{"id":"https://openalex.org/W1958759744","doi":"https://doi.org/10.13053/cys-19-1-1922","title":"Clustering XML Documents using Structure and Content Based in a Proposal Similarity Function (OverallSimSUX)","display_name":"Clustering XML Documents using Structure and Content Based in a Proposal Similarity Function (OverallSimSUX)","publication_year":2015,"publication_date":"2015-03-31","ids":{"openalex":"https://openalex.org/W1958759744","doi":"https://doi.org/10.13053/cys-19-1-1922","mag":"1958759744"},"language":"en","primary_location":{"id":"doi:10.13053/cys-19-1-1922","is_oa":false,"landing_page_url":"https://doi.org/10.13053/cys-19-1-1922","pdf_url":null,"source":{"id":"https://openalex.org/S61446325","display_name":"Computaci\u00f3n y Sistemas","issn_l":"1405-5546","issn":["1405-5546","2007-9737"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319599","host_organization_name":"National Polytechnic Institute","host_organization_lineage":["https://openalex.org/P4310319599"],"host_organization_lineage_names":["National Polytechnic Institute"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computaci\u00f3n y Sistemas","raw_type":"journal-article"},"type":"article","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":null,"display_name":"Damny Magdaleno Guevara","orcid":null},"institutions":[{"id":"https://openalex.org/I3018837529","display_name":"Universidad Central \"Marta Abreu\" de las Villas (UCLV)","ror":"https://ror.org/01cdy6h50","country_code":"CU","type":"education","lineage":["https://openalex.org/I3018837529"]}],"countries":["CU"],"is_corresponding":false,"raw_author_name":"Damny Magdaleno Guevara","raw_affiliation_strings":["Universidad Central Marta Abreu de Las Villas, Santa Clara, Cuba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Central Marta Abreu de Las Villas, Santa Clara, Cuba","institution_ids":["https://openalex.org/I3018837529"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ivette E. Fuentes Herrera","orcid":null},"institutions":[{"id":"https://openalex.org/I3018837529","display_name":"Universidad Central \"Marta Abreu\" de las Villas (UCLV)","ror":"https://ror.org/01cdy6h50","country_code":"CU","type":"education","lineage":["https://openalex.org/I3018837529"]}],"countries":["CU"],"is_corresponding":false,"raw_author_name":"Ivette E. Fuentes Herrera","raw_affiliation_strings":["Universidad Central Marta Abreu de Las Villas, Santa Clara, Cuba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Central Marta Abreu de Las Villas, Santa Clara, Cuba","institution_ids":["https://openalex.org/I3018837529"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104354205","display_name":"Mar\u00eda M. Garc\u00eda","orcid":"https://orcid.org/0000-0002-7185-5116"},"institutions":[{"id":"https://openalex.org/I3018837529","display_name":"Universidad Central \"Marta Abreu\" de las Villas (UCLV)","ror":"https://ror.org/01cdy6h50","country_code":"CU","type":"education","lineage":["https://openalex.org/I3018837529"]}],"countries":["CU"],"is_corresponding":false,"raw_author_name":"Mar\u00eda M. Garc\u00eda Lorenzo","raw_affiliation_strings":["Universidad Central Marta Abreu de Las Villas, Santa Clara, Cuba"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Central Marta Abreu de Las Villas, Santa Clara, Cuba","institution_ids":["https://openalex.org/I3018837529"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I3018837529"],"apc_list":null,"apc_paid":null,"fwci":2.1827,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.90015142,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"19","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9988999962806702,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.9988999962806702,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.996999979019165,"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":0.8296570777893066},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6718342304229736},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6303493976593018},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.6208685636520386},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5904589295387268},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5157094597816467},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4865049719810486},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.4795669913291931},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46556970477104187},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46173369884490967},{"id":"https://openalex.org/keywords/semi-structured-data","display_name":"Semi-structured