Arabic Sentiment Research Articles

Optimizing Sentiment Classification for Arabic Opinion Texts

Meanwhile, products and services reviews’ provide a guide for potential customers allowing them to reach real knowledge about such products/services while making decisions. Sentiment classification is the task of analyzing opinions expressed in textual reviews automatically. The efficiency of this task is influenced by the set of representative features extracted from the reviews. Nevertheless, the value of extracted features lies as well in those that highly contribute to the classification process. Here comes the role of dimensionality reduction to eliminate the noise and reduce the feature high space while preserving required accuracies. The Arabic language and its datasets have inherent challenges. Besides, most sentiment classification studies integrating dimensionality reduction have focused on English texts, with only few studies conducted for other languages including Arabic. Massive amounts of Arabic data have been generated due to the huge population of the Arab world, and despite that, the aforementioned technical gaps are still existing for such language. This paper proposes a supervised learning approach for Arabic reviews sentiment classification. This approach utilizes optimized compact features that depend on a well representative feature set coupled with feature reduction techniques, which manages to guarantee high accuracy and time/space savings simultaneously. The employed feature set includes a triple combination of N-gram features and positive/negative N-grams counts features obtained after considering negation handling. The proposed approach examines two different linear transformation methods; principal component analysis (PCA) as an unsupervised transformation method and latent Dirichlet allocation (LDA) as a supervised transformation method. A spam detection process is executed prior to the learning for the purpose of increasing the classifier robustness. The proposed approach has been experimented with five Arabic opinion text datasets, of different domains and varying sizes (1.6 up to 94 K reviews). Experiments have been conducted for two-class (positive/negative sentiments) and three-class (positive/negative/neutral sentiments) classification problems. Accuracy values have been recorded in the range of 95.5–99.8% for the two-class classification problem and 92–97.3% for the three-class classification problem. The LDA feature reduction outperformed PCA by an average of 4.34% and 3.52% in accuracy and F1 Score measures, respectively. The overall approach outperformed the existing related works in literature by far of 23% and 34% for accuracy and F1 Score, respectively. The experimental studies and the obtained results show the efficiency of the proposed solution, which employs optimized features that rely on integrating a feature reduction module, together with a well representative feature set based on negation handled triple combination of N-gram features and positive/negative N-grams counts features. The overall results demonstrate great improvement with 24% increase in accuracy, 93% savings in the feature space, and 97% decrease in the classification execution time.

Improving Arabic Sentiment Analysis Using CNN-Based Architectures and Text Preprocessing.

Sentiment analysis is an essential process which is important to many natural language applications. In this paper, we apply two models for Arabic sentiment analysis to the ASTD and ATDFS datasets, in both 2-class and multiclass forms. Model MC1 is a 2-layer CNN with global average pooling, followed by a dense layer. MC2 is a 2-layer CNN with max pooling, followed by a BiGRU and a dense layer. On the difficult ASTD 4-class task, we achieve 73.17%, compared to 65.58% reported by Attia et al., 2018. For the easier 2-class task, we achieve 90.06% with MC1 compared to 85.58% reported by Kwaik et al., 2019. We carry out experiments on various data splits, to match those used by other researchers. We also pay close attention to Arabic preprocessing and include novel steps not reported in other works. In an ablation study, we investigate the effect of two steps in particular, the processing of emoticons and the use of a custom stoplist. On the 4-class task, these can make a difference of up to 4.27% and 5.48%, respectively. On the 2-class task, the maximum improvements are 2.95% and 3.87%.

Arabic sentiment analysis about online learning to mitigate covid-19

Abstract The Covid-19 pandemic is forcing organizations to innovate and change their strategies for a new reality. This study collects online learning related tweets in Arabic language to perform a comprehensive emotion mining and sentiment analysis (SA) during the pandemic. The present study exploits Natural Language Processing (NLP) and Machine Learning (ML) algorithms to extract subjective information, determine polarity and detect the feeling. We begin with pulling out the tweets using Twitter APIs and then preparing for intensive preprocessing. Second, the National Research Council Canada (NRC) Word-Emotion Lexicon was examined to calculate the presence of the eight emotions at their emotional weight. Third, Information Gain (IG) is used as a filtering technique. Fourth, the latent reasons behind the negative sentiments were recognized and analyzed. Finally, different classification algorithms including Naïve Bayes (NB), Multinomial Naïve Bayes (MNB), K Nearest Neighbor (KNN), Logistic Regression (LR), and Support Vector Machine (SVM) were examined. The experiments reveal that the proposed model performs well in analyzing the perception of people about coronavirus with a maximum accuracy of about 89.6% using SVM classifier. From a practical perspective, the method could be generalized to other topical domains, such as public health monitoring and crisis management. It would help public health officials identify the progression and peaks of concerns for a disease in space and time, which enables the implementation of appropriate preventive actions to mitigate these diseases.

