{"id":"https://openalex.org/W2150331627","doi":"https://doi.org/10.1145/1013367.1013481","title":"Distribution of relevant documents in domain-level aggregates for topic distillation","display_name":"Distribution of relevant documents in domain-level aggregates for topic distillation","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W2150331627","doi":"https://doi.org/10.1145/1013367.1013481","mag":"2150331627"},"language":"en","primary_location":{"id":"doi:10.1145/1013367.1013481","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1013367.1013481","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/A5110866799","display_name":"Vassilis Plachouras","orcid":null},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"V. Plachouras","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079046603","display_name":"Iadh Ounis","orcid":"https://orcid.org/0000-0003-4701-3223"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"I. Ounis","raw_affiliation_strings":["University of Glasgow, Glasgow, United Kingdom"],"affiliations":[{"raw_affiliation_string":"University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5110866799"],"corresponding_institution_ids":["https://openalex.org/I7882870"],"apc_list":null,"apc_paid":null,"fwci":0.4497,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.76156615,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"372","last_page":"372"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9984999895095825,"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":0.9983999729156494,"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/hyperlink","display_name":"Hyperlink","score":0.86540687084198},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.7375435829162598},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7302389144897461},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.7046912908554077},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5814379453659058},{"id":"https://openalex.org/keywords/distribution","display_name":"Distribution (mathematics)","score":0.5388407707214355},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.5174422860145569},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.44713422656059265},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3201417624950409},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.2341013252735138},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.19704174995422363},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14142516255378723},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.10068845748901367},{"id":"https://openalex.org/keywords/chromatography","display_name":"Chromatography","score":0.08848658204078674},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.0665743350982666},{"id":"https://openalex.org/keywords/nanotechnology","display_name":"Nanotechnology","score":0.05511528253555298}],"concepts":[{"id":"https://openalex.org/C30088001","wikidata":"https://www.wikidata.org/wiki/Q102014","display_name":"Hyperlink","level":3,"score":0.86540687084198},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.7375435829162598},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7302389144897461},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.7046912908554077},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5814379453659058},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.5388407707214355},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.5174422860145569},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.44713422656059265},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3201417624950409},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2341013252735138},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.19704174995422363},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14142516255378723},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.10068845748901367},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.08848658204078674},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0665743350982666},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.05511528253555298},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1013367.1013481","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1013367.1013481","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2013123195","https://openalex.org/W2026313208","https://openalex.org/W2082398795","https://openalex.org/W2085470508","https://openalex.org/W2105157020","https://openalex.org/W2166315712"],"related_works":["https://openalex.org/W2384033143","https://openalex.org/W1525584714","https://openalex.org/W2366569016","https://openalex.org/W2169968158","https://openalex.org/W1999760390","https://openalex.org/W2086877241","https://openalex.org/W2521046503","https://openalex.org/W1989883077","https://openalex.org/W2086028161","https://openalex.org/W1974853862"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,25,56],"study":[4],"the":[5,15,35,78],"distribution":[6,79],"of":[7,34,80],"relevant":[8,72,88],"documents":[9,17],"in":[10],"aggregates,":[11,60],"formed":[12],"by":[13],"grouping":[14],"retrieved":[16],"according":[18],"to":[19,70],"their":[20],"domain.":[21],"For":[22],"each":[23],"aggregate,":[24],"take":[26],"into":[27],"account":[28],"its":[29,38],"size,":[30],"and":[31,40],"a":[32,46],"measure":[33],"correlation":[36],"between":[37],"incoming":[39],"outgoing":[41],"hyperlinks.":[42],"We":[43],"report":[44],"on":[45],"preliminary":[47],"experiment":[48],"with":[49,64],"two":[50],"TREC":[51],"topic":[52],"distillation":[53],"tasks,":[54],"where":[55],"find":[57],"that":[58,77],"larger":[59],"or":[61],"those":[62],"aggregates":[63,82],"correlated":[65],"hyperlinks,":[66],"are":[67],"more":[68],"likely":[69],"contain":[71],"documents.":[73,89],"This":[74],"result":[75],"shows":[76],"domain-level":[81],"is":[83],"potentially":[84],"useful":[85],"for":[86],"finding":[87]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
