Arabic Sentiment Research Articles

Enhancing Arabic Sentiment Analysis in E-Commerce Reviews on Social Media Through a Stacked Ensemble Deep Learning Approach

Enhancing Arabic Sentiment Analysis in E-Commerce Reviews on Social Media Through a Stacked Ensemble Deep Learning Approach

Developing Analytical Tools for Arabic Sentiment Analysis of COVID-19 Data

Due to the widespread distribution of coronavirus and the existence of a massive quantity of data on social networking sites, particularly Twitter, there was an urgent need to develop a model that evaluates users’ emotions and determines how they feel about the pandemic. However, the absence of resources to assist Sentiment Analysis (SA) in Arabic hampered the completion of this endeavor. This work presents the ArSentiCOVID lexicon, the first and largest Arabic SA lexicon for COVID-19 that handles negation and emojis. We design a lexicon-based sentiment analyzer tool that depends mainly on the ArSentiCOVID lexicon to perform a three-way classification. Furthermore, we employ the sentiment analyzer to automatically assemble 42K annotated Arabic tweets for COVID-19. We conduct two experiments. First, we test the effect of applying negation and emoji rules to the created lexicon. The results indicate that after applying the emoji, negation, and both rules, the F-score improved by 2.13%, 4.13%, and 6.13%, respectively. Second, we applied an ensemble method that combines four feature groups (n-grams, negation, polarity, and emojis) as input features for eight Machine Learning (ML) classifiers. The results reveal that Random Forest (RF) and Support Vector Machine (SVM) classifiers work best, and that the four feature groups combined are best for representing features produced the maximum accuracy of (92.21%), precision (92.23%), recall (92.21%), and F-score (92.23%) with 3.2% improvement over the base model.

Arabic Sentiment Analysis Based on Word Embeddings and Deep Learning

Social media networks have grown exponentially over the last two decades, providing the opportunity for users of the internet to communicate and exchange ideas on a variety of topics. The outcome is that opinion mining plays a crucial role in analyzing user opinions and applying these to guide choices, making it one of the most popular areas of research in the field of natural language processing. Despite the fact that several languages, including English, have been the subjects of several studies, not much has been conducted in the area of the Arabic language. The morphological complexities and various dialects of the language make semantic analysis particularly challenging. Moreover, the lack of accurate pre-processing tools and limited resources are constraining factors. This novel study was motivated by the accomplishments of deep learning algorithms and word embeddings in the field of English sentiment analysis. Extensive experiments were conducted based on supervised machine learning in which word embeddings were exploited to determine the sentiment of Arabic reviews. Three deep learning algorithms, convolutional neural networks (CNNs), long short-term memory (LSTM), and a hybrid CNN-LSTM, were introduced. The models used features learned by word embeddings such as Word2Vec and fastText rather than hand-crafted features. The models were tested using two benchmark Arabic datasets: Hotel Arabic Reviews Dataset (HARD) for hotel reviews and Large-Scale Arabic Book Reviews (LARB) for book reviews, with different setups. Comparative experiments utilized the three models with two-word embeddings and different setups of the datasets. The main novelty of this study is to explore the effectiveness of using various word embeddings and different setups of benchmark datasets relating to balance, imbalance, and binary and multi-classification aspects. Findings showed that the best results were obtained in most cases when applying the fastText word embedding using the HARD 2-imbalance dataset for all three proposed models: CNN, LSTM, and CNN-LSTM. Further, the proposed CNN model outperformed the LSTM and CNN-LSTM models for the benchmark HARD dataset by achieving 94.69%, 94.63%, and 94.54% accuracy with fastText, respectively. Although the worst results were obtained for the LABR 3-imbalance dataset using both Word2Vec and FastText, they still outperformed other researchers’ state-of-the-art outcomes applying the same dataset.

