{"id":"https://openalex.org/W2188994205","doi":"https://doi.org/10.1016/j.procs.2015.11.035","title":"An Algorithm of Finding Thematically Similar Documents with Creating Context-semantic Graph Based on Probabilistic-entropy Approach","display_name":"An Algorithm of Finding Thematically Similar Documents with Creating Context-semantic Graph Based on Probabilistic-entropy Approach","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2188994205","doi":"https://doi.org/10.1016/j.procs.2015.11.035","mag":"2188994205"},"language":"en","primary_location":{"id":"doi:10.1016/j.procs.2015.11.035","doi":"https://doi.org/10.1016/j.procs.2015.11.035","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2015.11.035","pdf_url":"https://www.sciencedirect.com/science/article/pii/S1877050915033840/pdf","source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://www.sciencedirect.com/science/article/pii/S1877050915033840/pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087422679","display_name":"\u041c\u043e\u043b\u043e\u0448\u043d\u0438\u043a\u043e\u0432 \u0418\u0432\u0430\u043d \u0410\u043b\u0435\u043a\u0441\u0430\u043d\u0434\u0440\u043e\u0432\u0438\u0447","orcid":"https://orcid.org/0000-0002-5000-7257","observed_orcids":["https://orcid.org/0000-0002-5000-7257"]},"institutions":[{"id":"https://openalex.org/I2800235667","display_name":"Kurchatov Institute","ror":"https://ror.org/00n1nz186","country_code":"RU","type":"facility","lineage":["https://openalex.org/I2800235667"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"I.A. Moloshnikov","raw_affiliation_strings":["National Research Centre \u201cKurchatov Institute\u201d, Moscow, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Research Centre \u201cKurchatov Institute\u201d, Moscow, Russia","institution_ids":["https://openalex.org/I2800235667"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021722017","display_name":"Alexander G. Sboev","orcid":"https://orcid.org/0000-0002-6921-4133","observed_orcids":["https://orcid.org/0000-0002-6921-4133"]},"institutions":[{"id":"https://openalex.org/I2800235667","display_name":"Kurchatov Institute","ror":"https://ror.org/00n1nz186","country_code":"RU","type":"facility","lineage":["https://openalex.org/I2800235667"]},{"id":"https://openalex.org/I887846188","display_name":"National Research Nuclear University MEPhI","ror":"https://ror.org/04w8z7f34","country_code":"RU","type":"education","lineage":["https://openalex.org/I887846188"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"A.G. Sboev","raw_affiliation_strings":["NRC \u201cKurchatov Institute\u201d, National Research Nuclear University MEPhI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NRC \u201cKurchatov Institute\u201d, National Research Nuclear University MEPhI","institution_ids":["https://openalex.org/I2800235667","https://openalex.org/I887846188"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030818725","display_name":"\u0420\u044b\u0431\u043a\u0430 \u0420\u043e\u043c\u0430\u043d \u0411\u043e\u0440\u0438\u0441\u043e\u0432\u0438\u0447","orcid":"https://orcid.org/0000-0002-5595-6398","observed_orcids":["https://orcid.org/0000-0002-5595-6398"]},"institutions":[{"id":"https://openalex.org/I2800235667","display_name":"Kurchatov Institute","ror":"https://ror.org/00n1nz186","country_code":"RU","type":"facility","lineage":["https://openalex.org/I2800235667"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"R.B. Rybka","raw_affiliation_strings":["NRC \u201cKurchatov Institute\u201d"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NRC \u201cKurchatov Institute\u201d","institution_ids":["https://openalex.org/I2800235667"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057211077","display_name":"D.V. Gydovskikh","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2800235667","display_name":"Kurchatov Institute","ror":"https://ror.org/00n1nz186","country_code":"RU","type":"facility","lineage":["https://openalex.org/I2800235667"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"D.V. Gydovskikh","raw_affiliation_strings":["NRC \u201cKurchatov Institute\u201d"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NRC \u201cKurchatov Institute\u201d","institution_ids":["https://openalex.org/I2800235667"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5087422679"],"corresponding_institution_ids":["https://openalex.org/I2800235667"],"apc_list":null,"apc_paid":null,"fwci":0.7172,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.6682613,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":97},"biblio":{"volume":"66","issue":null,"first_page":"297","last_page":"306"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.763700008392334,"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":0.763700008392334,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.2110999971628189,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.006200000178068876,"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/keyword-extraction","display_name":"keyword