{"id":"https://openalex.org/W2018933122","doi":"https://doi.org/10.1145/1507509.1507514","title":"Generating unambiguous URL clusters from web search","display_name":"Generating unambiguous URL clusters from web search","publication_year":2009,"publication_date":"2009-02-09","ids":{"openalex":"https://openalex.org/W2018933122","doi":"https://doi.org/10.1145/1507509.1507514","mag":"2018933122"},"language":"en","primary_location":{"id":"doi:10.1145/1507509.1507514","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1507509.1507514","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2009 workshop on Web Search Click Data","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://eprints.uwe.ac.uk/36509/1/Generating_unambiguous_URL_clusters_from_Web_searc.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036304666","display_name":"Gavin Smith","orcid":"https://orcid.org/0000-0001-5679-6309"},"institutions":[{"id":"https://openalex.org/I170239107","display_name":"University of South Australia","ror":"https://ror.org/01p93h210","country_code":"AU","type":"education","lineage":["https://openalex.org/I170239107"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"G. Smith","raw_affiliation_strings":["University of South Australia"],"affiliations":[{"raw_affiliation_string":"University of South Australia","institution_ids":["https://openalex.org/I170239107"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113501081","display_name":"Tim Brailsford","orcid":"https://orcid.org/0000-0002-0816-2093"},"institutions":[{"id":"https://openalex.org/I142263535","display_name":"University of Nottingham","ror":"https://ror.org/01ee9ar58","country_code":"GB","type":"education","lineage":["https://openalex.org/I142263535"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"T. Brailsford","raw_affiliation_strings":["University of Nottingham"],"affiliations":[{"raw_affiliation_string":"University of Nottingham","institution_ids":["https://openalex.org/I142263535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053825881","display_name":"Christoph Donner","orcid":null},"institutions":[{"id":"https://openalex.org/I170239107","display_name":"University of South Australia","ror":"https://ror.org/01p93h210","country_code":"AU","type":"education","lineage":["https://openalex.org/I170239107"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"C. Donner","raw_affiliation_strings":["University of South Australia"],"affiliations":[{"raw_affiliation_string":"University of South Australia","institution_ids":["https://openalex.org/I170239107"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048183094","display_name":"Dennis Hooijmaijers","orcid":null},"institutions":[{"id":"https://openalex.org/I170239107","display_name":"University of South Australia","ror":"https://ror.org/01p93h210","country_code":"AU","type":"education","lineage":["https://openalex.org/I170239107"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"D. Hooijmaijers","raw_affiliation_strings":["University of South Australia"],"affiliations":[{"raw_affiliation_string":"University of South Australia","institution_ids":["https://openalex.org/I170239107"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031300934","display_name":"Mark Truran","orcid":null},"institutions":[{"id":"https://openalex.org/I874055015","display_name":"Teesside University","ror":"https://ror.org/03z28gk75","country_code":"GB","type":"education","lineage":["https://openalex.org/I874055015"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"M. Truran","raw_affiliation_strings":["University of Teesside"],"affiliations":[{"raw_affiliation_string":"University of Teesside","institution_ids":["https://openalex.org/I874055015"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026654187","display_name":"James Goulding","orcid":"https://orcid.org/0000-0002-8892-6398"},"institutions":[{"id":"https://openalex.org/I142263535","display_name":"University of Nottingham","ror":"https://ror.org/01ee9ar58","country_code":"GB","type":"education","lineage":["https://openalex.org/I142263535"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"J. Goulding","raw_affiliation_strings":["University of Nottingham"],"affiliations":[{"raw_affiliation_string":"University of Nottingham","institution_ids":["https://openalex.org/I142263535"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053740034","display_name":"Helen Ashman","orcid":"https://orcid.org/0000-0003-3587-4608"},"institutions":[{"id":"https://openalex.org/I170239107","display_name":"University of South Australia","ror":"https://ror.org/01p93h210","country_code":"AU","type":"education","lineage":["https://openalex.org/I170239107"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"H. Ashman","raw_affiliation_strings":["University of South Australia"],"affiliations":[{"raw_affiliation_string":"University of South