Hybrid Filter-Genetic Feature Selection Method For Arabic Sentiment Analysis

The dramatic increase in user comments describing their feelings about products, services, and events brings sentiment analysis to the forefront as a way to monitor public opinion about products and events. Feature selection is an important subtask of sentiment analysis, which aims to improve the performance of learning algorithms and reduce the dimensionality of a problem. Feature selection is an important subtask of sentiment analysis, as it can improve the performance of learning algorithms while reducing the dimensionality of a problem. Moreover, the high-dimensional feature spaces caused by the morphological richness of Arabic motivate further research in this area. In this paper, a hybrid filter-based and genetic feature selection algorithm is proposed using four machine learning algorithms, namely decision tree, Naive-Bayes, K-NN and meta-ensemble methods. The performance of the proposed algorithm is compared with the performance of baseline models. A wide range of experiments are conducted on two standard Arabic datasets. The experimental results clearly show that the improved methods outperform the other baseline models for Arabic sentiment analysis. The results show that the improved models outperform traditional approaches in terms of classification accuracy, with a 5% increase in the macro average of F1.

Categorization of Arabic posts using Artificial Neural Network and hash features

Sentiment analysis is an important study topic with diverse application domains including social network monitoring and automatic analysis of the body of natural language communication. Existing research on sentiment analysis has already utilised substantial domain knowledge available online comprising users’ opinion in various areas such as business, education, and social media. There is however limited literature available on Arabic language sentiment analysis. Furthermore, datasets used in majority of these studies have poor classification. In the present study, we utilised a primary dataset comprising 2122 sentences and 15,331 words compiled from 206 publicly available online posts to perform sentiment classification by using advanced machine learning technique based on Artificial Neural Networks. Unlike lexicon-based techniques that suffer from low accuracy due to their computational nature and parameter configuration, Artificial Neural Networks were used to classify people opinion posts into three categories including conservative, reform and revolution, accompanied by multiple hasher vector size to benchmark the performance of the proposed model. Extensive simulation results indicated an accuracy of 93.33%, 100%, and 100% for the classification of conservation, reform, and revolutionary classes, respectively.

Towards Generalization of Machine Learning Models: A Case Study of Arabic Sentiment Analysis

The abundance of social media data in the Arab world, specifically on Twitter, enabled companies and entities to exploit such rich and beneficial data that could be mined and used to extract important information, including sentiments and opinions of people towards a topic or a merchandise. However, with this plenitude comes the issue of producing models that are able to deliver consistent outcomes when tested within various contexts. Although model generalization has been thoroughly investigated in many fields, it has not been heavily investigated in the Arabic context. To address this gap, we investigate the generalization of models and data in Arabic with application to sentiment analysis, by performing a battery of experiments and building different models that are tested on five independent test sets to understand their performance when presented with unseen data. In doing so, we detail different techniques that improve the generalization of machine learning models in Arabic sentiment analysis, and share a large versatile dataset consisting of approximately 1.64M Arabic tweets and their corresponding sentiment to be used for future research. Our experiments concluded that the most consistent model is trained using a dataset labelled by a cascaded approach of two models, one that labels neutral tweets and another that identifies positive/negative tweets based on the Arabic emoji lexicon after class balancing. Both the BERT and the SVM models trained using the refined data achieve an average F-1 score of 0.62 and 0.60, and standard deviation of 0.06 and 0.04 respectively, when evaluated on five diverse test sets, outperforming other models by at least 17% relative gain in F-1. Based on our experiments, we share recommendations to improve model generalization for classification tasks.

