{"id":"https://openalex.org/W2146013359","doi":"https://doi.org/10.1109/cidm.2011.5949449","title":"Geodesic distances for web document clustering","display_name":"Geodesic distances for web document clustering","publication_year":2011,"publication_date":"2011-04-01","ids":{"openalex":"https://openalex.org/W2146013359","doi":"https://doi.org/10.1109/cidm.2011.5949449","mag":"2146013359"},"language":"en","primary_location":{"id":"doi:10.1109/cidm.2011.5949449","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cidm.2011.5949449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Symposium on Computational Intelligence and Data Mining (CIDM)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/11147/5014","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036394895","display_name":"Selma Tek\u0131r","orcid":"https://orcid.org/0000-0002-0488-9682"},"institutions":[{"id":"https://openalex.org/I120217413","display_name":"Izmir Institute of Technology","ror":"https://ror.org/03stptj97","country_code":"TR","type":"education","lineage":["https://openalex.org/I120217413"]},{"id":"https://openalex.org/I189712700","display_name":"University of Konstanz","ror":"https://ror.org/0546hnb39","country_code":"DE","type":"education","lineage":["https://openalex.org/I189712700"]}],"countries":["DE","TR"],"is_corresponding":false,"raw_author_name":"Selma Tekir","raw_affiliation_strings":["Faculty of Computer Science, University of Konstanz, Konstanz, Germany","Dept. of Computer Engineering, Izmir Institute of Technology, Turkey 35430"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science, University of Konstanz, Konstanz, Germany","institution_ids":["https://openalex.org/I189712700"]},{"raw_affiliation_string":"Dept. of Computer Engineering, Izmir Institute of Technology, Turkey 35430","institution_ids":["https://openalex.org/I120217413"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076733321","display_name":"Florian Mansmann","orcid":null},"institutions":[{"id":"https://openalex.org/I189712700","display_name":"University of Konstanz","ror":"https://ror.org/0546hnb39","country_code":"DE","type":"education","lineage":["https://openalex.org/I189712700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Florian Mansmann","raw_affiliation_strings":["Faculty of Computer Science, University of Konstanz, Konstanz, Germany","Faculty of Computer Science, Box 78, University of Konstanz, Germany 78457"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science, University of Konstanz, Konstanz, Germany","institution_ids":["https://openalex.org/I189712700"]},{"raw_affiliation_string":"Faculty of Computer Science, Box 78, University of Konstanz, Germany 78457","institution_ids":["https://openalex.org/I189712700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073919282","display_name":"Daniel A. Keim","orcid":"https://orcid.org/0000-0001-7966-9740"},"institutions":[{"id":"https://openalex.org/I189712700","display_name":"University of Konstanz","ror":"https://ror.org/0546hnb39","country_code":"DE","type":"education","lineage":["https://openalex.org/I189712700"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel Keim","raw_affiliation_strings":["Faculty of Computer Science, University of Konstanz, Konstanz, Germany","Faculty of Computer Science, Box 78, University of Konstanz, Germany 78457"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science, University of Konstanz, Konstanz, Germany","institution_ids":["https://openalex.org/I189712700"]},{"raw_affiliation_string":"Faculty of Computer Science, Box 78, University of Konstanz, Germany 78457","institution_ids":["https://openalex.org/I189712700"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9221,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75798966,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"393","issue":null,"first_page":"15","last_page":"21"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9943000078201294,"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"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9943000078201294,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9941999912261963,"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/T10824","display_name":"Image Retrieval and Classification Techniques","score":0.9621000289916992,"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":0.7768822312355042},{"id":"https://openalex.org/keywords/geodesic","display_name":"Geodesic","score":0.7543336153030396},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.5492553114891052},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5325073003768921},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.5259561538696289},{"id":"https://openalex.org/keywords/distance-matrix","display_name":"Distance