Skip navigation
Please use this identifier to cite or link to this item: https://libeldoc.bsuir.by/handle/123456789/34543
Title: Recognition of Sarcastic Sentences in the Task of Sentiment Analysis
Other Titles: Распознавание предложений содержащих сарказм в задаче анализа тональности
Authors: Dolbin, A.
Rozaliev, V.
Orlova, Y.
Fomenkov, S.
Долбин, А. В.
Розалиев, В. Л.
Орлова, Ю. А.
Фоменков, С. А.
Keywords: материалы конференций
sentiment analysis
named entity recognition
text mining
Issue Date: 2019
Publisher: БГУИР
Citation: Recognition of Sarcastic Sentences in the Task of Sentiment Analysis / A. Dolbin [et al.] // Открытые семантические технологии проектирования интеллектуальных систем = Open Semantic Technologies for Intelligent Systems (OSTIS-2019) : материалы международной научно-технической конференции, Минск, 21 - 23 февраля 2019 г. / Белорусский государственный университет информатики и радиоэлектроники; редкол.: В. В. Голенков (гл. ред.) [и др.]. - Минск, 2019. - С. 293 - 296.
Abstract: This article is devoted to the sarcasm recognition in the text written in a natural language. The main goal is to increase the accuracy of sentiment analysis. The sentiment level determination of a text that describes the appearance of a person was chosen as a domain area for the experiment. At first, references to the personality and elements that describes appearance from text are detected using the method of latent semantic analysis. The next step is to evaluate the attitude to a person in text using pre-labeled sentiment dictionary. At this stage, the method of recognising sarcastic sentences that contains a description of the appearance is used. The sentiment level should be re-evaluated in the person information model. The results of the experiment showed that the recognition of sarcasm based on the morphological features of words and the frequency characteristics of the sentences does not effectively increase the accuracy of sentiment level determination.
URI: https://libeldoc.bsuir.by/handle/123456789/34543
Appears in Collections:OSTIS-2019

Files in This Item:
File Description SizeFormat 
Dolbin_Recognition.PDF143 kBAdobe PDFView/Open
Show full item record


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.