1. Электронный научный архив УрФУ
  2. 00. Общеуниверситетские коллекции
  3. Научные публикации ученых УрФУ, проиндексированные в SCOPUS и WoS CC
Пожалуйста, используйте этот идентификатор, чтобы цитировать или ссылаться на этот ресурс: http://elar.urfu.ru/handle/10995/92747
Полная запись метаданных
Поле DCЗначениеЯзык
dc.contributor.authorLutfullaeva, M.en
dc.contributor.authorMedvedeva, M.en
dc.contributor.authorKomotskiy, E.en
dc.contributor.authorSpasov, K.en
dc.contributor.authorPhDen
dc.date.accessioned2020-10-20T16:37:01Z-
dc.date.available2020-10-20T16:37:01Z-
dc.date.issued2018-
dc.identifier.citationOptimization of Sentiment Analysis Methods for classifying text comments of bank customers / M. Lutfullaeva, M. Medvedeva, E. Komotskiy, K. Spasov, et al.. — DOI 10.1016/j.ifacol.2018.11.353 // IFAC-PapersOnLine. — 2018. — Vol. 32. — Iss. 51. — P. 55-60.en
dc.identifier.issn2405-8963-
dc.identifier.otherhttps://doi.org/10.1016/j.ifacol.2018.11.353pdf
dc.identifier.other1good_DOI
dc.identifier.other82598bb2-44b5-41e4-844d-79a1a4625f43pure_uuid
dc.identifier.otherhttp://www.scopus.com/inward/record.url?partnerID=8YFLogxK&scp=85058419848m
dc.identifier.urihttp://elar.urfu.ru/handle/10995/92747-
dc.description.abstractA method of sentiment analysis of the text and its approbation in solving the problem of analysis of text comments left by the Bank's customers are performed. The proposed method consists in a combination of three approaches: rules-based, dictionaries and machine learning with a teacher. New method of text vectorization- tonal vectorization instead of classical ones, such as “bag-of-words ” and TF-IDF, is proposed. The text was classified by logistic regression with regularization. A series of experiments were carried out and the optimal value of the regularization parameter was found in terms of classification accuracy. © 2018en
dc.format.mimetypeapplication/pdfen
dc.language.isoenen
dc.publisherElsevier B.V.en
dc.rightsinfo:eu-repo/semantics/openAccessen
dc.sourceIFAC-PapersOnLineen
dc.subjectMACHINE LEARNINGen
dc.subjectOPTIMIZATIONen
dc.subjectSENTIMENT ANALYSISen
dc.subjectSENTIMENT OF THE TEXTen
dc.subjectTHE BAG-OF-WORDSen
dc.subjectTONAL DICTIONARYen
dc.subjectTONAL VECTORIZERen
dc.subjectARTIFICIAL INTELLIGENCEen
dc.subjectLEARNING SYSTEMSen
dc.subjectOPTIMIZATIONen
dc.subjectSENTIMENT ANALYSISen
dc.subjectBAG OF WORDSen
dc.subjectCLASSIFICATION ACCURACYen
dc.subjectLOGISTIC REGRESSIONSen
dc.subjectOPTIMAL VALUESen
dc.subjectREGULARIZATION PARAMETERSen
dc.subjectSENTIMENT OF THE TEXTen
dc.subjectVECTORIZATIONen
dc.subjectVECTORIZERen
dc.subjectDATA MININGen
dc.titleOptimization of Sentiment Analysis Methods for classifying text comments of bank customersen
dc.typeArticleen
dc.typeinfo:eu-repo/semantics/articleen
dc.typeinfo:eu-repo/semantics/publishedVersionen
dc.identifier.rsi38641229-
dc.identifier.doi10.1016/j.ifacol.2018.11.353-
dc.identifier.scopus85058419848-
local.affiliationUral Federal University. The First President Of Russia B.N. Yeltsin, Yekaterinburg, Russian Federation
local.affiliationSofia University “St.Kliment Ohridski”, Sofia, Bulgaria
local.contributor.employeeLutfullaeva, M., Ural Federal University. The First President Of Russia B.N. Yeltsin, Yekaterinburg, Russian Federation
local.contributor.employeeMedvedeva, M., Ural Federal University. The First President Of Russia B.N. Yeltsin, Yekaterinburg, Russian Federation
local.contributor.employeeKomotskiy, E., Ural Federal University. The First President Of Russia B.N. Yeltsin, Yekaterinburg, Russian Federation
local.contributor.employeeSpasov, K., PhD, Sofia University “St.Kliment Ohridski”, Sofia, Bulgaria
local.description.firstpage55-
local.description.lastpage60-
local.issue51-
local.volume32-
dc.identifier.wos000453278300012-
local.identifier.pure8417006-
local.identifier.eid2-s2.0-85058419848-
local.identifier.wosWOS:000453278300012-
Располагается в коллекциях:Научные публикации ученых УрФУ, проиндексированные в SCOPUS и WoS CC

Файлы этого ресурса:
Файл Описание РазмерФормат 
10.1016-j.ifacol.2018.11.353.pdf515,96 kBAdobe PDFПросмотреть/Открыть
Показать базовое описание ресурса Статистика  Google Scholar





Все ресурсы в архиве электронных ресурсов защищены авторским правом, все права сохранены.