matrix","score":0.5147838592529297},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4746875464916229},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.4600178897380829},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43538451194763184},{"id":"https://openalex.org/keywords/euclidean-distance","display_name":"Euclidean distance","score":0.4341218173503876},{"id":"https://openalex.org/keywords/curvature","display_name":"Curvature","score":0.42476847767829895},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.41971278190612793},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.41208693385124207},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3514995574951172},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33114615082740784},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2884608507156372},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.20245906710624695},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.1298305094242096},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11408010125160217}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7768822312355042},{"id":"https://openalex.org/C165818556","wikidata":"https://www.wikidata.org/wiki/Q213488","display_name":"Geodesic","level":2,"score":0.7543336153030396},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.5492553114891052},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5325073003768921},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5259561538696289},{"id":"https://openalex.org/C111208986","wikidata":"https://www.wikidata.org/wiki/Q901698","display_name":"Distance matrix","level":2,"score":0.5147838592529297},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4746875464916229},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.4600178897380829},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43538451194763184},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.4341218173503876},{"id":"https://openalex.org/C195065555","wikidata":"https://www.wikidata.org/wiki/Q214881","display_name":"Curvature","level":2,"score":0.42476847767829895},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.41971278190612793},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.41208693385124207},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3514995574951172},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33114615082740784},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2884608507156372},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.20245906710624695},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.1298305094242096},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11408010125160217},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/cidm.2011.5949449","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cidm.2011.5949449","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Symposium on Computational Intelligence and Data Mining (CIDM)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.669.9046","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.669.9046","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://bib.dbvis.de/uploadedFiles/311.pdf","raw_type":"text"},{"id":"pmh:oai:kops.uni-konstanz.de:123456789/19079","is_oa":false,"landing_page_url":"http://nbn-resolving.de/urn:nbn:de:bsz:352-190796","pdf_url":null,"source":{"id":"https://openalex.org/S4306401487","display_name":"KOPS (University of Konstanz)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I189712700","host_organization_name":"University of Konstanz","host_organization_lineage":["https://openalex.org/I189712700"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2011 IEEE Symposium on Computational Intelligence and Data Mining (CIDM). IEEE, 2011, S. 15-21. ISBN 978-1-4244-9926-7. Verf\u00fcgbar unter: doi: 10.1109/CIDM.2011.5949449","raw_type":"doc-type:conferenceObject"},{"id":"pmh:oai:openaccess.iyte.edu.tr:11147/5014","is_oa":true,"landing_page_url":"http://hdl.handle.net/11147/5014","pdf_url":null,"source":{"id":"https://openalex.org/S4306400894","display_name":"\u0130YTE (\u0130ZM\u0130R Y\u00dcKSEK TEKNOLOJ\u0130 ENST\u0130T\u00dcS\u00dc)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I120217413","host_organization_name":"Izmir Institute of