A review of sentiment analysis research in Arabic language

Abstract

Sentiment analysis is a task of natural language processing which has recently attracted increasing attention. However, sentiment analysis research has mainly been carried out for the English language. Although Arabic is ramping up as one of the most used languages on the Internet, only a few studies have focused on Arabic sentiment analysis so far. In this paper, we carry out an in-depth qualitative study of the most important research works in this context by presenting limits and strengths of existing approaches. In particular, we survey both approaches that leverage machine translation or transfer learning to adapt English resources to Arabic and approaches that stem directly from the Arabic language.

References in corpus (7)

• SMOTE: Synthetic Minority Over-sampling Technique
• Towards Better UD Parsing: Deep Contextualized Word Embeddings, Ensemble, and Treebank Concatenation
• Sentiment Analysis For Modern Standard Arabic And Colloquial
• What the [MASK]? Making Sense of Language-Specific BERT Models
• Critical Survey of the Freely Available Arabic Corpora
• ArSentD-LEV: A Multi-Topic Corpus for Target-based Sentiment Analysis in Arabic Levantine Tweets
• Sentiment Analysis of Arabic Tweets: Feature Engineering and A Hybrid Approach

Cited by in corpus (6)

• Arabic Fake News Detection Based on Deep Contextualized Embedding Models
• Algerian Dialect
• Deep Multi-Task Model for Sarcasm Detection and Sentiment Analysis in Arabic Language
• Overview of the Arabic Sentiment Analysis 2021 Competition at KAUST
• Arabic Sentiment Analysis with Noisy Deep Explainable Model
• Dhati+: Fine-tuned Large Language Models for Arabic Subjectivity Evaluation