extraction","score":0.7519999742507935},{"id":"https://openalex.org/keywords/search-result-visualization","display_name":"search result visualization","score":0.578000009059906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8885636329650879},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6218984127044678},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5955421924591064},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.5610362887382507},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5469874739646912},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4515010416507721},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.4168933033943176},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3957664370536804},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38746896386146545},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3778955340385437},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3610547184944153},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.35158365964889526},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.procs.2015.11.035","doi":"https://doi.org/10.1016/j.procs.2015.11.035","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2015.11.035","pdf_url":"https://www.sciencedirect.com/science/article/pii/S1877050915033840/pdf","source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.procs.2015.11.035","doi":"https://doi.org/10.1016/j.procs.2015.11.035","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2015.11.035","pdf_url":"https://www.sciencedirect.com/science/article/pii/S1877050915033840/pdf","source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-scientific","cwts-core","jufo-1","norway-1"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Procedia Computer Science","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2615622630","display_name":null,"funder_award_id":"15\u201029\u201001173","funder_id":"https://openalex.org/F4320321079","funder_display_name":"Russian Foundation for Basic Research"},{"id":"https://openalex.org/G6065839518","display_name":null,"funder_award_id":"15-29-","funder_id":"https://openalex.org/F4320321079","funder_display_name":"Russian Foundation for Basic Research"}],"funders":[{"id":"https://openalex.org/F4320321079","display_name":"Russian Foundation for Basic Research","ror":"https://ror.org/02mh1ke95"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2188994205.pdf","grobid_xml":"https://content.openalex.org/works/W2188994205.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W1496341874","https://openalex.org/W1880262756","https://openalex.org/W1958077162","https://openalex.org/W2031169004","https://openalex.org/W2101234009","https://openalex.org/W2105157020","https://openalex.org/W2125910575","https://openalex.org/W2131744502","https://openalex.org/W4236122429"],"related_works":["https://openalex.org/W2294998124","https://openalex.org/W2626873900","https://openalex.org/W2598271700","https://openalex.org/W193928184","https://openalex.org/W3021751881","https://openalex.org/W2506939128","https://openalex.org/W2136652593","https://openalex.org/W2190155047","https://openalex.org/W2044634547","https://openalex.org/W81219397"],"abstract_inverted_index":{"An":[0],"algorithm":[1,31],"of":[2,15,36,38,46,52,65,70,75,86,102,107],"finding":[3],"documents":[4,16,108],"on":[5,10,34,72,84],"a":[6,11,100],"given":[7,57],"topic":[8],"based":[9,33],"selected":[12],"reference":[13],"collection":[14],"along":[17],"with":[18,92],"creating":[19],"context-semantic":[20],"graph":[21,83,111],"for":[22,44],"visualizing":[23],"themes":[24],"in":[25,104,109],"search":[26],"results":[27,60],"is":[28,32],"presented.":[29],"The":[30],"integration":[35],"set":[37],"probabilistic,":[39],"entropic,":[40],"and":[41,50,67],"semantic":[42],"markers":[43],"extractions":[45],"weighted":[47],"key":[48,90],"words":[49],"combinations":[51],"words,":[53],"which":[54],"describe":[55],"the":[56,68,96],"topic.":[58],"Test":[59],"demonstrate":[61,99],"an":[62],"average":[63],"precision":[64],"99%":[66],"recall":[69],"84%":[71],"expert":[73],"selection":[74],"documents.":[76],"Also":[77],"developed":[78],"special":[79],"approach":[80],"to":[81,98],"constructing":[82],"base":[85],"algorithms":[87],"that":[88],"extract":[89],"phrases":[91],"weights.":[93],"It":[94],"gives":[95],"possibility":[97],"structure":[101],"subtopics":[103],"large":[105],"collections":[106],"compact":[110],"form.":[112]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2016-06-24T00:00:00"}