{"id":"https://openalex.org/W2115159475","doi":"https://doi.org/10.1109/iri.2004.1431469","title":"Affinity-based similarity measure for web document clustering","display_name":"Affinity-based similarity measure for web document clustering","publication_year":2005,"publication_date":"2005-05-24","ids":{"openalex":"https://openalex.org/W2115159475","doi":"https://doi.org/10.1109/iri.2004.1431469","mag":"2115159475"},"language":"en","primary_location":{"id":"doi:10.1109/iri.2004.1431469","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iri.2004.1431469","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2004 IEEE International Conference on Information Reuse and Integration, 2004. IRI 2004.","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/A5036221136","display_name":"Mei\u2010Ling Shyu","orcid":"https://orcid.org/0000-0003-0902-0844"},"institutions":[{"id":"https://openalex.org/I145608581","display_name":"University of Miami","ror":"https://ror.org/02dgjyy92","country_code":"US","type":"education","lineage":["https://openalex.org/I145608581"]},{"id":"https://openalex.org/I83328450","display_name":"Miami University","ror":"https://ror.org/05nbqxr67","country_code":"US","type":"education","lineage":["https://openalex.org/I83328450"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mei-Ling Shyu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Miami, Coral Gables, FL, USA","Dept. of Electr. & Comput. Eng., Miami Univ., Coral Gables, FL, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Miami, Coral Gables, FL, USA","institution_ids":["https://openalex.org/I145608581"]},{"raw_affiliation_string":"Dept. of Electr. & Comput. Eng., Miami Univ., Coral Gables, FL, USA#TAB#","institution_ids":["https://openalex.org/I83328450"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049219173","display_name":"Shu\u2010Ching Chen","orcid":"https://orcid.org/0000-0001-9209-390X"},"institutions":[{"id":"https://openalex.org/I19700959","display_name":"Florida International University","ror":"https://ror.org/02gz6gg07","country_code":"US","type":"education","lineage":["https://openalex.org/I19700959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shu-Ching Chen","raw_affiliation_strings":["Distributed Multimedia Information System Laboratory, School of Computer Science, Florida International University, Miami, FL, USA","FLORIDA INTERNATIONAL UNIVERSITY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Distributed Multimedia Information System Laboratory, School of Computer Science, Florida International University, Miami, FL, USA","institution_ids":["https://openalex.org/I19700959"]},{"raw_affiliation_string":"FLORIDA INTERNATIONAL UNIVERSITY","institution_ids":["https://openalex.org/I19700959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087183012","display_name":"M. Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I19700959","display_name":"Florida International University","ror":"https://ror.org/02gz6gg07","country_code":"US","type":"education","lineage":["https://openalex.org/I19700959"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Min Chen","raw_affiliation_strings":["Distributed Multimedia Information System Laboratory, School of Computer Science, Florida International University, Miami, FL, USA","FLORIDA INTERNATIONAL UNIVERSITY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Distributed Multimedia Information System Laboratory, School of Computer Science, Florida International University, Miami, FL, USA","institution_ids":["https://openalex.org/I19700959"]},{"raw_affiliation_string":"FLORIDA INTERNATIONAL UNIVERSITY","institution_ids":["https://openalex.org/I19700959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110190476","display_name":"Stuart H. Rubin","orcid":null},"institutions":[{"id":"https://openalex.org/I1339224429","display_name":"Naval Information Warfare Center Pacific","ror":"https://ror.org/01gs1cg95","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330347796","https://openalex.org/I1339224429","https://openalex.org/I2802223155","https://openalex.org/I3130687028"]},{"id":"https://openalex.org/I2802223155","display_name":"Naval Information Warfare Systems Command","ror":"https://ror.org/000ztjy10","country_code":"US","type":"government","lineage":["https://openalex.org/I1330347796","https://openalex.org/I2802223155","https://openalex.org/I3130687028"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S.H. Rubin","raw_affiliation_strings":["Center SSC San Diego, SPA WAR Systems Center, San Diego, CA, USA","Space and Naval Warfare Systems Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center SSC San Diego, SPA WAR Systems Center, San Diego, CA, USA","institution_ids":["https://openalex.org/I1339224429"]},{"raw_affiliation_string":"Space and Naval Warfare Systems Center","institution_ids":["https://openalex.org/I2802223155"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":null,"first_page":"247","last_page":"252"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9980999827384949,"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":0.9980999827384949,"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":0.9922999739646912,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9887999892234802,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7844634056091309},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7817766070365906},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.65135657787323},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.6440169811248779},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.602412223815918},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5270060896873474},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5075830221176147},{"id":"https://openalex.org/keywords/similarity-measure","display_name":"Similarity