Open Access

ARTICLE

Classifying Multi-Lingual Reviews Sentiment Analysis in Arabic and English Languages Using the Stochastic Gradient Descent Model

Yasser Alharbi¹, Sarwar Shah Khan^2,*

1 College of Computer Science and Engineering, University of Hail, Hail, 55436, Saudi Arabia
2 Department of Computer Science, University of Engineering & Technology, Mardan, 23200, Pakistan

* Corresponding Author: Sarwar Shah Khan. Email:

Computers, Materials & Continua 2025, 83(1), 1275-1290. https://doi.org/10.32604/cmc.2025.061490

Received 26 November 2024; Accepted 13 January 2025; Issue published 26 March 2025

Abstract

Sentiment analysis plays an important role in distilling and clarifying content from movie reviews, aiding the audience in understanding universal views towards the movie. However, the abundance of reviews and the risk of encountering spoilers pose challenges for efficient sentiment analysis, particularly in Arabic content. This study proposed a Stochastic Gradient Descent (SGD) machine learning (ML) model tailored for sentiment analysis in Arabic and English movie reviews. SGD allows for flexible model complexity adjustments, which can adapt well to the Involvement of Arabic language data. This adaptability ensures that the model can capture the nuances and specific local patterns of Arabic text, leading to better performance. Two distinct language datasets were utilized, and extensive pre-processing steps were employed to optimize the datasets for analysis. The proposed SGD model, designed to accommodate the nuances of each language, aims to surpass existing models in terms of accuracy and efficiency. The SGD model achieves an accuracy of 84.89 on the Arabic dataset and 87.44 on the English dataset, making it the top-performing model in terms of accuracy on both datasets. This indicates that the SGD model consistently demonstrates high accuracy levels across Arabic and English datasets. This study helps deepen the understanding of sentiments across various linguistic datasets. Unlike many studies that focus solely on movie reviews, the Arabic dataset utilized here includes hotel reviews, offering a broader perspective.

---

Keywords

---