{"id":"https://openalex.org/W4362671796","doi":"https://doi.org/10.3390/a16040198","title":"Model of Lexico-Semantic Bonds between Texts for Creating Their Similarity Metrics and Developing Statistical Clustering Algorithm","display_name":"Model of Lexico-Semantic Bonds between Texts for Creating Their Similarity Metrics and Developing Statistical Clustering Algorithm","publication_year":2023,"publication_date":"2023-04-05","ids":{"openalex":"https://openalex.org/W4362671796","doi":"https://doi.org/10.3390/a16040198"},"language":"en","primary_location":{"id":"doi:10.3390/a16040198","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a16040198","pdf_url":"https://www.mdpi.com/1999-4893/16/4/198/pdf?version=1680690701","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-4893/16/4/198/pdf?version=1680690701","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5014751855","display_name":"Liliya Demidova","orcid":"https://orcid.org/0000-0003-4516-3746"},"institutions":[{"id":"https://openalex.org/I4210135186","display_name":"MIREA - Russian Technological University","ror":"https://ror.org/04qrtgy16","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210135186"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Liliya Demidova","raw_affiliation_strings":["Institute of Information Technology, MIREA-Russian Technological University, 78 Vernadsky Avenue, 119454 Moscow, Russia"],"affiliations":[{"raw_affiliation_string":"Institute of Information Technology, MIREA-Russian Technological University, 78 Vernadsky Avenue, 119454 Moscow, Russia","institution_ids":["https://openalex.org/I4210135186"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000292401","display_name":"Dmitry Zhukov","orcid":"https://orcid.org/0000-0002-1211-5214"},"institutions":[{"id":"https://openalex.org/I4210135186","display_name":"MIREA - Russian Technological University","ror":"https://ror.org/04qrtgy16","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210135186"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Dmitry Zhukov","raw_affiliation_strings":["Institute of Cybersecurity and Digital Technologies, MIREA-Russian Technological University, 78 Vernadsky Avenue, 119454 Moscow, Russia"],"affiliations":[{"raw_affiliation_string":"Institute of Cybersecurity and Digital Technologies, MIREA-Russian Technological University, 78 Vernadsky Avenue, 119454 Moscow, Russia","institution_ids":["https://openalex.org/I4210135186"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026632434","display_name":"Elena Andrianova","orcid":"https://orcid.org/0000-0001-6418-6797"},"institutions":[{"id":"https://openalex.org/I4210135186","display_name":"MIREA - Russian Technological University","ror":"https://ror.org/04qrtgy16","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210135186"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Elena Andrianova","raw_affiliation_strings":["Institute of Information Technology, MIREA-Russian Technological University, 78 Vernadsky Avenue, 119454 Moscow, Russia"],"affiliations":[{"raw_affiliation_string":"Institute of Information Technology, MIREA-Russian Technological University, 78 Vernadsky Avenue, 119454 Moscow, Russia","institution_ids":["https://openalex.org/I4210135186"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012119496","display_name":"Vladimir Kalinin","orcid":"https://orcid.org/0000-0003-1365-4639"},"institutions":[{"id":"https://openalex.org/I4210135186","display_name":"MIREA - Russian Technological University","ror":"https://ror.org/04qrtgy16","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210135186"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Vladimir Kalinin","raw_affiliation_strings":["Institute of Radio Electronics and Informatics, MIREA-Russian Technological University, 78 Vernadsky Avenue, 119454 Moscow, Russia"],"affiliations":[{"raw_affiliation_string":"Institute of Radio Electronics and Informatics, MIREA-Russian Technological University, 78 Vernadsky Avenue, 119454 Moscow, Russia","institution_ids":["https://openalex.org/I4210135186"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5000292401","https://openalex.org/A5014751855"],"corresponding_institution_ids":["https://openalex.org/I4210135186"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04610592,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":"4","first_page":"198","last_page":"198"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12734","display_name":"Information Systems and Technology Applications","score":0.9890000224113464,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12734","display_name":"Information Systems and Technology Applications","score":0.9890000224113464,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9818000197410583,"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/T13608","display_name":"Advanced Computational Techniques in Science and Engineering","score":0.9362000226974487,"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/cosine-similarity","display_name":"Cosine similarity","score":0.7407313585281372},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6970447301864624},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.6508060693740845},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5665268301963806},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5560294985771179},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5426914691925049},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5234465003013611},{"id":"https://openalex.org/keywords/lexico","display_name":"Lexico","score":0.5026829242706299},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.488357275724411},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3697272539138794},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3418337106704712},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33451831340789795}],"concepts":[{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.7407313585281372},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6970447301864624},