Please use this identifier to cite or link to this item:
Appears in Collections:Computing Science and Mathematics Conference Papers and Proceedings
Author(s): Dashtipour, Kia
Gogate, Mandar
Gelbukh, Alexander
Hussain, Amir
Title: Persian Sentence-level Sentiment Polarity Classification
Citation: Dashtipour K, Gogate M, Gelbukh A & Hussain A (2021) Persian Sentence-level Sentiment Polarity Classification. In: TBC. ICOTEN 2021: International Congress of Advanced Technology and Engineering, Virtual, 04.07.2021-05.07.2021. Piscataway, NJ, USA: IEEE.
Date Deposited: 21-Jun-2021
Conference Name: ICOTEN 2021: International Congress of Advanced Technology and Engineering
Conference Dates: 2021-07-04 - 2021-07-05
Conference Location: Virtual
Abstract: Assigning positive and negative polarity into Persian sentences is difficult task, there are different approaches has been proposed in various languages such as English. However, there is not any approach available to identify the final polarity of the Persian sentences. In this paper, the novel approach has been proposed to detect polarity for Persian sentences using PerSent lexicon (Persian lexicon). For this, we have proposed two different algorithms to detect polarity in the sentence and finally SVM, MLP and Na¨ıve Bayes classifier has been used to evaluate the performance of the proposed method. The SVM received better results in comparison with Na¨ıve Bayes and MLP.
Status: AM - Accepted Manuscript
Rights: © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Files in This Item:
File Description SizeFormat 
Persian_Polarity.pdfFulltext - Accepted Version186.53 kBAdobe PDFView/Open

This item is protected by original copyright

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

The metadata of the records in the Repository are available under the CC0 public domain dedication: No Rights Reserved

If you believe that any material held in STORRE infringes copyright, please contact providing details and we will remove the Work from public display in STORRE and investigate your claim.