Arabic sentiment analysis using GCL-based architectures and a customized regularization function

Sentiment analysis aims to extract emotions from textual data; with the proliferation of various social media platforms and the flow of data, particularly in the Arabic language, significant challenges have arisen, necessitating the development of various frameworks to handle issues. In this paper, we firstly design an architecture called Gated Convolution Long (GCL) to perform Arabic Sentiment Analysis. GCL can overcome difficulties with lengthy sequence training samples, extracting the optimal features that help improve Arabic sentiment analysis performance for binary and multiple classifications. The proposed method trains and tests in various Arabic datasets; The results are better than the baselines in all cases. GCL includes a Custom Regularization Function (CRF), which improves the performance and optimizes the validation loss. We carry out an ablation study and investigate the effect of removing CRF. CRF is shown to make a difference of up to 5.10% (2C) and 4.12% (3C). Furthermore, we study the relationship between Modern Standard Arabic and five Arabic dialects via a cross-dialect training study. Finally, we apply GCL through standard regularization (GCL+L1, GCL+L2, and GCL+LElasticNet) and our Lnew on two big Arabic sentiment datasets; GCL+Lnew gave the highest results (92.53%) with less performance time.

Evaluation of Hotel Performance with Sentiment Analysis by Deep Learning Techniques

The subject of sentiment analysis through social media sites has witnessed significant development due to the increasing reliance of people on social media in advertising and marketing, especially after the Corona pandemic. There is no doubt that the prevalence of the Arabic language makes it considered one of the most important languages all over the world. Through human comments, it can know things if they are positive or negative. But in fact, the comments are many, and it takes work to evaluate the place or the product through a detailed reading of each comment. Therefore, this study applied deep learning approaches to this issue to provide final results that could be utilized to differentiate between the comments in the dataset. Arabic Sentiment Analysis was used and gave a percentage for each positive and negative commentary. This work used eight methods of deep learning techniques after using Fast Text as embedding, except Ara BERT. These techniques are the transformer (AraBERT), RNN (Long short-term memory (LSTM), Bidirectional long-short term memory (BI-LSTM), Gated recurrent units (GRUs), Bidirectional Gated recurrent units (BI-GRU)), CNN (like ALEXNET, proposed CNN), and ensemble model (CNN with BI-GRU). The Hotel Arabic Reviews Dataset was utilized to test the models. This paper obtained the following results. In the Ara BERT model, the accuracy is 96.442%. In CNN, like the Alex Net model, the accuracy is 93.78%. In the suggested CNN model, the accuracy is 94.43%. In the suggested LSTM model, the accuracy is 95%. In the suggested BI-LSTM model, the accuracy is 95.11%. The accuracy of the suggested GRU model is 95.07%. The accuracy of the suggested BI-GRU model is 95.02%. The accuracy is 94.52% in the Ensemble CNN with BI-GRU model that has been proposed. Consequently, the AraBERT outperformed the other approaches in terms of accuracy. Because the AraBERT has already been trained on some Arabic Wikipedia entries. The LSTM, BI-LSTM, GRU, and BI-GRU, on the other hand, had comparable outcomes.

Affect Analysis in Arabic Text: Further Pre-Training Language Models for Sentiment and Emotion

One of the main tasks in the field of natural language processing (NLP) is the analysis of affective states (sentiment and emotional) based on written text, and attempts have improved dramatically in recent years. However, in studies on the Arabic language, machine learning or deep learning algorithms were utilised to analyse sentiment and emotion more often than current pre-trained language models. Additionally, further pre-training the language model on specific tasks (i.e., within-task and cross-task adaptation) has not yet been investigated for Arabic in general, and for the sentiment and emotion task in particular. In this paper, we adapt a BERT-based Arabic pretrained language model for the sentiment and emotion tasks by further pre-training it on a sentiment and emotion corpus. Hence, we developed five new Arabic models: QST, QSR, QSRT, QE3, and QE6. Five sentiment and two emotion datasets spanning both small- and large-resource settings were used to evaluate the developed models. The adaptation approaches significantly enhanced the performance of seven Arabic sentiment and emotion datasets. The developed models showed excellent improvements over the sentiment and emotion datasets, which ranged from 0.15–4.71%.

