{"id":"https://openalex.org/W2095478124","doi":"https://doi.org/10.1145/1541880.1541884","title":"A survey of Web clustering engines","display_name":"A survey of Web clustering engines","publication_year":2009,"publication_date":"2009-07-01","ids":{"openalex":"https://openalex.org/W2095478124","doi":"https://doi.org/10.1145/1541880.1541884","mag":"2095478124"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/1541880.1541884","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"review","type_crossref":"journal-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://search.fub.it/claudio/pdf/CSUR09.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5089034149","display_name":"Claudio Carpineto","orcid":"https://orcid.org/0009-0003-1051-9308"},"institutions":[{"id":"https://openalex.org/I2802782265","display_name":"Fondazione \"Ugo Bordoni\"","ror":"https://ror.org/01kc65v41","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2802782265"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Claudio Carpineto","raw_affiliation_strings":["Fondazione Ugo Bordoni, Roma, Italy"],"affiliations":[{"raw_affiliation_string":"Fondazione Ugo Bordoni, Roma, Italy","institution_ids":["https://openalex.org/I2802782265"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072945192","display_name":"Stanis\u0142aw Osi\u0144ski","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stanislaw Osi\u0144ski","raw_affiliation_strings":["Carrot Search"],"affiliations":[{"raw_affiliation_string":"Carrot Search","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036432554","display_name":"Giovanni Romano","orcid":"https://orcid.org/0009-0007-4611-1514"},"institutions":[{"id":"https://openalex.org/I2802782265","display_name":"Fondazione \"Ugo Bordoni\"","ror":"https://ror.org/01kc65v41","country_code":"IT","type":"facility","lineage":["https://openalex.org/I2802782265"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giovanni Romano","raw_affiliation_strings":["Fondazione Ugo Bordoni, Roma, Italy"],"affiliations":[{"raw_affiliation_string":"Fondazione Ugo Bordoni, Roma, Italy","institution_ids":["https://openalex.org/I2802782265"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061873963","display_name":"Dawid Weiss","orcid":null},"institutions":[{"id":"https://openalex.org/I46597724","display_name":"Pozna\u0144 University of Technology","ror":"https://ror.org/00p7p3302","country_code":"PL","type":"education","lineage":["https://openalex.org/I46597724"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Dawid Weiss","raw_affiliation_strings":["Poznan University of Technology, Poznan, Poland."],"affiliations":[{"raw_affiliation_string":"Poznan University of Technology, Poznan, Poland.","institution_ids":["https://openalex.org/I46597724"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":26.106,"has_fulltext":false,"cited_by_count":406,"citation_normalized_percentile":{"value":0.991228,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"41","issue":"3","first_page":"1","last_page":"38"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9994,"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":0.9994,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9963,"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/T11106","display_name":"Data Management and Algorithms","score":0.9958,"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/brown-clustering","display_name":"Brown clustering","score":0.49628478},{"id":"https://openalex.org/keywords/conceptual-clustering","display_name":"Conceptual clustering","score":0.4599236}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8776903},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8355166},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6485976},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5719067},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.5074758},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5046245},{"id":"https://openalex.org/C167984511","wikidata":"https://www.wikidata.org/wiki/Q17003931","display_name":"Brown clustering","level":5,"score":0.49628478},{"id":"https://openalex.org/C39235581","wikidata":"https://www.wikidata.org/wiki/Q5158434","display_name":"Conceptual clustering","level":5,"score":0.4599236},{"id":"https://openalex.org/C17212007","wikidata":"https://www.wikidata.org/wiki/Q5511111","display_name":"Fuzzy clustering","level":3,"score":0.40622187},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.32793748},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.253403},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20297986}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1145/1541880.1541884","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.157.6436","pdf_url":"http://search.fub.it/claudio/pdf/CSUR09.pdf","source":{"id":"https://openalex.org/S4306400349","display_name":"CiteSeer X (The Pennsylvania State University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I130769515","host_organization_name":"Pennsylvania State University","host_organization_lineage":["https://openalex.org/I130769515"],"host_organization_lineage_names":["Pennsylvania State University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.157.6436","pdf_url":"http://search.fub.it/claudio/pdf/CSUR09.pdf","source":{"id":"https://openalex.org/S4306400349","display_name":"CiteSeer X (The Pennsylvania State University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I130769515","host_organization_name":"Pennsylvania State University","host_organization_lineage":["https://openalex.org/I130769515"],"host_organization_lineage_names":["Pennsylvania State