{"id":"https://openalex.org/W2092906664","doi":"https://doi.org/10.1145/1183550.1183559","title":"Coarse-grained classification of web sites by their structural properties","display_name":"Coarse-grained classification of web sites by their structural properties","publication_year":2006,"publication_date":"2006-11-10","ids":{"openalex":"https://openalex.org/W2092906664","doi":"https://doi.org/10.1145/1183550.1183559","mag":"2092906664"},"language":"en","primary_location":{"id":"doi:10.1145/1183550.1183559","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1183550.1183559","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th annual ACM international workshop on Web information and data management","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ul.qucosa.de/id/qucosa%3A32830","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068628125","display_name":"Christoph Lindemann","orcid":null},"institutions":[{"id":"https://openalex.org/I926574661","display_name":"Leipzig University","ror":"https://ror.org/03s7gtk40","country_code":"DE","type":"education","lineage":["https://openalex.org/I926574661"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christoph Lindemann","raw_affiliation_strings":["University of Leipzig, Leipzig, Germany","University of Leipzig, Leipzig, Germany,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Leipzig, Leipzig, Germany","institution_ids":["https://openalex.org/I926574661"]},{"raw_affiliation_string":"University of Leipzig, Leipzig, Germany,","institution_ids":["https://openalex.org/I926574661"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085154909","display_name":"Lars Littig","orcid":null},"institutions":[{"id":"https://openalex.org/I926574661","display_name":"Leipzig University","ror":"https://ror.org/03s7gtk40","country_code":"DE","type":"education","lineage":["https://openalex.org/I926574661"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Lars Littig","raw_affiliation_strings":["University of Leipzig, Leipzig, Germany","University of Leipzig, Leipzig, Germany,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Leipzig, Leipzig, Germany","institution_ids":["https://openalex.org/I926574661"]},{"raw_affiliation_string":"University of Leipzig, Leipzig, Germany,","institution_ids":["https://openalex.org/I926574661"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I926574661"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"35","last_page":"42"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9987000226974487,"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":0.9987000226974487,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9973999857902527,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9807000160217285,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7458019256591797},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5557615756988525},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.5225362777709961},{"id":"https://openalex.org/keywords/precision-and-recall","display_name":"Precision and recall","score":0.5090605616569519},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4903578758239746},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4865188002586365},{"id":"https://openalex.org/keywords/web-site","display_name":"Web site","score":0.4460933804512024},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.44129371643066406},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.4196526110172272},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3529086112976074},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.29428428411483765},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26951295137405396}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7458019256591797},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5557615756988525},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.5225362777709961},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5090605616569519},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4903578758239746},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4865188002586365},{"id":"https://openalex.org/C2984519610","wikidata":"https://www.wikidata.org/wiki/Q35127","display_name":"Web site","level":3,"score":0.4460933804512024},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.44129371643066406},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.4196526110172272},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3529086112976074},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.29428428411483765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26951295137405396}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1183550.1183559","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1183550.1183559","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 8th annual ACM international workshop on Web information and data management","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.88.4283","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.88.4283","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://rvs.informatik.uni-leipzig.de/de/publikationen/papers/WIDM06.pdf","raw_type":"text"},{"id":"pmh:oai:lips.informatik.uni-leipzig.de:724","is_oa":false,"landing_page_url":"http://lips.informatik.uni-leipzig.de/?q=node/724","pdf_url":null,"source":{"id":"https://openalex.org/S4377196964","display_name":"Publikation Server (Leipzig University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I926574661","host_organization_name":"Leipzig University","host_organization_lineage":["https://openalex.org/I926574661"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proc. 8th ACM International Workshop on Web Information and Data Management (WIDM 2006) , Arlington, VA, November 2006","raw_type":null},{"id":"pmh:oai:qucosa:de:qucosa:32830","is_oa":true,"landing_page_url":"https://ul.qucosa.de/id/qucosa%3A32830","pdf_url":null,"source":{"id":"https://openalex.org/S4377196435","display_name":"Qucosa (Saxon State and University Library Dresden)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I3132420320","host_organization_name":"SLUB Dresden","host_organization_lineage":["https://openalex.org/I3132420320"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:qucosa:de:qucosa:32830","is_oa":true,"landing_page_url":"https://ul.qucosa.de/id/qucosa%3A32830","pdf_url":null,"source":{"id":"https://openalex.org/S4377196435","display_name":"Qucosa (Saxon State and University Library Dresden)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I3132420320","host_organization_name":"SLUB Dresden","host_organization_lineage":["https://openalex.org/I3132420320"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1494676986","https://openalex.org/W1566984846","https://openalex.org/W1971484467","https://openalex.org/W2017337590","https://openalex.org/W2050028965","https://openalex.org/W2065168033","https://openalex.org/W2070779353","https://openalex.org/W2089800021","https://openalex.org/W2112335400","https://openalex.org/W2117209866","https://openalex.org/W2140785063","https://openalex.org/W2169557227","https://openalex.org/W2175110005","https://openalex.org/W2704966794","https://openalex.org/W2799061466","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2945931694","https://openalex.org/W2622968908","https://openalex.org/W2386849321","https://openalex.org/W144381034","https://openalex.org/W3174726539","https://openalex.org/W2083329789","https://openalex.org/W2137912379","https://openalex.org/W2134078223","https://openalex.org/W2182629206","https://openalex.org/W2415191659"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,40,127],"identify":[4],"and":[5,29,54,76,92,153],"analyze":[6],"structural":[7,18,109],"properties":[8,19,110],"which":[9,104],"reflect":[10],"the":[11,21,23,25,30,49,52,55,66,133,158,164],"functionality":[12,56],"of":[13,27,33,57,65,88,137,151,155,160],"a":[14,42,100,129,149],"Web":[15,34,58,85,96,117,138,161],"site.":[16],"These":[17],"consider":[20],"size,":[22],"organization,":[24],"composition":[26],"URLs,":[28],"link":[31],"structure":[32,53],"sites.":[35,59,139],"Opposed":[36],"to":[37,46,114],"previous":[38],"work,":[39],"perform":[41],"comprehensive":[43],"measurement":[44],"study":[45,61],"delve":[47],"into":[48,107,163],"relation":[50],"between":[51,116],"Our":[60],"focuses":[62],"on":[63,124],"five":[64],"most":[67],"relevant":[68],"functional":[69,121],"classes,":[70],"namely":[71],"Academic,":[72],"Blog,":[73],"Corporate,":[74],"Personal,":[75],"Shop.":[77],"It":[78],"is":[79],"based":[80],"upon":[81],"more":[82],"than":[83],"1,400":[84],"sites":[86,118,162],"composed":[87],"7":[89],"million":[90,94],"crawled":[91],"47":[93],"known":[95],"pages.":[97],"We":[98],"present":[99],"detailed":[101],"statistical":[102],"analysis":[103],"provides":[105],"insight":[106],"how":[108],"can":[111],"be":[112],"used":[113],"distinguish":[115],"from":[119],"different":[120],"classes.":[122,166],"Building":[123],"these":[125],"results,":[126],"introduce":[128],"content-independent":[130],"approach":[131],"for":[132,157],"automated":[134],"coarse-grained":[135],"classification":[136,159],"A":[140],"na\u00efve":[141],"Bayesian":[142],"classifier":[143],"with":[144],"advanced":[145],"density":[146],"estimation":[147],"yields":[148],"precision":[150],"82%":[152],"recall":[154],"80%":[156],"considered":[165]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