Arabic Sentiment Analysis for Multi-dialect Text using Machine Learning Techniques

Social media networks facilitated the availability and accessibility of a wide range of information and data. It allows the users to share and express their opinions. In addition, it presents the appraisals of the top news and the evaluation of movies, products, and services. This headway has been controlled by a well-known field called Sentiment Analysis (SA). Compared to the research studies conducted in English Sentiment Analysis (ESA), little effort is exerted in Arabic Sentiment Analysis (ASA). The Arabic language is a morphologically rich language that poses significant challenges to Natural Language Processing (NLP) systems. The purpose of the paper is to enrich the Arabic Sentiment Analysis via proposing a sentiment analysis model for analyzing an Arabic multi-dialect text using machine learning algorithms. The proposed model is applied to two datasets: ASTD Egyptian-Dialect tweets and RES Multi-Dialect restaurant reviews. Different evaluation measures were used to evaluate the proposed model to identify the best performing classifiers. The findings of this research revealed that the developed model outperformed the other two research works in terms of accuracy, precision, and recall. In addition, the Bernoulli Naive Bayes (B-NB) classifier achieved the best results with 82% for the ASTD Egyptian-Dialect tweets dataset, while the SVM classifier scored the best accuracy result for the RES Multi-Dialect reviews dataset with 87.7%.

A Deep Learning Approach Combining CNN and Bi-LSTM with SVM Classifier for Arabic Sentiment Analysis

Deep learning models have recently been proven to be successful in various natural language processing tasks, including sentiment analysis. Conventionally, a deep learning model’s architecture includes a feature extraction layer followed by a fully connected layer used to train the model parameters and classification task. In this paper, we employ a deep learning model with modified architecture that combines Convolutional Neural Network (CNN) and Bidirectional Long Short-Term Memory (Bi-LSTM) for feature extraction, with Support Vector Machine (SVM) for Arabic sentiment classification. In particular, we use a linear SVM classifier that utilizes the embedded vectors obtained from CNN and Bi-LSTM for polarity classification of Arabic reviews. The proposed method was tested on three publicly available datasets. The results show that the method achieved superior performance than the two baseline algorithms of CNN and SVM in all datasets.

Sentiment Analysis Using Stacked Gated Recurrent Unit for Arabic Tweets

Over the last decade, the amount of Arabic content created on websites and social media has grown significantly. Opinions are shared openly and freely on social media, a process that provides a rich source for trend analyses. These analyses could be accomplished artificially by natural language processing tasks, such as sentiment analysis. Those tasks are implemented initially using machine learning. Due to its accuracy in studying unstructured data, deep learning has been increasingly used as well. The gated recurrent unit (GRU) is a promising approach in textual analysis and exhibits large morphological variations. We propose two neural models, i.e., the stacked gated recurrent unit (SGRU) and stacked bidirectional gated recurrent unit (SBi-GRU), with word embedding to mine Arabic opinions. We also propose a new way of discarding stop words using automatic sentiment refinement (ASR) instead of using manually collected stop words or using low quality available Arabic stop words’ lists. The performance of our proposed models is compared with that of long short-term memory (LSTM), the support vector machine (SVM), and the most recent pretrained Arabic bidirectional encoder representations from transformers (AraBERT). In addition, we compare our models’ performance to that of an ensemble architecture of the abovementioned models to find the best model architecture for Arabic natural language processing (NLP). To the best of our knowledge, no previous studies have applied either the unidirectional or bidirectional SGRU for Arabic sentiment classification. Furthermore, no ensemble models have been implemented from these architectures for the Arabic language. The results show that the six-layer SGRU stacking and five-layer SBi-GRU stacking achieve the highest accuracy and that the ensemble method outperforms all other models, with an accuracy exceeding 90%.

