{"id":"https://openalex.org/W2043571214","doi":"https://doi.org/10.1142/s0219649208001889","title":"A Comparison of Similarity Measures for Text Documents","display_name":"A Comparison of Similarity Measures for Text Documents","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2043571214","doi":"https://doi.org/10.1142/s0219649208001889","mag":"2043571214"},"language":"en","primary_location":{"id":"doi:10.1142/s0219649208001889","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219649208001889","pdf_url":null,"source":{"id":"https://openalex.org/S30163770","display_name":"Journal of Information & Knowledge Management","issn_l":"0219-6492","issn":["0219-6492","1793-6926"],"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":"Journal of Information & Knowledge Management","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/A5087787170","display_name":"Shanmugasundaram Hariharan","orcid":"https://orcid.org/0000-0001-9686-4329"},"institutions":[{"id":"https://openalex.org/I94948490","display_name":"B.S. Abdur Rahman Crescent Institute of Science & Technology","ror":"https://ror.org/01fqhas03","country_code":"IN","type":"education","lineage":["https://openalex.org/I94948490"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Shanmugasundaram Hariharan","raw_affiliation_strings":["Faculty of Information Technology, B.S.A. Crescent Engineering College Chennai, Tamilnadu, India"],"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology, B.S.A. Crescent Engineering College Chennai, Tamilnadu, India","institution_ids":["https://openalex.org/I94948490"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103292436","display_name":"Rengaramanujam Srinivasan","orcid":null},"institutions":[{"id":"https://openalex.org/I94948490","display_name":"B.S. Abdur Rahman Crescent Institute of Science & Technology","ror":"https://ror.org/01fqhas03","country_code":"IN","type":"education","lineage":["https://openalex.org/I94948490"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rengaramanujam Srinivasan","raw_affiliation_strings":["Faculty of Computer Science and Engineering, B.S.A. Crescent Engineering College Chennai, Tamilnadu, India"],"affiliations":[{"raw_affiliation_string":"Faculty of Computer Science and Engineering, B.S.A. Crescent Engineering College Chennai, Tamilnadu, India","institution_ids":["https://openalex.org/I94948490"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5087787170"],"corresponding_institution_ids":["https://openalex.org/I94948490"],"apc_list":null,"apc_paid":null,"fwci":2.79350834,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.93417862,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"07","issue":"01","first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9891999959945679,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9891999959945679,"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/T10028","display_name":"Topic Modeling","score":0.984000027179718,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9610000252723694,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.8203386068344116},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7653408050537109},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7602561116218567},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.6634549498558044},{"id":"https://openalex.org/keywords/newspaper","display_name":"Newspaper","score":0.5678542256355286},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5411474108695984},{"id":"https://openalex.org/keywords/similarity-measure","display_name":"Similarity measure","score":0.5306403040885925},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.48059651255607605},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.45953086018562317},{"id":"https://openalex.org/keywords/document-retrieval","display_name":"Document retrieval","score":0.4317856431007385},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2633293867111206},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.24019384384155273},{"id":"https://openalex.org/keywords/advertising","display_name":"Advertising","score":0.0720595121383667}],"concepts":[{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.8203386068344116},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7653408050537109},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7602561116218567},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.6634549498558044},{"id":"https://openalex.org/C201280247","wikidata":"https://www.wikidata.org/wiki/Q11032","display_name":"Newspaper","level":2,"score":0.5678542256355286},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5411474108695984},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.5306403040885925},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.48059651255607605},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.45953086018562317},{"id":"https://openalex.org/C161156560","wikidata":"https://www.wikidata.org/wiki/Q1638872","display_name":"Document retrieval","level":2,"score":0.4317856431007385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2633293867111206},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.24019384384155273},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.0720595121383667},{"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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1142/s0219649208001889","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219649208001889","pdf_url":null,"source":{"id":"https://openalex.org/S30163770","display_name":"Journal of Information & Knowledge Management","issn_l":"0219-6492","issn":["0219-6492","1793-6926"],"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":"Journal of Information & Knowledge Management","raw_type":"journal-article"},{"id":"pmh:oai:RePEc:wsi:jikmxx:v:07:y:2008:i:01:n:s0219649208001889","is_oa":false,"landing_page_url":"http://www.worldscientific.com/doi/abs/10.1142/S0219649208001889","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5099999904632568,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W89784227","https://openalex.org/W135761774","https://openalex.org/W1557757161","https://openalex.org/W1974339500","https://openalex.org/W2013698023","https://openalex.org/W2068549609","https://openalex.org/W2079656678","https://openalex.org/W2098162425","https://openalex.org/W2139188340","https://openalex.org/W2752198569","https://openalex.org/W2753710282","https://openalex.org/W4248343126","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2113651401","https://openalex.org/W2120435877","https://openalex.org/W2188472926","https://openalex.org/W2051752098","https://openalex.org/W2547096221","https://openalex.org/W2145036943","https://openalex.org/W3090266277","https://openalex.org/W1977123279","https://openalex.org/W1573119140","https://openalex.org/W2000031603"],"abstract_inverted_index":{"Similarity":[0],"is":[1],"an":[2],"important":[3],"and":[4,21],"widely":[5],"used":[6],"concept":[7],"in":[8,32],"many":[9],"applications":[10],"such":[11],"as":[12],"Document":[13,19],"Summarisation,":[14],"Question":[15],"Answering,":[16],"Information":[17],"Retrieval,":[18],"Clustering":[20],"Categorisation.":[22],"This":[23],"paper":[24],"presents":[25],"a":[26],"comparison":[27],"of":[28,36],"various":[29],"similarity":[30,52],"measures":[31],"comparing":[33],"the":[34,44,50],"content":[35],"text":[37],"documents.":[38],"We":[39],"have":[40],"attempted":[41],"to":[42],"find":[43],"best":[45],"measure":[46],"suited":[47],"for":[48,53],"finding":[49],"document":[51],"newspaper":[54],"reports.":[55]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":2}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}