{"id":"https://openalex.org/W2736451061","doi":"https://doi.org/10.1186/s40537-017-0083-6","title":"Improved sqrt-cosine similarity measurement","display_name":"Improved sqrt-cosine similarity measurement","publication_year":2017,"publication_date":"2017-07-25","ids":{"openalex":"https://openalex.org/W2736451061","doi":"https://doi.org/10.1186/s40537-017-0083-6","mag":"2736451061"},"language":"en","primary_location":{"id":"doi:10.1186/s40537-017-0083-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-017-0083-6","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-017-0083-6","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-017-0083-6","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5002977187","display_name":"Sahar Sohangir","orcid":"https://orcid.org/0000-0003-1800-1696"},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sahar Sohangir","raw_affiliation_strings":["Department of Computer & Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, FL, 33431, USA","Department of Computer & Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, USA"],"raw_orcid":"https://orcid.org/0000-0003-1800-1696","affiliations":[{"raw_affiliation_string":"Department of Computer & Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, FL, 33431, USA","institution_ids":["https://openalex.org/I63772739"]},{"raw_affiliation_string":"Department of Computer & Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, USA","institution_ids":["https://openalex.org/I63772739"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101983506","display_name":"Dingding Wang","orcid":"https://orcid.org/0000-0003-2339-8050"},"institutions":[{"id":"https://openalex.org/I63772739","display_name":"Florida Atlantic University","ror":"https://ror.org/05p8w6387","country_code":"US","type":"education","lineage":["https://openalex.org/I63772739"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dingding Wang","raw_affiliation_strings":["Department of Computer & Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, FL, 33431, USA","Department of Computer & Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer & Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, FL, 33431, USA","institution_ids":["https://openalex.org/I63772739"]},{"raw_affiliation_string":"Department of Computer & Electrical Engineering and Computer Science, Florida Atlantic University, Boca Raton, USA","institution_ids":["https://openalex.org/I63772739"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63772739"],"apc_list":{"value":1060,"currency":"GBP","value_usd":1300},"apc_paid":{"value":1060,"currency":"GBP","value_usd":1300},"fwci":4.3367,"has_fulltext":true,"cited_by_count":120,"citation_normalized_percentile":{"value":0.95482567,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"4","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11550","display_name":"Text and Document Classification Technologies","score":0.998199999332428,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.998199999332428,"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":0.9930999875068665,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9919999837875366,"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/cosine-similarity","display_name":"Cosine similarity","score":0.8710156679153442},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.8103612661361694},{"id":"https://openalex.org/keywords/euclidean-distance","display_name":"Euclidean distance","score":0.7174708247184753},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6572587490081787},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6100708246231079},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6046759486198425},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5503817796707153},{"id":"https://openalex.org/keywords/euclidean-geometry","display_name":"Euclidean geometry","score":0.5348884463310242},{"id":"https://openalex.org/keywords/trigonometric-functions","display_name":"Trigonometric functions","score":0.5341469645500183},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4575341045856476},{"id":"https://openalex.org/keywords/similarity-measure","display_name":"Similarity measure","score":0.4504106044769287},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.41126763820648193},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.41057509183883667},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3893703520298004},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33521100878715515},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.28312647342681885},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10730153322219849}],"concepts":[{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.8710156679153442},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.8103612661361694},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.7174708247184753},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6572587490081787},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6100708246231079},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6046759486198425},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5503817796707153},{"id":"https://openalex.org/C129782007","wikidata":"https://www.wikidata.org/wiki/Q162886","display_name":"Euclidean geometry","level":2,"score":0.5348884463310242},{"id":"https://openalex.org/C178009071","wikidata":"https://www.wikidata.org/wiki/Q93344","display_name":"Trigonometric