Investigating the Impact of Utilizing the K-Nearest Neighbor and Levenshtein Distance Algorithms for Arabic Sentiment Analysis on Mobile Applications

The field of sentiment analysis of Arabic scripts remains a major challenge due to the features, characteristics, and complexity of the Arabic language. Few studies on Arabic Sentiment Analysis (ASA) have been conducted to the best of our knowledge when compared to English or other Latin languages. In addition, for ASA, very few studies have been conducted regarding the comments of the users (customers) of the apps available on the Google Play Store within various mobile application reviews. Most of the current studies have been conducted on datasets collected from Twitter user comments. In this paper, we propose a new approach to the analysis of sentiment in Arabic script based on the comments dataset of users of some mobile applications available on the Google Play Store. The proposed approach involves improving algorithms such as the Levenshtein distance (LD) algorithm for data preprocessing and then combining it with the K-Nearest Neighbor (K-NN) algorithm. Through the proposed approach, the results of the experiment were shown, investigating the impact of utilizing the K-NN and LD algorithms for ASA on mobile applications effectively. The experiments were carried out. The K-NN with LD algorithm has gained a better level of evaluation compared to the K-NN algorithm. K-NN with LD algorithm has achieved the highest accuracy, recall, precision, and F-score, which were 83.11% in accuracy, 66.30% in recall, 85.10% in precision, and 74.53% in f-score evaluation measure when =3.

Arabic Sentiment Analysis for Twitter Data: A Systematic Literature Review

Social media platforms have a huge impact on our daily lives. They have succeeded in attracting many people to spend time communicating and expressing themselves. Twitter is a social media platform that could be considered as a source of public opinion about products, services, and events. Sentiment analysis is the art of studying public feelings about certain topics, which may be positive, negative, or neutral. This paper provides a systematic review of Arabic tweet sentiment analysis on papers published from 2012 to 2021 in digital libraries including IEEE Explorer, Science Direct, Springer Link, and Google Scholar. The main aim of this systematic review is to investigate the trends in the topics reported and to highlight potential new research lines. To achieve that, three main stages were implemented: planning, conducting, and reporting the review. Our findings suggest the need for an open-source large Arabic tweet dataset that can be used by researchers. Also, it was found that researchers have used various classification techniques, which led to different results.

ArSentBERT: fine-tuned bidirectional encoder representations from transformers model for Arabic sentiment classification

Sentiment analysis in the Arabic language is challenging because of its linguistic complexity. Arabic is complex in words, paragraphs, and sentence structure. Moreover, most Arabic documents contain multiple dialects, writing alphabets, and styles (e.g., Franco-Arab). Nevertheless, fine-tuned bidirectional encoder representations from transformers (BERT) models can provide a reasonable prediction accuracy for Arabic sentiment classification tasks. This paper presents a fine-tuning approach for BERT models for classifying Arabic sentiments. It uses Arabic BERT pre-trained models and tokenizers and includes three stages. The first stage is text preprocessing and data cleaning. The second stage uses transfer-learning of the pre-trained models’ weights and trains all encoder layers. The third stage uses a fully connected layer and a drop-out layer for classification. We tested our fine-tuned models on five different datasets that contain reviews in Arabic with different dialects and compared the results to 11 state-of-the-art models. The experiment results show that our models provide better prediction accuracy than our competitors. We show that the choice of the pre-trained BERT model and the tokenizer type improves the accuracy of Arabic sentiment classification.

ArSentBERT: fine-tuned bidirectional encoder representations from transformers model for Arabic sentiment classification

ArSentBERT: fine-tuned bidirectional encoder representations from transformers model for Arabic sentiment classification

