{"id":"https://openalex.org/W2091595785","doi":"https://doi.org/10.1142/s0218213008004266","title":"STRUCTURAL CLASSIFICATION OF XML DOCUMENTS USING MULTISETS","display_name":"STRUCTURAL CLASSIFICATION OF XML DOCUMENTS USING MULTISETS","publication_year":2008,"publication_date":"2008-10-01","ids":{"openalex":"https://openalex.org/W2091595785","doi":"https://doi.org/10.1142/s0218213008004266","mag":"2091595785"},"language":"en","primary_location":{"id":"doi:10.1142/s0218213008004266","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218213008004266","pdf_url":null,"source":{"id":"https://openalex.org/S178780388","display_name":"International Journal of Artificial Intelligence Tools","issn_l":"0218-2130","issn":["0218-2130","1793-6349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Artificial Intelligence Tools","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":"https://openalex.org/A5084069609","display_name":"Swami Iyer","orcid":"https://orcid.org/0000-0003-4375-5844"},"institutions":[{"id":"https://openalex.org/I33434090","display_name":"University of Massachusetts Boston","ror":"https://ror.org/04ydmy275","country_code":"US","type":"education","lineage":["https://openalex.org/I33434090"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"SWAMI IYER","raw_affiliation_strings":["Department of Computer Science, Universisty of Massachusetts at Boston, Boston, Massachusetts 02125, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Universisty of Massachusetts at Boston, Boston, Massachusetts 02125, USA","institution_ids":["https://openalex.org/I33434090"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072140970","display_name":"Dan A. Simovici","orcid":null},"institutions":[{"id":"https://openalex.org/I33434090","display_name":"University of Massachusetts Boston","ror":"https://ror.org/04ydmy275","country_code":"US","type":"education","lineage":["https://openalex.org/I33434090"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"DAN A. SIMOVICI","raw_affiliation_strings":["Department of Computer Science, Universisty of Massachusetts at Boston, Boston, Massachusetts 02125, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Universisty of Massachusetts at Boston, Boston, Massachusetts 02125, USA","institution_ids":["https://openalex.org/I33434090"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5084069609"],"corresponding_institution_ids":["https://openalex.org/I33434090"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.08506481,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"17","issue":"05","first_page":"1003","last_page":"1022"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9976000189781189,"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":0.9976000189781189,"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":0.991100013256073,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9858999848365784,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.89945387840271},{"id":"https://openalex.org/keywords/multiset","display_name":"Multiset","score":0.6484980583190918},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.6463389992713928},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6192221641540527},{"id":"https://openalex.org/keywords/document-structure-description","display_name":"Document Structure Description","score":0.5242460370063782},{"id":"https://openalex.org/keywords/xml-validation","display_name":"XML validation","score":0.5132855772972107},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.49384981393814087},{"id":"https://openalex.org/keywords/efficient-xml-interchange","display_name":"Efficient XML Interchange","score":0.4501285254955292},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.34360387921333313},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.18821817636489868},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.12425264716148376},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.056779325008392334},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.05179813504219055}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.89945387840271},{"id":"https://openalex.org/C2779623528","wikidata":"https://www.wikidata.org/wiki/Q864377","display_name":"Multiset","level":2,"score":0.6484980583190918},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.6463389992713928},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6192221641540527},{"id":"https://openalex.org/C68699486","wikidata":"https://www.wikidata.org/wiki/Q265904","display_name":"Document Structure Description","level":3,"score":0.5242460370063782},{"id":"https://openalex.org/C55348073","wikidata":"https://www.wikidata.org/wiki/Q595926","display_name":"XML validation","level":3,"score":0.5132855772972107},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.49384981393814087},{"id":"https://openalex.org/C11508877","wikidata":"https://www.wikidata.org/wiki/Q1124477","display_name":"Efficient XML Interchange","level":3,"score":0.4501285254955292},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.34360387921333313},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.18821817636489868},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.12425264716148376},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.056779325008392334},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.05179813504219055}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218213008004266","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218213008004266","pdf_url":null,"source":{"id":"https://openalex.org/S178780388","display_name":"International Journal of Artificial Intelligence Tools","issn_l":"0218-2130","issn":["0218-2130","1793-6349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal on Artificial Intelligence Tools","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W22683294","https://openalex.org/W186340092","https://openalex.org/W1493454437","https://openalex.org/W1527072379","https://openalex.org/W1548171311","https://openalex.org/W1565990971","https://openalex.org/W1575842006","https://openalex.org/W1583866884","https://openalex.org/W1602830587","https://openalex.org/W1628571627","https://openalex.org/W2024797550","https://openalex.org/W2106206965","https://openalex.org/W2139081439","https://openalex.org/W2160873337","https://openalex.org/W2517878783","https://openalex.org/W2999729612","https://openalex.org/W4285719527","https://openalex.org/W4313334828"],"related_works":["https://openalex.org/W2276215951","https://openalex.org/W2146760738","https://openalex.org/W2047342127","https://openalex.org/W2115478919","https://openalex.org/W2006926527","https://openalex.org/W1509918510","https://openalex.org/W2137809776","https://openalex.org/W2921934746","https://openalex.org/W2093637352","https://openalex.org/W2024164996"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"investigate":[4],"the":[5,17,28],"problem":[6],"of":[7,47],"clustering":[8],"XML":[9,21,65],"documents":[10,52,66],"based":[11],"on":[12,32],"their":[13],"structure.":[14],"We":[15],"represent":[16],"paths":[18],"in":[19,53],"an":[20],"document":[22],"as":[23],"a":[24,45,54],"multiset":[25],"and":[26,63],"use":[27],"symmetric":[29],"difference":[30],"operation":[31],"multisets":[33],"to":[34,43,61],"define":[35],"certain":[36],"metrics.":[37],"These":[38],"metrics":[39],"are":[40],"then":[41],"used":[42],"obtain":[44],"measure":[46],"similarity":[48],"between":[49],"any":[50],"two":[51],"collection.":[55],"Our":[56],"technique":[57],"was":[58],"successfully":[59],"applied":[60],"real":[62],"synthesized":[64],"yielding":[67],"high-quality":[68],"clusterings.":[69]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}