functions","level":2,"score":0.5341469645500183},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4575341045856476},{"id":"https://openalex.org/C2776517306","wikidata":"https://www.wikidata.org/wiki/Q29017317","display_name":"Similarity measure","level":2,"score":0.4504106044769287},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.41126763820648193},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.41057509183883667},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3893703520298004},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33521100878715515},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28312647342681885},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10730153322219849},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1186/s40537-017-0083-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-017-0083-6","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-017-0083-6","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:34bbd1ea22a44d428ba6ccb53fadbdd0","is_oa":true,"landing_page_url":"https://doaj.org/article/34bbd1ea22a44d428ba6ccb53fadbdd0","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Big Data, Vol 4, Iss 1, Pp 1-13 (2017)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s40537-017-0083-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s40537-017-0083-6","pdf_url":"https://journalofbigdata.springeropen.com/counter/pdf/10.1186/s40537-017-0083-6","source":{"id":"https://openalex.org/S2737955091","display_name":"Journal Of Big Data","issn_l":"2196-1115","issn":["2196-1115"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Big Data","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2736451061.pdf","grobid_xml":"https://content.openalex.org/works/W2736451061.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W38016875","https://openalex.org/W195533127","https://openalex.org/W334811598","https://openalex.org/W615842445","https://openalex.org/W1480376833","https://openalex.org/W1530303756","https://openalex.org/W1532325895","https://openalex.org/W1545965399","https://openalex.org/W1565050238","https://openalex.org/W1576344349","https://openalex.org/W1580791986","https://openalex.org/W1647729745","https://openalex.org/W1662133657","https://openalex.org/W1672197616","https://openalex.org/W1929496293","https://openalex.org/W1965555277","https://openalex.org/W1980073965","https://openalex.org/W1987869189","https://openalex.org/W2006340479","https://openalex.org/W2011272347","https://openalex.org/W2022762238","https://openalex.org/W2024635814","https://openalex.org/W2027499890","https://openalex.org/W2028672257","https://openalex.org/W2045997397","https://openalex.org/W2068549609","https://openalex.org/W2119706777","https://openalex.org/W2127707215","https://openalex.org/W2130658427","https://openalex.org/W2140156730","https://openalex.org/W2144898279","https://openalex.org/W2149148023","https://openalex.org/W2165182095","https://openalex.org/W2165533158","https://openalex.org/W2171313960","https://openalex.org/W2233362460","https://openalex.org/W2314199904","https://openalex.org/W2318802957","https://openalex.org/W2342204193","https://openalex.org/W2407118485","https://openalex.org/W2471643592","https://openalex.org/W2540570975","https://openalex.org/W2542459869","https://openalex.org/W2593759704","https://openalex.org/W2787894218","https://openalex.org/W2799061466","https://openalex.org/W3041201303","https://openalex.org/W3141455185","https://openalex.org/W3176183162","https://openalex.org/W4206262194","https://openalex.org/W4213009331","https://openalex.org/W4231631481","https://openalex.org/W4248010344","https://openalex.org/W4285719527","https://openalex.org/W7014191107"],"related_works":["https://openalex.org/W126212742","https://openalex.org/W1948687848","https://openalex.org/W2953417386","https://openalex.org/W2010199950","https://openalex.org/W2473504045","https://openalex.org/W2113119382","https://openalex.org/W2284045667","https://openalex.org/W57923944","https://openalex.org/W875509673","https://openalex.org/W3111740253"],"abstract_inverted_index":{"Text":[0],"similarity":[1,26,39,68,80,104],"measurement":[2,105],"aims":[3],"to":[4,15,81,100,108],"find":[5],"the":[6,35,76],"commonality":[7],"existing":[8,109],"among":[9],"text":[10,22,59,89],"documents,":[11],"which":[12,54],"is":[13,31,44,119],"fundamental":[14],"most":[16,36],"information":[17,19],"extraction,":[18],"retrieval,":[20],"and":[21,92],"mining":[23],"problems.":[24],"Cosine":[25],"based":[27,70],"on":[28,71],"Euclidean":[29,42],"distance":[30,43],"currently":[32],"one":[33],"of":[34,84],"widely":[37],"used":[38,57],"measurements.":[40],"However,":[41],"generally":[45],"not":[46],"an":[47],"effective":[48],"metric":[49],"for":[50],"dealing":[51],"with":[52],"probabilities,":[53],"are":[55,97],"often":[56],"in":[58,106],"analytics.":[60],"In":[61],"this":[62],"paper,":[63],"we":[64],"propose":[65],"a":[66,82],"new":[67,103],"measure":[69],"sqrt-cosine":[72,79],"similarity.":[73],"We":[74],"apply":[75],"proposed":[77,117],"improved":[78],"variety":[83],"document-understanding":[85],"tasks,":[86],"such":[87],"as":[88],"classification,":[90],"clustering,":[91],"query":[93],"search.":[94],"Comprehensive":[95],"experiments":[96],"then":[98],"conducted":[99],"evaluate":[101],"our":[102,116],"comparison":[107],"methods.":[110],"These":[111],"experimental":[112],"results":[113],"show":[114],"that":[115],"method":[118],"indeed":[120],"effective.":[121]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":11},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":5}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}