University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":121,"referenced_works":["https://openalex.org/W1491393069","https://openalex.org/W1495011550","https://openalex.org/W1500092210","https://openalex.org/W1503729935","https://openalex.org/W1512658957","https://openalex.org/W1532325895","https://openalex.org/W1533168581","https://openalex.org/W1537696678","https://openalex.org/W1539781829","https://openalex.org/W1548171311","https://openalex.org/W1552319112","https://openalex.org/W1553406086","https://openalex.org/W1553682320","https://openalex.org/W1555011919","https://openalex.org/W1570127741","https://openalex.org/W1573043584","https://openalex.org/W1574901103","https://openalex.org/W1586180959","https://openalex.org/W1595535037","https://openalex.org/W182489289","https://openalex.org/W1828298795","https://openalex.org/W1857054846","https://openalex.org/W190289764","https://openalex.org/W1971784203","https://openalex.org/W1974782086","https://openalex.org/W1976719972","https://openalex.org/W1977819398","https://openalex.org/W1978799369","https://openalex.org/W1980376361","https://openalex.org/W1982078690","https://openalex.org/W1990845847","https://openalex.org/W1992419399","https://openalex.org/W1992709202","https://openalex.org/W1996764654","https://openalex.org/W1999235772","https://openalex.org/W2003650253","https://openalex.org/W2004360803","https://openalex.org/W201179911","https://openalex.org/W2021457058","https://openalex.org/W2022828110","https://openalex.org/W2025162602","https://openalex.org/W2026743036","https://openalex.org/W2030470432","https://openalex.org/W2038519936","https://openalex.org/W2039346806","https://openalex.org/W2040058125","https://openalex.org/W2040221623","https://openalex.org/W2040928194","https://openalex.org/W2043747172","https://openalex.org/W2045812729","https://openalex.org/W2047032662","https://openalex.org/W2053606794","https://openalex.org/W2054274648","https://openalex.org/W2054816608","https://openalex.org/W2055150316","https://openalex.org/W2059513841","https://openalex.org/W2061198046","https://openalex.org/W2066073289","https://openalex.org/W2073433993","https://openalex.org/W2074449313","https://openalex.org/W2096700676","https://openalex.org/W2096815466","https://openalex.org/W2097125878","https://openalex.org/W2097720891","https://openalex.org/W2098162425","https://openalex.org/W2100958137","https://openalex.org/W2103986443","https://openalex.org/W2104217798","https://openalex.org/W2106441507","https://openalex.org/W2107838985","https://openalex.org/W2110441437","https://openalex.org/W2116237179","https://openalex.org/W2118020653","https://openalex.org/W2119210561","https://openalex.org/W2121996546","https://openalex.org/W2126631147","https://openalex.org/W2127053467","https://openalex.org/W2128341918","https://openalex.org/W2129066856","https://openalex.org/W2129223612","https://openalex.org/W2130395434","https://openalex.org/W2131840460","https://openalex.org/W2132341030","https://openalex.org/W2134089414","https://openalex.org/W2137256672","https://openalex.org/W2139280638","https://openalex.org/W2139653758","https://openalex.org/W2143079043","https://openalex.org/W2145036943","https://openalex.org/W2146872957","https://openalex.org/W2147152072","https://openalex.org/W2147159144","https://openalex.org/W2147468287","https://openalex.org/W2155194165","https://openalex.org/W2156037541","https://openalex.org/W2158275940","https://openalex.org/W2158529844","https://openalex.org/W2158651412","https://openalex.org/W2158874082","https://openalex.org/W2159757173","https://openalex.org/W2160799467","https://openalex.org/W2160893714","https://openalex.org/W2161884853","https://openalex.org/W2164755290","https://openalex.org/W2165612380","https://openalex.org/W2171593626","https://openalex.org/W2313094819","https://openalex.org/W2435251607","https://openalex.org/W2483571705","https://openalex.org/W2504358273","https://openalex.org/W2561675875","https://openalex.org/W2580302247","https://openalex.org/W2612166593","https://openalex.org/W2913066018","https://openalex.org/W2963673689","https://openalex.org/W369619126","https://openalex.org/W4206790557","https://openalex.org/W4241122026","https://openalex.org/W4255318870","https://openalex.org/W4285719527","https://openalex.org/W4292013700"],"related_works":["https://openalex.org/W3140018618","https://openalex.org/W3037575264","https://openalex.org/W2622412490","https://openalex.org/W2557733197","https://openalex.org/W2519801912","https://openalex.org/W2186905933","https://openalex.org/W2160785859","https://openalex.org/W2067669858","https://openalex.org/W2049890817","https://openalex.org/W182213215"],"abstract_inverted_index":{"Web":[0,38,101],"clustering":[1,39,49,69,89,102],"engines":[2,103],"organize":[3],"search":[4,20,46],"results":[5,53],"by":[6,18,67,76],"topic,":[7],"thus":[8],"offering":[9],"a":[10,37,97],"complementary":[11],"view":[12],"to":[13,85,108],"the":[14,27,34,55,58,73,77,80,88,93],"flat-ranked":[15],"list":[16],"returned":[17],"conventional":[19],"engines.":[21],"In":[22],"this":[23],"survey,":[24],"we":[25],"discuss":[26,106],"issues":[28],"that":[29,63],"must":[30],"be":[31,65],"addressed":[32,66],"in":[33],"development":[35],"of":[36,45,57,79,96,99],"engine,":[40],"including":[41],"acquisition":[42],"and":[43,50,104],"preprocessing":[44],"results,":[47],"their":[48,110],"visualization.":[51],"Search":[52],"clustering,":[54],"core":[56],"system,":[59],"has":[60],"specific":[61],"requirements":[62],"cannot":[64],"classical":[68],"algorithms.":[70],"We":[71,91],"emphasize":[72],"role":[74],"played":[75],"quality":[78],"cluster":[81],"labels":[82],"as":[83],"opposed":[84],"optimizing":[86],"only":[87],"structure.":[90],"highlight":[92],"main":[94],"characteristics":[95],"number":[98],"existing":[100],"also":[105],"how":[107],"evaluate":[109],"retrieval":[111],"performance.":[112],"Some":[113],"directions":[114],"for":[115],"future":[116],"research":[117],"are":[118],"finally":[119],"presented.":[120]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2095478124","counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":18},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":21},{"year":2016,"cited_by_count":29},{"year":2015,"cited_by_count":35},{"year":2014,"cited_by_count":41},{"year":2013,"cited_by_count":51},{"year":2012,"cited_by_count":61}],"updated_date":"2024-12-19T07:38:30.926085","created_date":"2016-06-24"}