Arabic Aspect-Based Sentiment Analysis: A Systematic Literature Review

Recently sentiment analysis in Arabic has attracted much attention from researchers. A modest number of studies have been conducted on Arabic sentiment analysis. However, due to the vast increase in users’ comments and reviews on social media and e-commerce websites, the necessity to detect sentence-level and aspect-level sentiments has also increased. The aspect-based sentiment analysis has emerged to detect sentiments at the aspect level. Few studies have attempted to perform aspect-based sentiment analysis on Arabic texts because Arabic natural language processing is a challenging task and because of the lack of available Arabic annotated corpora. In this paper, we conducted a systematic review of the methods, techniques, and datasets employed in aspect-based sentiment analysis on Arabic texts. A total of 21 articles published between 2015–2021 were included in this review. After analysing these articles, we found a lack of annotated datasets that can be used by researchers. In addition, the used datasets were limited to few fields. This review will serve as a foundation for researchers interested in Aspect-Based Sentiment Analysis, it will assist them in developing new models and techniques to tackle this task in the future.

A Novel Deep Learning-Based Multilevel Parallel Attention Neural (MPAN) Model for Multidomain Arabic Sentiment Analysis

Over the past few years, much work has been done to develop machine learning models that perform Arabic sentiment analysis (ASA) tasks at various levels and in different domains. However, most of this work has been based on shallow machine learning, with little attention given to deep learning approaches. Furthermore, the deep learning models used for ASA have been based on noncontextualized embedding schemes that negatively impact model performances. This article proposes a novel deep learning-based multilevel parallel attention neural (MPAN) model that uses a simple positioning binary embedding scheme (PBES) to simultaneously compute contextualized embeddings at the character, word, and sentence levels. The MPAN model then computes multilevel attention vectors and concatenates them at the output level to produce competitive accuracies. Specifically, the MPAN model produces state-of-the-art results that outperform all established ASA baselines using 34 publicly available ASA datasets. The proposed model is further shown to produce new state-of-the-art accuracies for two multidomain collections: 95.61% for a binary classification collection and 94.25% for a tertiary classification collection. Finally, the performance of the MPAN model is further validated using the public IMDB movie review dataset, on which it produces an accuracy of 96.13%, placing it in second position on the global IMDB leaderboard.

Deep Bidirectional LSTM Network Learning-Based Sentiment Analysis for Arabic Text

Abstract Sentiment analysis aims to predict sentiment polarities (positive, negative or neutral) of a given piece of text. It lies at the intersection of many fields such as Natural Language Processing (NLP), Computational Linguistics, and Data Mining. Sentiments can be expressed explicitly or implicitly. Arabic Sentiment Analysis presents a challenge undertaking due to its complexity, ambiguity, various dialects, the scarcity of resources, the morphological richness of the language, the absence of contextual information, and the absence of explicit sentiment words in an implicit piece of text. Recently, deep learning has obviously shown a great success in the field of sentiment analysis and is considered as the state-of-the-art model in Arabic Sentiment Analysis. However, the state-of-the-art accuracy for Arabic sentiment analysis still needs improvements regarding contextual information and implicit sentiment expressed in different real cases. In this paper, an efficient Bidirectional LSTM Network (BiLSTM) is investigated to enhance Arabic Sentiment Analysis, by applying Forward-Backward encapsulate contextual information from Arabic feature sequences. The experimental results on six benchmark sentiment analysis datasets demonstrate that our model achieves significant improvements over the state-of-art deep learning models and the baseline traditional machine learning methods.

