{"id":"https://openalex.org/W2009761865","doi":"https://doi.org/10.1145/1498759.1498809","title":"Clustering the tagged web","display_name":"Clustering the tagged web","publication_year":2009,"publication_date":"2009-02-09","ids":{"openalex":"https://openalex.org/W2009761865","doi":"https://doi.org/10.1145/1498759.1498809","mag":"2009761865"},"language":"en","primary_location":{"id":"doi:10.1145/1498759.1498809","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1498759.1498809","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},"type":"conference-paper","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/A5071710055","display_name":"Daniel Ramage","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105015","display_name":"Stanford Health Care","ror":"https://ror.org/019wqcg20","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210105015"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Ramage","raw_affiliation_strings":["Serra Mall, Stanford, CA","Serra Mall, Stanford, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Serra Mall, Stanford, CA","institution_ids":["https://openalex.org/I4210105015"]},{"raw_affiliation_string":"Serra Mall, Stanford, CA#TAB#","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114253779","display_name":"Paul Heymann","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105015","display_name":"Stanford Health Care","ror":"https://ror.org/019wqcg20","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210105015"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul Heymann","raw_affiliation_strings":["Serra Mall, Stanford, CA","Serra Mall, Stanford, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Serra Mall, Stanford, CA","institution_ids":["https://openalex.org/I4210105015"]},{"raw_affiliation_string":"Serra Mall, Stanford, CA#TAB#","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046006076","display_name":"Christopher D. Manning","orcid":"https://orcid.org/0000-0001-6155-649X"},"institutions":[{"id":"https://openalex.org/I4210105015","display_name":"Stanford Health Care","ror":"https://ror.org/019wqcg20","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210105015"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher D. Manning","raw_affiliation_strings":["Serra Mall, Stanford, CA","Serra Mall, Stanford, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Serra Mall, Stanford, CA","institution_ids":["https://openalex.org/I4210105015"]},{"raw_affiliation_string":"Serra Mall, Stanford, CA#TAB#","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055883336","display_name":"H\u00e9ctor Garc\u00eda-Molina","orcid":null},"institutions":[{"id":"https://openalex.org/I4210105015","display_name":"Stanford Health Care","ror":"https://ror.org/019wqcg20","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I4210105015"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hector Garcia-Molina","raw_affiliation_strings":["Serra Mall, Stanford, CA","Serra Mall, Stanford, CA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Serra Mall, Stanford, CA","institution_ids":["https://openalex.org/I4210105015"]},{"raw_affiliation_string":"Serra Mall, Stanford, CA#TAB#","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":31.2298,"has_fulltext":false,"cited_by_count":219,"citation_normalized_percentile":{"value":0.99706206,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"54","last_page":"63"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9990000128746033,"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"}},{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9979000091552734,"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/T11106","display_name":"Data Management and Algorithms","score":0.9922000169754028,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.8278013467788696},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7844318151473999},{"id":"https://openalex.org/keywords/latent-dirichlet-allocation","display_name":"Latent Dirichlet allocation","score":0.6966010332107544},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.6850032210350037},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5617114305496216},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5453091263771057},{"id":"https://openalex.org/keywords/directory","display_name":"Directory","score":0.5195013284683228},{"id":"https://openalex.org/keywords/topic-model","display_name":"Topic model","score":0.4073617458343506},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.39675021171569824},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.31811681389808655},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24431633949279785}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8278013467788696},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7844318151473999},{"id":"https://openalex.org/C500882744","wikidata":"https://www.wikidata.org/wiki/Q269236","display_name":"Latent Dirichlet