Attention Mechanism Architecture for Arabic Sentiment Analysis

This article tackles the problem of sentiment analysis in the Arabic language where a new deep learning model has been put forward. The proposed model uses a hybrid bidirectional gated recurrent unit (BiGRU) and bidirectional long short-term memory (BiLSTM) additive-attention model where the Bidirectional GRU/LSTM reads the individual sentence input from left to right and vice versa, enabling the capture of the contextual information. However, the model is trained on two types of embeddings: FastText and local learnable embeddings. The BiLSTM and BiGRU architectures are put into competition to identify the best hyperparameter set for the model. The developed model has been tested on three large-scale commonly employed Arabic sentiment dataset: large-scale Arabic Book Reviews Dataset (ABRD), Hotel Arabic-Reviews Dataset (HARD), and Books Reviews in the Arabic Dataset (BRAD). The testing results demonstrate that our model outperforms both the baseline models and the state-of-the-art models reported in the original references of these datasets, achieving accuracy scores of 98.6%, 96.19%, 95.65% for LARB, HARD, and BRAD, respectively. Furthermore, to demonstrate the generalization capabilities of our model, the performances of the model have been evaluated on three other natural language processing tasks: news categorization, offensive speech detection, and Russian sentiment analysis. The results demonstrated the developed model is language- and task-independent, which offers new perspectives for the application of the developed models in several other natural language processing challenges.

A Comparative Analysis of Word Embedding and Deep Learning for Arabic Sentiment Classification

Sentiment analysis on social media platforms (i.e., Twitter or Facebook) has become an important tool to learn about users’ opinions and preferences. However, the accuracy of sentiment analysis is disrupted by the challenges of natural language processing (NLP). Recently, deep learning models have proved superior performance over statistical- and lexical-based approaches in NLP-related tasks. Word embedding is an important layer of deep learning models to generate input features. Many word embedding models have been presented for text representation of both classic and context-based word embeddings. In this paper, we present a comparative analysis to evaluate both classic and contextualized word embeddings for sentiment analysis. The four most frequently used word embedding techniques were used in their trained and pre-trained versions. The selected embedding represents classical and contextualized techniques. Classical word embedding includes algorithms such as GloVe, Word2vec, and FastText. By contrast, ARBERT is used as a contextualized embedding model. Since word embedding is more typically employed as the input layer in deep networks, we used deep learning architectures BiLSTM and CNN for sentiment classification. To achieve these goals, the experiments were applied to a series of benchmark datasets: HARD, Khooli, AJGT, ArSAS, and ASTD. Finally, a comparative analysis was conducted on the results obtained for the experimented models. Our outcomes indicate that, generally, generated embedding by one technique achieves higher performance than its pretrained version for the same technique by around 0.28 to 1.8% accuracy, 0.33 to 2.17% precision, and 0.44 to 2% recall. Moreover, the contextualized transformer-based embedding model BERT achieved the highest performance in its pretrained and trained versions. Additionally, the results indicate that BiLSTM outperforms CNN by approximately 2% in 3 datasets, HARD, Khooli, and ArSAS, while CNN achieved around 2% higher performance in the smaller datasets, AJGT and ASTD.

Improving sentiment domain adaptation for Arabic using an unsupervised self-labeling framework

Numerous domain adaptation methods have been proposed over the last decade, of which the most widely used methods have become popular owing to their generality in terms of tasks or language. While generality fails to consider language-specific issues, sentiment-specific adaptation methods rely on language-specific high-quality resources such as tagging tools or sentiment lexicons. This study proposes a resource-free unsupervised self-labeling adaptation framework for Arabic sentiment classification. By leveraging the sentiment-specific task of lexicon induction using a combination of feature selection methods and an improved hybrid word pairwise similarity technique, the proposed framework proved to be less sensitive to the issue of Arabic feature sparsity. A total of 12 traditional and 12 transformer-based experiments on two Arabic multi-domain datasets adapted in the proposed framework demonstrated that a simple yet effective unsupervised self-labeling approach outperformed complex representation learning adaptation approaches for the Arabic language. The proposed framework showed an improvement over the best-performing method by 2% on a dataset of reviews and competitive results on a dataset of tweets.

A Deep Neural Network Optimized by a Genetic Algorithm to Improve Arabic Sentiment Classification

A Deep Neural Network Optimized by a Genetic Algorithm to Improve Arabic Sentiment Classification

Improving the Polarity of Text through word2vec Embedding for Primary Classical Arabic Sentiment Analysis.