A comparative study of effective approaches for Arabic sentiment analysis

Sentiment analysis (SA) is a natural language processing (NLP) application that aims to analyse and identify sentiment within a piece of text. Arabic SA started to receive more attention in the last decade with many approaches showing some effectiveness for detecting sentiment on multiple datasets. While there have been some surveys summarising some of the approaches for Arabic SA in literature, most of these approaches are reported on different datasets, which makes it difficult to identify the most effective approaches among those. In addition, those approaches do not cover the recent advances in NLP that use transformers. This paper presents a comprehensive comparative study on the most effective approaches used for Arabic sentiment analysis. We re-implement most of the existing approaches for Arabic SA and test their effectiveness on three of the most popular benchmark datasets for Arabic SA. Further, we examine the use of transformer-based language models for Arabic SA and show their superior performance compared to the existing approaches, where the best model achieves F-score scores of 0.69, 0.76, and 0.92 on the SemEval, ASTD, and ArSAS benchmark datasets. We also apply an extensive analysis of the possible reasons for failures, which show the limitations of the existing annotated Arabic SA datasets, and the challenge of sarcasm that is prominent in Arabic dialects. Finally, we highlight the main gaps in Arabic sentiment analysis research and suggest the most in-need future research directions in this area.

Improving Arabic Sentiment Classification Using a Combined Approach

The aim of sentiment classification is to automatically extract and classify a textual review as expressing a positive or negative opinion. In this paper, we study the sentiment classification problem in the Arabic language. We propose a method that attempts to extract subjective parts of document reviews. In addition, a lexicon is used to find implicit opinions and sentiments in reviews. We combine the extracted opinions with the sentiment words returned by the lexical approach. Finally, a feature reduction technique is applied. To evaluate the proposed method, support vector machines (SVM) classifier is applied for the classification task. The results indicate that our proposed approach provides superior performance in terms of classification measures.

Deep analysis of an Arabic sentiment classification system based on lexical resource expansion and custom approaches building

Sentiment analysis aims to extract emotions from a broad set of data. This paper studies the impact of lexical resource enrichment on Arabic Sentiment Analysis. At first and as there is a lack of Arabic lexical resources in the field of sentiment analysis, we build new resources and use several lexicon construction methods. The first method is manual and it lies in extracting sentimental words from a selected dataset and the second is semi-automatic and based on translating an English lexicon into Arabic followed by a manual check. Both methods generate terms in word form. Besides the mentioned resources, the paper enriches an existing resource that contains terms related to four specific domains by creating its equivalent lemmatized version. Following various methods, we created lexicons with different morphologies to enrich the existing Arabic resources. Subsequently, these resources are used in developing a polarity classifier. The paper explains the followed steps to construct the different lexical resources, defines the pre-processing levels and gives statistics related to each lexicon. Then, we present the classification approaches we used to determine the polarity of the new data. In order to perform in depth analysis of the results in correspondence to the extracted features, we opt for the unsupervised and the supervised approaches that help to have a clear view on their internal architecture and process. The experiments are based on features alteration, besides opting for a feature selection approach in order to keep the most pertinent features and reduce the characteristic vector size. Moreover, we perform an in depth analysis of the characteristic vectors and corpus nature and we explain the main causes behind results improvement and degradation. The results of the tests carried out show the relevance of each component of the system.

A Method of Deep Learning Tackles Sentiment Analysis Problem in Arabic Texts

Sentiment Analysis (SA) is a field of Natural Language Processing (NLP) whose goal is to extract the emotion, sentiment or more general opinion expressed in a human-written text. Opinions and emotions play a central role in human life. Therefore, there are many academic researches in this field for processing many languages like English However, there is scarce in its implementation with addressing Arabic Sentiment Analysis (ASA). It is a challenging field where Arabic language has a rich morphological structure and there are many other defies more than in other languages. For that, the proposed model tackles ASA by using a Deep Learning approach. In this work, one of word embedding methods, such as a first hidden layer for features extracting from the input dataset and Long Short-Term Memory (LSTM) as a deep neural network, has been used for training. The model combined with Softmax layer is applied to turn numeric outputs from LSTM layer into probabilities to classify the outputs to positive or negative. There are two datasets that are used for training the model separately with each one. The first one is ASTD dataset as a dialectal Arabic type about different tweets from internet, the results with this dataset is compared with another academic work that used the same one. The results from this work outperforms through accuracy about 14.95% and F-score about 15.14% more than what performed in the previous work. The second one is HTL dataset as a modern standard Arabic type about opinions of reviewers on different hotels from several countries. This dataset is bigger in size than the first one to show the size effect on the results of this model. So, the accuracy increased about 11% and F-score about 10.8% more than what performed with the first dataset.

