{"id":"https://openalex.org/W1843995512","doi":"https://doi.org/10.3233/jcm-2010-0269","title":"Shape pattern matching: A tool to cluster unstructured text documents","display_name":"Shape pattern matching: A tool to cluster unstructured text documents","publication_year":2010,"publication_date":"2010-09-07","ids":{"openalex":"https://openalex.org/W1843995512","doi":"https://doi.org/10.3233/jcm-2010-0269","mag":"1843995512"},"language":"en","primary_location":{"id":"doi:10.3233/jcm-2010-0269","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jcm-2010-0269","pdf_url":null,"source":{"id":"https://openalex.org/S2765058733","display_name":"Journal of Computational Methods in Sciences and Engineering","issn_l":"1472-7978","issn":["1472-7978","1875-8983"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Methods in Sciences and Engineering","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/A5082753354","display_name":"Durga Toshniwal","orcid":null},"institutions":[{"id":"https://openalex.org/I154851008","display_name":"Indian Institute of Technology Roorkee","ror":"https://ror.org/00582g326","country_code":"IN","type":"education","lineage":["https://openalex.org/I154851008"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Durga Toshniwal","raw_affiliation_strings":["Department of Electronics and Computer Engineering, Indian Institute of Technology Roorkee, Roorkee \u2013 247 667, Uttarakhand, India","(Correspd. E-mail: durgafec@iitr.ernet.in) Department of Electronics and Computer Engineering, Indian Institute of Technology Roorkee, Roorkee - 247 667, Uttarakhand, India#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Computer Engineering, Indian Institute of Technology Roorkee, Roorkee \u2013 247 667, Uttarakhand, India","institution_ids":["https://openalex.org/I154851008"]},{"raw_affiliation_string":"(Correspd. E-mail: durgafec@iitr.ernet.in) Department of Electronics and Computer Engineering, Indian Institute of Technology Roorkee, Roorkee - 247 667, Uttarakhand, India#TAB#","institution_ids":["https://openalex.org/I154851008"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042165238","display_name":"Rishiraj Saha Roy","orcid":"https://orcid.org/0000-0002-5774-5658"},"institutions":[{"id":"https://openalex.org/I154851008","display_name":"Indian Institute of Technology Roorkee","ror":"https://ror.org/00582g326","country_code":"IN","type":"education","lineage":["https://openalex.org/I154851008"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rishiraj Saha Roy","raw_affiliation_strings":["Department of Electronics and Computer Engineering, Indian Institute of Technology Roorkee, Roorkee \u2013 247 667, Uttarakhand, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronics and Computer Engineering, Indian Institute of Technology Roorkee, Roorkee \u2013 247 667, Uttarakhand, India","institution_ids":["https://openalex.org/I154851008"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5082753354"],"corresponding_institution_ids":["https://openalex.org/I154851008"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.11699504,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"10","issue":"s1","first_page":"S73","last_page":"S84"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9955999851226807,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9955999851226807,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9886000156402588,"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":0.9869999885559082,"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":0.7563101053237915},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7202956080436707},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6977304220199585},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.627660870552063},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.6175817847251892},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5338662266731262},{"id":"https://openalex.org/keywords/vector-space-model","display_name":"Vector space model","score":0.529880166053772},{"id":"https://openalex.org/keywords/vector-space","display_name":"Vector space","score":0.444816529750824},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.43834444880485535},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4355718493461609},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.41979917883872986},{"id":"https://openalex.org/keywords/alphabet","display_name":"Alphabet","score":0.41688960790634155},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36944615840911865},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.340018093585968},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16070380806922913}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7563101053237915},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7202956080436707},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6977304220199585},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.627660870552063},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.6175817847251892},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5338662266731262},{"id":"https://openalex.org/C89686163","wikidata":"https://www.wikidata.org/wiki/Q1187982","display_name":"Vector