measure","score":0.4989190101623535},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.4923912286758423},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4913264811038971},{"id":"https://openalex.org/keywords/hyperlink","display_name":"Hyperlink","score":0.4870162606239319},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.48252031207084656},{"id":"https://openalex.org/keywords/euclidean-distance","display_name":"Euclidean distance","score":0.41008105874061584},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.39542460441589355},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2041357457637787},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1870618760585785}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7844634056091309},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7817766070365906},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.65135657787323},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.6440169811248779},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.602412223815918},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5270060896873474},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5075830221176147},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.4989190101623535},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.4923912286758423},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4913264811038971},{"id":"https://openalex.org/C30088001","wikidata":"https://www.wikidata.org/wiki/Q102014","display_name":"Hyperlink","level":3,"score":0.4870162606239319},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.48252031207084656},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.41008105874061584},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.39542460441589355},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2041357457637787},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1870618760585785},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iri.2004.1431469","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iri.2004.1431469","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2004 IEEE International Conference on Information Reuse and Integration, 2004. IRI 2004.","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.72.4170","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.72.4170","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.fiu.edu/~chens/PDF/iri04-sim.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1521439890","https://openalex.org/W1833785989","https://openalex.org/W1967890081","https://openalex.org/W1972645849","https://openalex.org/W2004152272","https://openalex.org/W2046878543","https://openalex.org/W2100779515","https://openalex.org/W2100958137","https://openalex.org/W2102283304","https://openalex.org/W2115593707","https://openalex.org/W2169606818","https://openalex.org/W2171216086","https://openalex.org/W2999729612","https://openalex.org/W4298882835","https://openalex.org/W6631328736","https://openalex.org/W6675619233"],"related_works":["https://openalex.org/W2379693035","https://openalex.org/W2284045667","https://openalex.org/W57923944","https://openalex.org/W2981287881","https://openalex.org/W1598081081","https://openalex.org/W2056226831","https://openalex.org/W1823511492","https://openalex.org/W4237094173","https://openalex.org/W4386612228","https://openalex.org/W3200484643"],"abstract_inverted_index":{"Compared":[0],"to":[1,20],"the":[2,5,10,14,38,41,46,55,66,74,80,100,105,110,114],"regular":[3,25],"documents,":[4],"major":[6],"distinguishing":[7],"characteristics":[8],"of":[9,57,68],"Web":[11,28,61,83],"documents":[12,84],"are":[13,92],"dynamic":[15,34],"hyper-structure.":[16],"Thus,":[17],"in":[18,78],"addition":[19],"terms":[21],"or":[22],"keywords":[23],"for":[24],"document":[26,29,58,62,120],"clustering,":[27],"clustering":[30,59,63,121],"can":[31],"incorporate":[32],"some":[33],"information":[35],"such":[36],"as":[37],"hyperlinks":[39],"and":[40,99,113],"access":[42,76],"patterns":[43,77],"extracted":[44],"from":[45],"user":[47,75],"query":[48],"logs.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53],"extend":[54],"concept":[56],"into":[60],"by":[64],"introducing":[65],"strategy":[67],"affinity-based":[69],"similarity":[70,107],"measure,":[71],"which":[72],"utilizes":[73],"determining":[79],"similarities":[81],"among":[82],"via":[85],"a":[86,95],"probabilistic":[87],"model.":[88],"Several":[89],"comparison":[90],"experiments":[91],"conducted":[93],"using":[94],"real":[96],"data":[97],"set":[98],"experimental":[101],"results":[102],"demonstrate":[103],"that":[104],"proposed":[106],"measure":[108],"outperforms":[109],"cosine":[111],"coefficient":[112],"Euclidean":[115],"distance":[116],"method":[117],"under":[118],"different":[119],"algorithms.":[122]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}