Over the past decade, Sentiment analysis has attracted significant researcher attention. Despite a huge number of studies in this field, Sentiment analysis of authors' books (classical Arabic) with extracting the embedding features has not yet been done. The recent feature extraction of Arabic text depends on the frequency of the words within the corpus without extracting the relation between these words. This paper aims to create a new classical Arabic dataset CASAD from many art books by collecting sentences from several stories with human-expert labeling. Additionally, the feature extraction of those datasets is created by word embedding techniques equivalent to Word2vec that are able to extract the deep relation which means features of the formal Arabic language. These features are evaluated by several types of machine learning for classical Arabic, for example, support vector machines (SVM), Logistic Regression (LR), Naive Bayes (NB) K-Nearest Neighbors (KNN), Latent Dirichlet Allocation (LDA) and Classification And Regression Trees (CART). Moreover, statistical methods such as validation and reliability are applied to evaluate this dataset's label. Finally, our experiments evaluated the classification rate of the feature-extraction matrices in two and three classes using six machine-learning algorithms for tenfold cross-validation that showed that the Logistic Regression with Word2Vec approach is the most accurate in predicting topic-polarity occurrence.

A Comparative Study of Effective Domain Adaptation Approaches for Arabic Sentiment Classification

Over the last decade, many methods have been developed to address the domain dependency problem of sentiment classification under domain shift. This problem is exacerbated in Arabic by its feature sparsity induced by morphological complexity and dialect variability. However, only a few studies have proposed sentiment domain adaptation methods for Arabic, with inconsistent comparisons resulting from different datasets and settings, making it difficult to identify the most effective approaches. This is the first comparative study of the most effective domain adaptation methods for Arabic sentiment classification. We replicate the existing methods proposed for Arabic and compare their effectiveness on the standard dataset settings. To further examine the extent to which adaptation performance differs between Modern Standard Arabic (MSA) and Dialectal Arabic (DA), we employ two public multi-domain sentiment datasets. We also test two well-established methods that have been thoroughly utilized in English-related studies and examine if they maintain the same levels of performance when applied to Arabic. Our findings indicate that adaptation performanace on MSA is better than on DA for all traditional approaches. However, implementing adaptation on top of transformer-based language models shows superior performance on DA. Finally, methods that have proven to excel in English suffer from low performance when applied to Arabic and exhibit negative transfer in most cases.

Arabic Tweets-Based Sentiment Analysis to Investigate the Impact of COVID-19 in KSA: A Deep Learning Approach

The World Health Organization (WHO) declared the outbreak of Coronavirus disease 2019 (COVID-19) a pandemic on 11 March 2020. The evolution of this pandemic has raised global health concerns, making people worry about how to protect themselves and their families. This has greatly impacted people’s sentiments. There was a dire need to investigate a large amount of social data such as tweets and others that emerged during the post-pandemic era for the assessment of people’s sentiments. As a result, this study aims at Arabic tweet-based sentiment analysis considering the COVID-19 pandemic in Saudi Arabia. The datasets have been collected in two different periods in three major regions in Saudi Arabia, which are: Riyadh, Dammam, and Jeddah. Tweets were annotated with three sentiments: positive, negative, and neutral after due pre-processing. Convolutional neural networks (CNN) and bi-directional long short memory (BiLSTM) deep learning algorithms were applied for classifying the sentiment of Arabic tweets. This experiment showed that the performance of CNN achieved 92.80% accuracy. The performance of BiLSTM was scored at 91.99% in terms of accuracy. Moreover, as an outcome of this study, an overwhelming upsurge in negative sentiments were observed in the dataset during COVID-19 compared to the negative sentiments of the dataset before COVID-19. The technique has been compared with the state-of-the-art techniques in the literature and it was observed that the proposed technique is promising in terms of various performance parameters.