5],"to":[6,55,62,153],"automatically":[7,33,80],"derive":[8],"web":[9,101,156,183],"wrappers,":[10],"i.e.,":[11],"programs":[12],"that":[13,43,121,145,185],"extract":[14],"data":[15],"from":[16,37],"HTML":[17,47],"pages,":[18],"and":[19,126,165],"transform":[20],"them":[21],"into":[22],"a":[23,35,38,45,89,94,113,123,159],"more":[24],"structured":[25],"format,":[26],"typically":[27],"in":[28],"XML":[29],"syntax.":[30],"These":[31],"induce":[34],"wrapper":[36,65],"set":[39],"of":[40,59,79,85,98,109,119,133,149,162,170],"sample":[41,60],"pages":[42,61,69,86,120],"share":[44,122],"common":[46,124],"template.":[48],"An":[49],"open":[50],"issue,":[51],"however,":[52],"is":[53],"how":[54],"collect":[56],"suitable":[57],"classes":[58,84,118],"feed":[63],"the":[64,68,77,82,107,110,134,147,154,163,171],"inducer.":[66],"Presently,":[67],"are":[70,117],"chosen":[71],"manually.In":[72],"this":[73,138],"paper,":[74],"we":[75,104,140],"tackle":[76],"problem":[78],"discovering":[81],"main":[83],"offered":[87],"by":[88,91],"site":[90,102,111,172],"exploring":[92],"only":[93],"small,":[95],"representative,":[96],"portion":[97,161],"it.":[99],"The":[100],"model":[103,169],"propose":[105],"describes":[106],"structure":[108],"as":[112],"graph":[114],"whose":[115,127],"nodes":[116],"structure,":[125],"edges":[128],"represent":[129],"links":[130],"among":[131],"instances":[132],"page":[135],"classes.":[136],"Using":[137],"model,":[139],"developed":[142],"an":[143,150,167],"algorithm":[144],"accepts":[146],"url":[148],"entry":[151],"point":[152],"target":[155],"site,":[157,164],"visits":[158],"limited":[160],"produces":[166],"accurate":[168],"structure.":[173],"We":[174],"also":[175],"report":[176],"on":[177,181],"preliminary":[178],"experiments":[179],"performed":[180],"actual":[182],"sites,":[184],"produced":[187],"encouraging":[188],"results.":[189]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