Australia","institution_ids":["https://openalex.org/I170239107"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5036304666"],"corresponding_institution_ids":["https://openalex.org/I170239107"],"apc_list":null,"apc_paid":null,"fwci":0.4516,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72603501,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"28","last_page":"34"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9983000159263611,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9983000159263611,"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/T10028","display_name":"Topic Modeling","score":0.9962999820709229,"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":0.828040361404419},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.6212056875228882},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6169448494911194},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5934431552886963},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4530175030231476},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.23095515370368958},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.069949209690094}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.828040361404419},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.6212056875228882},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6169448494911194},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5934431552886963},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4530175030231476},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.23095515370368958},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.069949209690094},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1507509.1507514","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1507509.1507514","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2009 workshop on Web Search Click Data","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.169.2049","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.169.2049","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://acrc.unisa.edu.au/wp-content/uploads/2009/05/smith.pdf","raw_type":"text"},{"id":"pmh:oai:eprints.uwe.ac.uk:36509","is_oa":true,"landing_page_url":"http://eprints.uwe.ac.uk/36509/1/Generating_unambiguous_URL_clusters_from_Web_searc.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306401464","display_name":"UWE Research Repository (UWE Bristol)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I178535277","host_organization_name":"University of the West of England","host_organization_lineage":["https://openalex.org/I178535277"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"},{"id":"pmh:oai:tees.openrepository.com:10149/94119","is_oa":false,"landing_page_url":"http://hdl.handle.net/10149/94119","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Meetings and Proceedings"}],"best_oa_location":{"id":"pmh:oai:eprints.uwe.ac.uk:36509","is_oa":true,"landing_page_url":"http://eprints.uwe.ac.uk/36509/1/Generating_unambiguous_URL_clusters_from_Web_searc.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306401464","display_name":"UWE Research Repository (UWE Bristol)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I178535277","host_organization_name":"University of the West of England","host_organization_lineage":["https://openalex.org/I178535277"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1486670681","https://openalex.org/W1531195949","https://openalex.org/W1555354714","https://openalex.org/W1972645849","https://openalex.org/W1978486030","https://openalex.org/W2034184069","https://openalex.org/W2041179002","https://openalex.org/W2129520810","https://openalex.org/W2143956100","https://openalex.org/W2160555926"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W1967370444","https://openalex.org/W2157408137","https://openalex.org/W2150136235","https://openalex.org/W2085215424","https://openalex.org/W4312252109","https://openalex.org/W2000745862"],"abstract_inverted_index":{"This":[0,83],"paper":[1,97],"reports":[2,98],"on":[3,88,99,106],"the":[4,15,45,59,69,72,107,110],"generation":[5],"of":[6,9,71,81],"unambiguous":[7],"clusters":[8,74],"URLs":[10,46],"from":[11,14,31,101],"clickthrough":[12],"data":[13],"MSN":[16],"search":[17],"query":[18,34],"log":[19],"excerpt":[20],"(the":[21],"RFP":[22,111],"2006":[23,112],"dataset).":[24],"Selections":[25],"(clickthroughs)":[26],"by":[27],"a":[28,32,62,103],"single":[29,33,63],"user":[30],"can":[35,51,75],"be":[36,52,76],"assumed":[37],"to":[38,54,109],"have":[39],"some":[40],"mutual":[41],"semantic":[42],"relevance,":[43],"and":[44,90,95],"coselected":[47],"in":[48],"this":[49,96],"way":[50],"aggregated":[53],"form":[55],"single-sense":[56],"clusters.":[57],"When":[58],"graphs":[60],"for":[61],"term":[64],"separate":[65],"into":[66],"distinct":[67,73],"clusters,":[68],"semantics":[70],"interpreted":[77],"as":[78],"disambiguated":[79],"aggregations":[80],"URLs.":[82],"principle":[84,108],"had":[85],"been":[86],"tested":[87],"smaller":[89],"more":[91],"constrained":[92],"datasets":[93],"previously,":[94],"findings":[100],"applying":[102],"method":[104],"based":[105],"dataset.":[113]},"counts_by_year":[{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
