{"id":"https://openalex.org/W2151888610","doi":"https://doi.org/10.1145/1013367.1013438","title":"Matching web site structure and content","display_name":"Matching web site structure and content","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W2151888610","doi":"https://doi.org/10.1145/1013367.1013438","mag":"2151888610"},"language":"en","primary_location":{"id":"doi:10.1145/1013367.1013438","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1013367.1013438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th international World Wide Web conference on Alternate track papers &amp; posters  - WWW Alt. '04","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/A5011311291","display_name":"Vassil Gedov","orcid":null},"institutions":[{"id":"https://openalex.org/I25974101","display_name":"University of W\u00fcrzburg","ror":"https://ror.org/00fbnyb24","country_code":"DE","type":"education","lineage":["https://openalex.org/I25974101"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Vassil Gedov","raw_affiliation_strings":["University of W\u00fcrzburg, Germany"],"affiliations":[{"raw_affiliation_string":"University of W\u00fcrzburg, Germany","institution_ids":["https://openalex.org/I25974101"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056072935","display_name":"Carsten Stolz","orcid":null},"institutions":[{"id":"https://openalex.org/I199417121","display_name":"Catholic University of Eichst\u00e4tt-Ingolstadt","ror":"https://ror.org/00mx91s63","country_code":"DE","type":"education","lineage":["https://openalex.org/I199417121"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Carsten Stolz","raw_affiliation_strings":["University of Eichst\u00e4ett-Ingolstadt, Germany"],"affiliations":[{"raw_affiliation_string":"University of Eichst\u00e4ett-Ingolstadt, Germany","institution_ids":["https://openalex.org/I199417121"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016409536","display_name":"Ralph Neuneier","orcid":null},"institutions":[{"id":"https://openalex.org/I1325886976","display_name":"Siemens (Germany)","ror":"https://ror.org/059mq0909","country_code":"DE","type":"company","lineage":["https://openalex.org/I1325886976"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ralph Neuneier","raw_affiliation_strings":["Siemens AG - Corporate Technology, Germany"],"affiliations":[{"raw_affiliation_string":"Siemens AG - Corporate Technology, Germany","institution_ids":["https://openalex.org/I1325886976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034004640","display_name":"Micha\u0142 Skubacz","orcid":null},"institutions":[{"id":"https://openalex.org/I1325886976","display_name":"Siemens (Germany)","ror":"https://ror.org/059mq0909","country_code":"DE","type":"company","lineage":["https://openalex.org/I1325886976"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Michal Skubacz","raw_affiliation_strings":["Siemens AG - Corporate Technology, Germany"],"affiliations":[{"raw_affiliation_string":"Siemens AG - Corporate Technology, Germany","institution_ids":["https://openalex.org/I1325886976"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084058235","display_name":"Dietmar Seipel","orcid":null},"institutions":[{"id":"https://openalex.org/I25974101","display_name":"University of W\u00fcrzburg","ror":"https://ror.org/00fbnyb24","country_code":"DE","type":"education","lineage":["https://openalex.org/I25974101"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Dietmar Seipel","raw_affiliation_strings":["University of W\u00fcerzburg, Germany"],"affiliations":[{"raw_affiliation_string":"University of W\u00fcerzburg, Germany","institution_ids":["https://openalex.org/I25974101"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5011311291"],"corresponding_institution_ids":["https://openalex.org/I25974101"],"apc_list":null,"apc_paid":null,"fwci":2.4224,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.91933325,"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":"286","last_page":"286"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9991000294685364,"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":0.9991000294685364,"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/T13976","display_name":"Web visibility and informetrics","score":0.9901999831199646,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9869999885559082,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7137140035629272},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.5617419481277466},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5202635526657104},{"id":"https://openalex.org/keywords/web-site","display_name":"Web site","score":0.465232789516449},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.46255698800086975},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4389280080795288},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.24931174516677856},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13707369565963745},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12941506505012512}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7137140035629272},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.5617419481277466},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5202635526657104},{"id":"https://openalex.org/C2984519610","wikidata":"https://www.wikidata.org/wiki/Q35127","display_name":"Web site","level":3,"score":0.465232789516449},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.46255698800086975},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4389280080795288},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.24931174516677856},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13707369565963745},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12941506505012512},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1013367.1013438","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1013367.1013438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th international World Wide Web conference on Alternate track papers &amp; posters  - WWW Alt. '04","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1.7313","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1.7313","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.www2004.org/proceedings/docs/2p286.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W1506845741","https://openalex.org/W2052142057","https://openalex.org/W2079672501"],"related_works":["https://openalex.org/W255623911","https://openalex.org/W291827334","https://openalex.org/W1601617767","https://openalex.org/W2766007331","https://openalex.org/W2027911892","https://openalex.org/W2520355961","https://openalex.org/W1606752009","https://openalex.org/W4245697572","https://openalex.org/W277486614","https://openalex.org/W2419063854"],"abstract_inverted_index":{"To":[0],"keep":[1],"an":[2,29,74],"overview":[3],"of":[4,17,48,62,92,111,141],"a":[5,60,77,93,105,142],"complex":[6],"corporate":[7],"web":[8,37,50,57,94,125,143],"sites,":[9],"it":[10],"is":[11,32],"crucial":[12],"to":[13,35],"understand":[14],"the":[15,21,41,46,49,70,89,109,136],"relationship":[16,91],"contents,":[18],"structure":[19,47,72,138],"and":[20,96,139],"user's":[22],"behavior.":[23],"In":[24,99],"this":[25,67,100],"paper,":[26],"we":[27,85,102,116,130],"describe":[28],"approach":[30,129],"which":[31,120],"allowing":[33],"us":[34],"compare":[36],"page":[38,58,95,106],"content":[39,110,140],"with":[40,59,69,145],"information":[42,68],"implictly":[43],"defined":[44],"by":[45,54,134],"site.":[51],"We":[52,65],"start":[53],"describing":[55],"each":[56],"set":[61],"key":[63],"words.":[64],"combine":[66],"link":[71],"in":[73,108],"algorithm":[75],"generating":[76],"context":[78],"based":[79],"description.":[80],"By":[81],"comparing":[82],"both":[83],"descriptions,":[84],"draw":[86],"conclusions":[87],"about":[88],"semantic":[90],"its":[97,112],"neighbourhood.":[98,113],"way,":[101],"indicate":[103],"whether":[104],"fits":[107],"Doing":[114],"this,":[115],"implicitly":[117],"identify":[118],"topics":[119],"span":[121],"over":[122],"several":[123],"connected":[124],"pages.":[126],"With":[127],"our":[128],"support":[131],"redesign":[132],"processes":[133],"assessing":[135],"actual":[137],"site":[144],"designer's":[146],"concepts.":[147]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
