{"id":"https://openalex.org/W2008468035","doi":"https://doi.org/10.1145/1458502.1458520","title":"Granular modeling of web documents","display_name":"Granular modeling of web documents","publication_year":2008,"publication_date":"2008-10-30","ids":{"openalex":"https://openalex.org/W2008468035","doi":"https://doi.org/10.1145/1458502.1458520","mag":"2008468035"},"language":"en","primary_location":{"id":"doi:10.1145/1458502.1458520","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458502.1458520","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM 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/A5005702955","display_name":"Elisabetta Fersini","orcid":"https://orcid.org/0000-0002-8987-100X"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Elisabetta Fersini","raw_affiliation_strings":["University of Milano-Bicocca, Milano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Milano-Bicocca, Milano, Italy","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061496529","display_name":"Enza Messina","orcid":"https://orcid.org/0000-0002-4062-0824"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Enza Messina","raw_affiliation_strings":["University of Milano-Bicocca, Milano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Milano-Bicocca, Milano, Italy","institution_ids":["https://openalex.org/I66752286"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011390491","display_name":"Francesco Archetti","orcid":"https://orcid.org/0000-0003-1131-3830"},"institutions":[{"id":"https://openalex.org/I66752286","display_name":"University of Milano-Bicocca","ror":"https://ror.org/01ynf4891","country_code":"IT","type":"education","lineage":["https://openalex.org/I66752286"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesco Archetti","raw_affiliation_strings":["University of Milano-Bicocca, Milano, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Milano-Bicocca, Milano, Italy","institution_ids":["https://openalex.org/I66752286"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1755,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.83884833,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"111","last_page":"118"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9984999895095825,"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"}},"topics":[{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9984999895095825,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9980000257492065,"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/T11063","display_name":"Rough Sets and Fuzzy Logic","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.86018967628479},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.7626067399978638},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5774821043014526},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5591322779655457},{"id":"https://openalex.org/keywords/semantic-web-stack","display_name":"Semantic Web Stack","score":0.5473293662071228},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5302198529243469},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5216579437255859},{"id":"https://openalex.org/keywords/social-semantic-web","display_name":"Social Semantic Web","score":0.4959016740322113},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4615905284881592},{"id":"https://openalex.org/keywords/explicit-semantic-analysis","display_name":"Explicit semantic analysis","score":0.46072128415107727},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.43562251329421997},{"id":"https://openalex.org/keywords/semantic-web","display_name":"Semantic Web","score":0.42264217138290405},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.41557109355926514},{"id":"https://openalex.org/keywords/semantic-technology","display_name":"Semantic technology","score":0.09124702215194702}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.86018967628479},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.7626067399978638},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5774821043014526},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5591322779655457},{"id":"https://openalex.org/C167379230","wikidata":"https://www.wikidata.org/wiki/Q1026884","display_name":"Semantic Web Stack","level":3,"score":0.5473293662071228},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5302198529243469},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5216579437255859},{"id":"https://openalex.org/C534406577","wikidata":"https://www.wikidata.org/wiki/Q7550843","display_name":"Social Semantic Web","level":3,"score":0.4959016740322113},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4615905284881592},{"id":"https://openalex.org/C173862523","wikidata":"https://www.wikidata.org/wiki/Q5421270","display_name":"Explicit semantic analysis","level":5,"score":0.46072128415107727},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.43562251329421997},{"id":"https://openalex.org/C2129575","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Semantic Web","level":2,"score":0.42264217138290405},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.41557109355926514},{"id":"https://openalex.org/C6881194","wikidata":"https://www.wikidata.org/wiki/Q7449091","display_name":"Semantic technology","level":4,"score":0.09124702215194702},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1458502.1458520","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458502.1458520","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 10th ACM workshop on Web information and data management","raw_type":"proceedings-article"},{"id":"pmh:oai:boa.unimib.it:10281/13871","is_oa":false,"landing_page_url":"http://hdl.handle.net/10281/13871","pdf_url":null,"source":{"id":"https://openalex.org/S4306401259","display_name":"BOA (University of Milano-Bicocca)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66752286","host_organization_name":"University of Milano-Bicocca","host_organization_lineage":["https://openalex.org/I66752286"],"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":[{"display_name":"Quality Education","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1512098439","https://openalex.org/W1566513354","https://openalex.org/W1599022437","https://openalex.org/W1738091461","https://openalex.org/W1912123407","https://openalex.org/W1978394996","https://openalex.org/W1981202432","https://openalex.org/W2066636486","https://openalex.org/W2069870183","https://openalex.org/W2089199911","https://openalex.org/W2096041903","https://openalex.org/W2107034620","https://openalex.org/W2111289574","https://openalex.org/W2121641626","https://openalex.org/W2121871415","https://openalex.org/W2123504579","https://openalex.org/W2125055259","https://openalex.org/W2130610812","https://openalex.org/W2140204390","https://openalex.org/W2140275264","https://openalex.org/W2147169507","https://openalex.org/W2165612380","https://openalex.org/W2167859982","https://openalex.org/W2170344111","https://openalex.org/W2466512847","https://openalex.org/W2913668833","https://openalex.org/W2999905431","https://openalex.org/W7055702063"],"related_works":["https://openalex.org/W2349698472","https://openalex.org/W1521613906","https://openalex.org/W2388164838","https://openalex.org/W3150576547","https://openalex.org/W2366430559","https://openalex.org/W1585941060","https://openalex.org/W2005492920","https://openalex.org/W146038348","https://openalex.org/W2265570313","https://openalex.org/W2032956642"],"abstract_inverted_index":{"One":[0],"of":[1,45,62,71,105,140],"the":[2,103,138],"most":[3],"important":[4],"tasks":[5],"in":[6,60,67,124],"Information":[7],"Retrieval":[8],"(IR)":[9],"is":[10,20],"related":[11],"to":[12,24,34,90,101,136],"web":[13,27,54,73],"page":[14,28,74,151],"information":[15,148],"extraction":[16],"and":[17,33,75,100,131,145],"processing.":[18],"It":[19],"a":[21,26,40,53,72,87,92],"common":[22],"approach":[23],"consider":[25],"as":[29,39,129],"an":[30],"atomic":[31],"unit":[32],"model":[35],"its":[36],"textual":[37],"content":[38],"\"bag-of-words\".":[41],"However,":[42],"this":[43,83,113,147],"kind":[44],"representation":[46,89],"does":[47],"not":[48,119],"reflect":[49],"how":[50],"people":[51],"perceive":[52],"page.":[55],"A":[56],"granular":[57,88],"document":[58],"representation,":[59],"terms":[61],"semantic":[63,69,97],"objects,":[64],"can":[65,116],"help":[66],"identifying":[68],"areas":[70],"using":[76],"them":[77],"for":[78,95,121,149],"different":[79],"IR":[80,106],"goals.":[81],"In":[82,108],"paper":[84],"we":[85,110],"use":[86],"define":[91],"new":[93,114],"metric":[94,115],"evaluating":[96],"object":[98],"importance":[99],"enhance":[102],"performance":[104],"systems.":[107],"particular":[109],"show":[111],"that":[112],"be":[117],"used":[118],"only":[120],"classification":[122],"goals,":[123],"which":[125],"instances":[126],"are":[127],"assumed":[128],"independent":[130],"identically":[132],"distributed,":[133],"but":[134],"also":[135],"gauge":[137],"strength":[139],"relationship":[141],"between":[142],"hypertextual":[143],"documents":[144],"exploit":[146],"improving":[150],"ranking":[152],"performance.":[153]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2016-06-24T00:00:00"}
