{"id":"https://openalex.org/W2104890789","doi":"https://doi.org/10.1145/1141277.1141527","title":"A scalable algorithm for high-quality clustering of web snippets","display_name":"A scalable algorithm for high-quality clustering of web snippets","publication_year":2006,"publication_date":"2006-04-23","ids":{"openalex":"https://openalex.org/W2104890789","doi":"https://doi.org/10.1145/1141277.1141527","mag":"2104890789"},"language":"en","primary_location":{"id":"doi:10.1145/1141277.1141527","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1141277.1141527","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 ACM symposium on Applied computing","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/A5033343264","display_name":"Filippo Geraci","orcid":"https://orcid.org/0000-0001-6993-6761"},"institutions":[{"id":"https://openalex.org/I102064193","display_name":"University of Siena","ror":"https://ror.org/01tevnk56","country_code":"IT","type":"education","lineage":["https://openalex.org/I102064193"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Filippo Geraci","raw_affiliation_strings":["Consiglio Nazionale delle Ricerche, Pisa, Italy and Universit\u00e0 di Siena, Via Roma, Siena, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Consiglio Nazionale delle Ricerche, Pisa, Italy and Universit\u00e0 di Siena, Via Roma, Siena, Italy","institution_ids":["https://openalex.org/I102064193"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028551838","display_name":"Marco Pellegrini","orcid":"https://orcid.org/0000-0003-3151-9481"},"institutions":[{"id":"https://openalex.org/I4210107558","display_name":"Consorzio Pisa Ricerche","ror":"https://ror.org/01t0n3b84","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210107558"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marco Pellegrini","raw_affiliation_strings":["Consiglio Nazionale delle Ricerche, Pisa, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Consiglio Nazionale delle Ricerche, Pisa, Italy","institution_ids":["https://openalex.org/I4210107558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057848120","display_name":"Paolo Pisati","orcid":null},"institutions":[{"id":"https://openalex.org/I4210107558","display_name":"Consorzio Pisa Ricerche","ror":"https://ror.org/01t0n3b84","country_code":"IT","type":"facility","lineage":["https://openalex.org/I4210107558"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Paolo Pisati","raw_affiliation_strings":["Consiglio Nazionale delle Ricerche, Pisa, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Consiglio Nazionale delle Ricerche, Pisa, Italy","institution_ids":["https://openalex.org/I4210107558"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063975186","display_name":"Fabrizio Sebastiani","orcid":"https://orcid.org/0000-0003-4221-6427"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Fabrizio Sebastiani","raw_affiliation_strings":["Universit\u00e0 di Padova, Padova, Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e0 di Padova, Padova, Italy","institution_ids":["https://openalex.org/I138689650"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.1755,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.92741024,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1058","last_page":"1062"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9994999766349792,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9994999766349792,"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":0.9962999820709229,"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"}},{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.9848999977111816,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/cluster-analysis","display_name":"Cluster analysis","score":0.8127788305282593},{"id":"https://openalex.org/keywords/snippet","display_name":"Snippet","score":0.7992844581604004},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7914556264877319},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6765362024307251},{"id":"https://openalex.org/keywords/canopy-clustering-algorithm","display_name":"Canopy clustering algorithm","score":0.5501042008399963},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.5392081141471863},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5193032622337341},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5166692733764648},{"id":"https://openalex.org/keywords/data-stream-clustering","display_name":"Data stream clustering","score":0.4660986661911011},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.4505902826786041},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.44941624999046326},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.44663190841674805},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.41869622468948364},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.2227863073348999},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.20271000266075134},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.18994009494781494}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8127788305282593},{"id":"https://openalex.org/C2777822670","wikidata":"https://www.wikidata.org/wiki/Q1120538","display_name":"Snippet","level":2,"score":0.7992844581604004},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7914556264877319},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6765362024307251},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.5501042008399963},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.5392081141471863},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5193032622337341},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5166692733764648},{"id":"https://openalex.org/C193143536","wikidata":"https://www.wikidata.org/wiki/Q5227360","display_name":"Data stream clustering","level":5,"score":0.4660986661911011},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.4505902826786041},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.44941624999046326},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.44663190841674805},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41869622468948364},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2227863073348999},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.20271000266075134},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.18994009494781494},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1141277.1141527","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1141277.1141527","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2006 ACM symposium on Applied computing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.721.4536","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.721.4536","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://wwwold.iit.cnr.it/staff/marco.pellegrini/papiri/kboost-2009.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.49000000953674316}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W182666420","https://openalex.org/W190289764","https://openalex.org/W299839057","https://openalex.org/W1487761086","https://openalex.org/W1500092210","https://openalex.org/W1522930108","https://openalex.org/W1530232144","https://openalex.org/W1651093245","https://openalex.org/W1973264045","https://openalex.org/W1980317569","https://openalex.org/W2048239613","https://openalex.org/W2073849744","https://openalex.org/W2074449313","https://openalex.org/W2100958137","https://openalex.org/W2125095221","https://openalex.org/W2127218421","https://openalex.org/W2133311553","https://openalex.org/W2147159144","https://openalex.org/W6631307971","https://openalex.org/W6637231022"],"related_works":["https://openalex.org/W2559422900","https://openalex.org/W3144143113","https://openalex.org/W2491448268","https://openalex.org/W4306940721","https://openalex.org/W2181939267","https://openalex.org/W2892323093","https://openalex.org/W3174322327","https://openalex.org/W2160785859","https://openalex.org/W3120229345","https://openalex.org/W2394193399"],"abstract_inverted_index":{"We":[0,28,49],"consider":[1],"the":[2,30,46,68,94,98,112,116,119,125],"problem":[3],"of":[4,16,63,67,82,93,115,122],"partitioning,":[5],"in":[6,20,37,107],"a":[7,14,21,41,91],"highly":[8,11],"accurate":[9],"and":[10,87],"efficient":[12],"way,":[13],"set":[15],"n":[17],"documents":[18],"lying":[19],"metric":[22,38],"space":[23],"into":[24],"k":[25],"non-overlapping":[26],"clusters.":[27],"augment":[29],"well-known":[31],"furthest-point-first":[32],"algorithm":[33,52,101],"for":[34],"k-center":[35],"clustering":[36,129],"spaces":[39],"with":[40],"filtering":[42],"scheme":[43],"based":[44],"on":[45],"triangular":[47],"inequality.":[48],"apply":[50],"this":[51,89],"to":[53],"Web":[54,108],"snippet":[55,109],"clustering,":[56,110],"comparing":[57],"it":[58],"against":[59],"strong":[60],"baselines":[61],"consisting":[62],"recent,":[64],"fast":[65],"variants":[66],"classical":[69],"k-means":[70],"iterative":[71],"algorithm.":[72],"Our":[73,100],"main":[74],"conclusion":[75],"is":[76,102],"that":[77],"our":[78],"method":[79],"attains":[80],"solutions":[81],"better":[83],"or":[84,118],"comparable":[85],"accuracy,":[86],"does":[88],"within":[90],"fraction":[92],"time":[95],"required":[96],"by":[97],"baselines.":[99],"thus":[103],"valuable":[104],"when,":[105],"as":[106],"either":[111],"real-time":[113],"nature":[114],"task":[117],"large":[120],"amount":[121],"data":[123],"make":[124],"poorly":[126],"scalable,":[127],"traditional":[128],"methods":[130],"unsuitable.":[131]},"counts_by_year":[{"year":2015,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}