Arabic Sentiment Classification on Twitter Using Deep Learning Techniques
Gamal, Donia; Alfonse, Marco; Jiménez-Zafra, Salud María; Aref, M.;
Abstract
Sentiment analysis is one of the biggest challenges for mining textual online content generated by users. This paper concentrates on reviews and feedback from customers, which are relevant content types representing opinions. The aim of this work is to identify the semantic orientation of each sentence (e.g. positive or negative). Traditional methods for classifying sentiments often involve significant human efforts, e.g. construction of lexicons, feature engineering, etc. In recent years, deep learning has emerged as a powerful way of solving the problem of classifying sentiments. In this paper, a novel deep learning framework is proposed for sentiment classification on different sizes of four binary balanced Arabic datasets; Arabic Twitter Dataset (collected dataset), ArSenTD, Arabic Sentiment Analysis Dataset, and Arabic 100k Reviews dataset. The proposed framework overcomes the limitations of current Arabic sentiment analysis, and consists of using different types of deep neural networks: The densely connected neural network (Basic Neural Network), Convolutional Neural Network (CNN), Long Short Term Memory Network (LSTM), which is a variant of Recurrent Neural Networks (RNN), Bidirectional LSTM (Bi-LSTM), and CNN + LSTM. Experiments on different datasets prove the effectiveness of the proposed framework and its superiority over the traditional methods for datasets of large sizes approaching 100% of accuracy.
Other data
Title | Arabic Sentiment Classification on Twitter Using Deep Learning Techniques | Authors | Gamal, Donia ; Alfonse, Marco ; Jiménez-Zafra, Salud María; Aref, M. | Keywords | Arabic natural language processing;Deep learning;Opinion mining;Sentiment analysis | Issue Date | 1-Jan-2023 | Journal | Lecture Notes on Data Engineering and Communications Technologies | ISBN | 978-3-031-24474-2 978-3-031-24475-9 |
ISSN | 23674512 | DOI | 10.1007/978-3-031-24475-9_21 | Scopus ID | 2-s2.0-85152241449 |
Recommend this item
Similar Items from Core Recommender Database
Items in Ain Shams Scholar are protected by copyright, with all rights reserved, unless otherwise indicated.