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.6508060693740845},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5665268301963806},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5560294985771179},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5426914691925049},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5234465003013611},{"id":"https://openalex.org/C2777776507","wikidata":"https://www.wikidata.org/wiki/Q4807054","display_name":"Lexico","level":3,"score":0.5026829242706299},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.488357275724411},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3697272539138794},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3418337106704712},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33451831340789795},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/a16040198","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a16040198","pdf_url":"https://www.mdpi.com/1999-4893/16/4/198/pdf?version=1680690701","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:a2a185b2284949628745e4a94813ef1a","is_oa":true,"landing_page_url":"https://doaj.org/article/a2a185b2284949628745e4a94813ef1a","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms, Vol 16, Iss 4, p 198 (2023)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1999-4893/16/4/198/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/a16040198","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms; Volume 16; Issue 4; Pages: 198","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/a16040198","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a16040198","pdf_url":"https://www.mdpi.com/1999-4893/16/4/198/pdf?version=1680690701","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4362671796.pdf"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W98055435","https://openalex.org/W1732310889","https://openalex.org/W1864421552","https://openalex.org/W2008077314","https://openalex.org/W2014440992","https://openalex.org/W2046186301","https://openalex.org/W2165232124","https://openalex.org/W2295025645","https://openalex.org/W2307614288","https://openalex.org/W2407983325","https://openalex.org/W2523638362","https://openalex.org/W2528807332","https://openalex.org/W2545327431","https://openalex.org/W2550389024","https://openalex.org/W2562576330","https://openalex.org/W2597328883","https://openalex.org/W2602655087","https://openalex.org/W2610222147","https://openalex.org/W2617160631","https://openalex.org/W2619571458","https://openalex.org/W2734337707","https://openalex.org/W2798039575","https://openalex.org/W2889326414","https://openalex.org/W3126902826","https://openalex.org/W3133708803","https://openalex.org/W4224068063","https://openalex.org/W6728370504"],"related_works":["https://openalex.org/W2389818373","https://openalex.org/W2220831889","https://openalex.org/W2056226831","https://openalex.org/W2226024386","https://openalex.org/W3013312691","https://openalex.org/W3027421045","https://openalex.org/W4312683641","https://openalex.org/W2380654781","https://openalex.org/W2576320324","https://openalex.org/W2114797768"],"abstract_inverted_index":{"To":[0],"solve":[1],"the":[2,42,50,53,64,71,74,77,87,90,101,106,114,132,152,156,163,166,172,175,189,192,200,212,216,226,250,264,286],"problem":[3],"of":[4,16,45,52,55,67,73,76,89,103,126,155,159,165,174,191,205,219,228,249,263,266,288],"text":[5,68,78,143,234,293],"clustering":[6,144,235],"according":[7],"to":[8,150,186,223,247],"semantic":[9,59,84,109,203],"groups,":[10],"we":[11,34,121],"suggest":[12],"using":[13,81],"a":[14,17,24,93,124,272],"model":[15,173,214,240,281],"unified":[18],"lexico-semantic":[19,31,133,176,217],"bond":[20,177],"between":[21,135,178],"texts":[22,98,220],"and":[23,47,49,275,282,296],"similarity":[25,79,104,267,294],"matrix":[26,80,125,170,190],"based":[27,39,198,237],"on":[28,41,113,199,238],"it.":[29],"Using":[30],"analysis":[32,85],"methods,":[33,86],"can":[35,122],"create":[36],"\u201cterm\u2013document\u201d":[37],"matrices":[38],"both":[40],"occurrence":[43],"frequencies":[44],"words":[46],"n-grams":[48],"determination":[51],"degrees":[54],"nodes":[56],"in":[57,105,118,162,171],"their":[58,229,297],"network,":[60],"followed":[61],"by":[62],"calculating":[63],"cosine":[65,88,127,167,193],"metrics":[66,295],"similarity.":[69],"In":[70,180],"process":[72],"construction":[75],"lexical":[82,107,201],"or":[83,108,202],"angle":[91],"for":[92,141,215,268,291],"vector":[94],"pair":[95],"describing":[96],"such":[97],"will":[99],"determine":[100],"degree":[102,265],"presentation,":[110],"respectively.":[111],"Based":[112],"averaging":[115],"procedure":[116],"described":[117],"this":[119,182,239],"paper,":[120],"obtain":[123],"metric":[128,168,194],"values":[129,161,195],"that":[130,211,244],"describes":[131],"bonds":[134],"texts.":[136,206],"We":[137],"propose":[138],"an":[139],"algorithm":[140,147,183,236,258,283],"solving":[142],"problems.":[145],"This":[146],"allows":[148,184,221],"one":[149,185,222],"use":[151],"statistical":[153,233],"characteristics":[154],"distribution":[157],"functions":[158],"element":[160],"rows":[164],"value":[169],"documents.":[179],"addition,":[181],"separately":[187,197],"describe":[188],"obtained":[196],"properties":[204],"Our":[207],"research":[208],"has":[209],"shown":[210],"developed":[213],"presentation":[218],"slightly":[224],"increase":[225],"accuracy":[227],"subsequent":[230],"clustering.":[231,298],"The":[232,279],"shows":[241],"excellent":[242],"results":[243],"are":[245],"comparable":[246],"those":[248],"widely":[251],"used":[252],"affinity":[253],"propagation":[254],"algorithm.":[255],"Additionally,":[256],"our":[257],"does":[259],"not":[260],"require":[261],"specification":[262],"combining":[269],"vectors":[270],"into":[271],"common":[273],"cluster":[274],"other":[276],"configuration":[277],"parameters.":[278],"suggested":[280],"significantly":[284],"expand":[285],"list":[287],"known":[289],"approaches":[290],"determining":[292]},"counts_by_year":[],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}