Technology","host_organization_lineage":["https://openalex.org/I120217413"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conferenceObject"},{"id":"pmh:oai:openaccess.iyte.edu.tr:8080:11147/5014","is_oa":true,"landing_page_url":"http://doi.org/10.1109/CIDM.2011.5949449","pdf_url":null,"source":{"id":"https://openalex.org/S4306400894","display_name":"\u0130YTE (\u0130ZM\u0130R Y\u00dcKSEK TEKNOLOJ\u0130 ENST\u0130T\u00dcS\u00dc)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I120217413","host_organization_name":"Izmir Institute of Technology","host_organization_lineage":["https://openalex.org/I120217413"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conferenceObject"}],"best_oa_location":{"id":"pmh:oai:openaccess.iyte.edu.tr:11147/5014","is_oa":true,"landing_page_url":"http://hdl.handle.net/11147/5014","pdf_url":null,"source":{"id":"https://openalex.org/S4306400894","display_name":"\u0130YTE (\u0130ZM\u0130R Y\u00dcKSEK TEKNOLOJ\u0130 ENST\u0130T\u00dcS\u00dc)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I120217413","host_organization_name":"Izmir Institute of Technology","host_organization_lineage":["https://openalex.org/I120217413"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"conferenceObject"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W22578957","https://openalex.org/W1522930108","https://openalex.org/W1833785989","https://openalex.org/W1854214752","https://openalex.org/W1890948429","https://openalex.org/W1959178355","https://openalex.org/W2011265791","https://openalex.org/W2033403400","https://openalex.org/W2045117606","https://openalex.org/W2076018387","https://openalex.org/W2112090702","https://openalex.org/W2117536229","https://openalex.org/W2127218421","https://openalex.org/W2129630294","https://openalex.org/W2138621811","https://openalex.org/W2143605277","https://openalex.org/W2145460600","https://openalex.org/W2165769875","https://openalex.org/W2478708596","https://openalex.org/W2592187527","https://openalex.org/W2997501009","https://openalex.org/W4243375721","https://openalex.org/W4244030505","https://openalex.org/W6600907327","https://openalex.org/W6631307971","https://openalex.org/W6639055396","https://openalex.org/W6678914141","https://openalex.org/W6684601597","https://openalex.org/W6945718787"],"related_works":["https://openalex.org/W1605858995","https://openalex.org/W2908582041","https://openalex.org/W4294328694","https://openalex.org/W2010199950","https://openalex.org/W2977833894","https://openalex.org/W2169691698","https://openalex.org/W2908357282","https://openalex.org/W2119897186","https://openalex.org/W2348550256","https://openalex.org/W2480028963"],"abstract_inverted_index":{"While":[0],"traditional":[1,39,163],"distance":[2,40,78,87,99,165],"measures":[3,24,41,65],"are":[4,136],"often":[5],"capable":[6],"of":[7,60,70,84,88,118,128,139,173,182,191],"properly":[8],"describing":[9],"similarity":[10,64],"between":[11,48],"objects,":[12],"in":[13,29,73,96],"some":[14,93],"application":[15],"areas":[16],"there":[17],"is":[18,80,176],"still":[19],"potential":[20],"to":[21,50],"fine-tune":[22],"these":[23,103,132],"with":[25,45,150,161],"additional":[26],"information":[27,47,190],"provided":[28,188],"the":[30,58,67,85,89,97,115,119,140,151,155,183,187],"data":[31,120,159],"sets.":[32],"In":[33,54],"this":[34],"work":[35],"we":[36,56,106,146],"combine":[37],"such":[38],"for":[42,111],"document":[43,113],"analysis":[44],"link":[46,116],"documents":[49],"improve":[51],"clustering":[52,108,133,148],"results.":[53],"particular,":[55],"test":[57],"effectiveness":[59,172],"geodesic":[61,98,169],"distances":[62],"as":[63,131],"under":[66],"space":[68],"assumption":[69],"spherical":[71],"geometry":[72],"a":[74,82,129],"0-sphere.":[75],"Our":[76],"proposed":[77,168],"measure":[79],"thus":[81],"combination":[83],"cosine":[86,164],"term-document":[90],"matrix":[91],"and":[92,122,166],"curvature":[94,104],"values":[95,110,135,181],"formula.":[100],"To":[101,142],"estimate":[102],"values,":[105],"calculate":[107],"coefficient":[109,134],"every":[112],"from":[114],"graph":[117],"set":[121,160],"increase":[123],"their":[124],"distinctiveness":[125],"by":[126,178],"means":[127],"heuristic":[130],"rough":[137],"estimates":[138],"curvatures.":[141],"evaluate":[143],"our":[144,167,174],"work,":[145],"perform":[147],"tests":[149],"k-means":[152],"algorithm":[153],"on":[154,186],"English":[156],"Wikipedia":[157],"hyperlinked":[158],"both":[162],"distance.":[170],"The":[171],"approach":[175],"measured":[177],"computing":[179],"micro-precision":[180],"clusters":[184],"based":[185],"categorical":[189],"each":[192],"article.":[193]},"counts_by_year":[{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}