allocation","level":3,"score":0.6966010332107544},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.6850032210350037},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5617114305496216},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5453091263771057},{"id":"https://openalex.org/C2777683733","wikidata":"https://www.wikidata.org/wiki/Q201456","display_name":"Directory","level":2,"score":0.5195013284683228},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.4073617458343506},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.39675021171569824},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.31811681389808655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24431633949279785},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1498759.1498809","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1498759.1498809","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Second ACM International Conference on Web Search and Data Mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.155.317","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.155.317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://nlp.stanford.edu/cmanning/papers/cluster-wsdm09.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.461.8390","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.461.8390","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://ilpubs.stanford.edu:8090/890/1/wsdm09.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8199999928474426,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W157719725","https://openalex.org/W202113353","https://openalex.org/W1489992655","https://openalex.org/W1522930108","https://openalex.org/W1532325895","https://openalex.org/W1549014378","https://openalex.org/W1604437383","https://openalex.org/W1880262756","https://openalex.org/W1965067550","https://openalex.org/W1996764654","https://openalex.org/W2001082470","https://openalex.org/W2007395264","https://openalex.org/W2020133434","https://openalex.org/W2020842694","https://openalex.org/W2042980227","https://openalex.org/W2064522604","https://openalex.org/W2066073289","https://openalex.org/W2066180141","https://openalex.org/W2074449313","https://openalex.org/W2091808810","https://openalex.org/W2096748234","https://openalex.org/W2100958137","https://openalex.org/W2107743791","https://openalex.org/W2110441437","https://openalex.org/W2114804204","https://openalex.org/W2116237179","https://openalex.org/W2120721759","https://openalex.org/W2124916819","https://openalex.org/W2130395434","https://openalex.org/W2141282920","https://openalex.org/W2147152072","https://openalex.org/W2147709600","https://openalex.org/W2158337386","https://openalex.org/W2162495634","https://openalex.org/W2164898661","https://openalex.org/W2167429226","https://openalex.org/W2170344111","https://openalex.org/W2435251607","https://openalex.org/W2440833291","https://openalex.org/W4233135949","https://openalex.org/W4241122026"],"related_works":["https://openalex.org/W2769501189","https://openalex.org/W4315588616","https://openalex.org/W4312773271","https://openalex.org/W2888805565","https://openalex.org/W2962686197","https://openalex.org/W2207653751","https://openalex.org/W2611137333","https://openalex.org/W3005513013","https://openalex.org/W4317422773","https://openalex.org/W2529577912"],"abstract_inverted_index":{"Automatically":[0],"clustering":[1,48,62,82],"web":[2,50,106],"pages":[3],"into":[4],"semantic":[5],"groups":[6],"promises":[7],"improved":[8],"search":[9],"and":[10,42,77,93],"browsing":[11],"on":[12,85],"the":[13,55,97,111,132],"web.":[14],"In":[15],"this":[16],"paper,":[17],"we":[18],"demonstrate":[19],"how":[20],"user-generated":[21],"tags":[22,58,71],"from":[23],"large-scale":[24],"social":[25],"bookmarking":[26],"websites":[27],"such":[28],"as":[29,34,72,74],"del.icio.us":[30],"can":[31,129],"be":[32],"used":[33],"a":[35,79,125,138],"complementary":[36],"data":[37,116],"source":[38],"to":[39,103],"page":[40,75,121],"text":[41,44,76,92,122],"anchor":[43],"for":[45],"improving":[46],"automatic":[47],"of":[49,57,114,134,144],"pages.":[51],"This":[52],"paper":[53],"explores":[54],"use":[56],"in":[59,63],"1)":[60],"K-means":[61,150],"an":[64,104],"extended":[65],"vector":[66],"space":[67],"model":[68,148],"that":[69,89,110],"includes":[70],"well":[73],"2)":[78],"novel":[80],"generative":[81,147],"algorithm":[83],"based":[84],"latent":[86],"Dirichlet":[87],"allocation":[88],"jointly":[90],"models":[91,98,136],"tags.":[94],"We":[95,108],"evaluate":[96],"by":[99],"comparing":[100],"their":[101],"output":[102],"established":[105],"directory.":[107],"find":[109],"naive":[112],"inclusion":[113,128],"tagging":[115],"improves":[117],"cluster":[118],"quality":[119,133],"versus":[120],"alone,":[123],"but":[124],"more":[126],"principled":[127],"substantially":[130],"improve":[131],"all":[135],"with":[137,151],"statistically":[139],"significant":[140],"absolute":[141],"F-score":[142,154],"increase":[143],"4%.":[145],"The":[146],"outperforms":[149],"another":[152],"8%":[153],"increase.":[155]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":11},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":23},{"year":2013,"cited_by_count":19},{"year":2012,"cited_by_count":25}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}