data","score":0.46024104952812195},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33142077922821045},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.30429601669311523},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1277487576007843}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8296570777893066},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6718342304229736},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6303493976593018},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.6208685636520386},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5904589295387268},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5157094597816467},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4865049719810486},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.4795669913291931},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46556970477104187},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46173369884490967},{"id":"https://openalex.org/C40077939","wikidata":"https://www.wikidata.org/wiki/Q2336004","display_name":"Semi-structured data","level":3,"score":0.46024104952812195},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33142077922821045},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.30429601669311523},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1277487576007843},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.13053/cys-19-1-1922","is_oa":false,"landing_page_url":"https://doi.org/10.13053/cys-19-1-1922","pdf_url":null,"source":{"id":"https://openalex.org/S61446325","display_name":"Computaci\u00f3n y Sistemas","issn_l":"1405-5546","issn":["1405-5546","2007-9737"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319599","host_organization_name":"National Polytechnic Institute","host_organization_lineage":["https://openalex.org/P4310319599"],"host_organization_lineage_names":["National Polytechnic Institute"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computaci\u00f3n y Sistemas","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6100000143051147}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W75234989","https://openalex.org/W204278075","https://openalex.org/W1505918596","https://openalex.org/W1510730614","https://openalex.org/W1549585131","https://openalex.org/W1569362407","https://openalex.org/W1575842006","https://openalex.org/W1651093245","https://openalex.org/W1691661057","https://openalex.org/W1839225257","https://openalex.org/W1997841190","https://openalex.org/W2008123298","https://openalex.org/W2016944307","https://openalex.org/W2020836195","https://openalex.org/W2025722262","https://openalex.org/W2064066237","https://openalex.org/W2108584692","https://openalex.org/W2128381480","https://openalex.org/W2139267689","https://openalex.org/W2165612380","https://openalex.org/W2487224391","https://openalex.org/W2732871444","https://openalex.org/W2949863272","https://openalex.org/W3214849857","https://openalex.org/W4252684946"],"related_works":["https://openalex.org/W2804364458","https://openalex.org/W4298130764","https://openalex.org/W2019737068","https://openalex.org/W2899601636","https://openalex.org/W4254379378","https://openalex.org/W3015674157","https://openalex.org/W4206655101","https://openalex.org/W4237592971","https://openalex.org/W2387982377","https://openalex.org/W2114818997"],"abstract_inverted_index":{"Every":[0],"day":[1],"more":[2],"digital":[3],"data":[4,118],"in":[5,29,125],"semi-structured":[6],"format":[7],"are":[8,47],"available":[9],"on":[10,86,94],"the":[11,30,103],"World":[12],"Wide":[13],"Web,":[14],"corporate":[15],"intranets,":[16],"and":[17,25,40,52,89],"other":[18],"media.":[19],"Knowledge":[20],"management":[21,63],"using":[22],"information":[23],"search":[24],"processing":[26],"is":[27,59],"essential":[28,60],"field":[31],"of":[32,45,64,79,82,105,110,115],"academic":[33],"writing.":[34],"This":[35],"task":[36],"becomes":[37],"increasingly":[38],"complex":[39],"defiant,":[41],"mainly":[42],"because":[43],"collections":[44],"documents":[46,84],"usually":[48],"heterogeneous,":[49],"big,":[50],"diverse,":[51],"dynamic.":[53],"To":[54],"resolve":[55],"these":[56],"challenges":[57],"it":[58],"to":[61,67],"improve":[62],"time":[65],"necessary":[66],"process":[68],"scientific":[69],"information.":[70],"In":[71],"this":[72],"paper,":[73],"we":[74],"propose":[75],"a":[76,95],"new":[77,96],"method":[78],"automatic":[80],"clustering":[81],"XML":[83],"based":[85],"their":[87],"content":[88],"structure,":[90],"as":[91,93],"well":[92],"similarity":[97,106],"function":[98],"OverallSimSUX":[99],"which":[100],"facilitates":[101],"capturing":[102],"degree":[104],"among":[107],"documents.":[108],"Evaluation":[109],"our":[111],"proposal":[112],"by":[113],"means":[114],"experiments":[116],"with":[117],"sets":[119],"showed":[120],"better":[121],"results":[122],"than":[123],"those":[124],"previous":[126],"work.":[127]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}