space model","level":2,"score":0.529880166053772},{"id":"https://openalex.org/C13336665","wikidata":"https://www.wikidata.org/wiki/Q125977","display_name":"Vector space","level":2,"score":0.444816529750824},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.43834444880485535},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4355718493461609},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.41979917883872986},{"id":"https://openalex.org/C112876837","wikidata":"https://www.wikidata.org/wiki/Q837518","display_name":"Alphabet","level":2,"score":0.41688960790634155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36944615840911865},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.340018093585968},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16070380806922913},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.3233/jcm-2010-0269","is_oa":false,"landing_page_url":"https://doi.org/10.3233/jcm-2010-0269","pdf_url":null,"source":{"id":"https://openalex.org/S2765058733","display_name":"Journal of Computational Methods in Sciences and Engineering","issn_l":"1472-7978","issn":["1472-7978","1875-8983"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Computational Methods in Sciences and Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8199999928474426,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W62087013","https://openalex.org/W76896516","https://openalex.org/W1593045043","https://openalex.org/W2024728919","https://openalex.org/W2054114339","https://openalex.org/W2087544630","https://openalex.org/W2109535575","https://openalex.org/W2109749916","https://openalex.org/W2115127664","https://openalex.org/W2125606783","https://openalex.org/W2131912994","https://openalex.org/W2140190241","https://openalex.org/W2156629362","https://openalex.org/W2270210878","https://openalex.org/W2316749158","https://openalex.org/W2537839714"],"related_works":["https://openalex.org/W2165612380","https://openalex.org/W187510616","https://openalex.org/W1500125366","https://openalex.org/W2096728994","https://openalex.org/W2551770406","https://openalex.org/W1557970708","https://openalex.org/W2137763598","https://openalex.org/W2349139068","https://openalex.org/W2611108488","https://openalex.org/W1575842006"],"abstract_inverted_index":{"Research":[0],"in":[1,16,33,98,133,162],"text":[2,31,48,94],"mining":[3],"has":[4,73,81],"recently":[5],"gained":[6],"a":[7,65,77,87,153],"lot":[8],"of":[9,19,101,121,140],"importance":[10],"due":[11],"to":[12,60,76],"the":[13,17,82,93,99,105,122,157,163],"large":[14],"increase":[15],"number":[18],"electronic":[20],"news":[21],"articles,":[22],"books,":[23],"research":[24],"papers,":[25],"and":[26],"e-mail":[27],"messages.":[28],"Clustering":[29],"organizes":[30],"documents":[32,49,95,106,151],"an":[34,42],"unsupervised":[35],"fashion.":[36],"In":[37,90],"this":[38,91],"paper,":[39],"we":[40],"propose":[41],"algorithm":[43],"for":[44],"clustering":[45],"uns":[46],"tructured":[47],"using":[50,115],"shape":[51,130,142,159],"pattern":[52,160],"matching.":[53],"The":[54,68,118,129],"Vector":[55],"Space":[56],"Model":[57],"is":[58,125,144],"used":[59],"represent":[61],"our":[62],"dataset":[63],"as":[64],"term-weight":[66],"matrix.":[67],"high":[69],"dimensional":[70],"vector":[71,124],"space":[72],"been":[74],"mapped":[75],"two-dimensional":[78],"plane":[79],"that":[80,112],"term":[83],"weights":[84],"plotted":[85],"against":[86],"time":[88,102],"axis.":[89],"way,":[92],"are":[96,107,113,137],"represented":[97],"form":[100],"sequences.":[103],"Initially,":[104],"broadly":[108],"grouped":[109],"into":[110],"categories":[111],"determined":[114],"domain":[116],"knowledge.":[117],"relevant":[119],"portion":[120],"document":[123],"then":[126],"clipped":[127,135],"out.":[128],"patterns":[131,143],"present":[132],"these":[134,141],"portions":[136],"observed.":[138],"Indexing":[139],"done":[145],"by":[146],"preparing":[147],"their":[148],"alphabet.":[149],"Grouping":[150],"within":[152],"category":[154],"which":[155],"share":[156],"same":[158],"results":[161],"required":[164],"clusters.":[165]},"counts_by_year":[{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}