Sentiment Analysis for Arabic Social Media

With the spread of social media services in Arabic societies, it leads to the explosive growth of Arabic posts, or comments. These services generate a huge volume of opinionated data on different topics such as politics and businesses. Analyzing valuable subjective information from data would assist in a better understanding and making decisions. Therefore, sentiment analysis coincides with social media networks and has become the most interesting research field in the sentiment analysis process. However, there are several challenges faced the sentiment analysis process. Arabic Sentiment analysis is indeed in its infantile stage and it has not obtained thoroughly attention wherein several challenges still need to address. Some of these challenges result from the complexity of Arabic natural language and other challenges result from social media platform itself. In this manuscript, we first study the impact of social media challenges on the challenges of Arabic language. Our findings show that such challenges add more complexities to the sentiment analysis process. Based on these findings, we review the contributed proposals, which give rise on analyzing Arabic social media data. Our review methodology is based on a set of criteria, which we propose to assess the advantages and limitations of these proposals. The interesting point here is to help researchers identify the social sentiment analysis problems along with a comprehensive survey on the sentiment analysis levels and classification approaches. Finally, we compare these proposals in terms of the average accuracy and suggest a new hybrid approach based on our findings.

Negation Handling in Machine Learning-Based Sentiment Classification for Colloquial Arabic

One crucial aspect of sentiment analysis is negation handling, where the occurrence of negation can flip the sentiment of a review and negatively affects the machine learning-based sentiment classification. The role of negation in Arabic sentiment analysis has been explored only to a limited extent, especially for colloquial Arabic. In this paper, the authors address the negation problem in colloquial Arabic sentiment classification using the machine learning approach. To this end, they propose a simple rule-based algorithm for handling the problem that affects the performance of a machine learning classifier. The rules were crafted based on observing many cases of negation, simple linguistic knowledge, and sentiment lexicon. They also examine the impact of the proposed algorithm on the performance of different machine learning algorithms. Furthermore, they compare the performance of the classifiers when their algorithm is used against three baselines. The experimental results show that there is a positive impact on the classifiers when the proposed algorithm is used compared to the baselines.

Sentiment Analysis of Arabic Reviews for Saudi Hotels Using Unsupervised Machine Learning

Virtual worlds such as social networking sites, blogs and content communities are extremely becoming one of the most powerful sources for news, markets, industries etc. These virtual worlds can be used for many aspects, because they are rich platforms full of feedback, emotions, thoughts and reviews. The main objective of this paper is to cluster Arabic reviews of Saudi hotels for sentiment analysis into positive and negative clusters. We used web scraping to collect Arabic reviews associated only with Saudi hotels, from the tourism website TripAdvisor and obtained in total 4604 Arabic reviews. Then the TF-IDF was applied to extract relevant features. An unsupervised learning approach was applied, in particular K-means and Hierarchical algorithms with two distance metrics: Cosine and Euclidean. Our manual labelled test data shows that the K-means algorithm with cosine distance performed well when applying all of our prepossessing steps. We concluded that the suggested prepossessing steps play a critical role in Arabic language processing and sentiment analysis.

Arabic dialect sentiment analysis with ZERO effort. \\ Case study: Algerian dialect

This paper presents an analytic study showing that it is entirely possible to analyze the sentiment of an Arabic dialect without constructing any resources. The idea of this work is to use the resources dedicated to a given dialect \textit{X} for analyzing the sentiment of another dialect \textit{Y}. The unique condition is to have \textit{X} and \textit{Y} in the same category of dialects. We apply this idea on Algerian dialect, which is a Maghrebi Arabic dialect that suffers from limited available tools and other handling resources required for automatic sentiment analysis. To do this analysis, we rely on Maghrebi dialect resources and two manually annotated sentiment corpus for respectively Tunisian and Moroccan dialect. We also use a large corpus for Maghrebi dialect. We use a state-of-the-art system and propose a new deep learning architecture for automatically classify the sentiment of Arabic dialect (Algerian dialect). Experimental results show that F1-score is up to 83% and it is achieved by Multilayer Perceptron (MLP) with Tunisian corpus and with Long short-term memory (LSTM) with the combination of Tunisian and Moroccan. An improvement of 15% compared to its closest competitor was observed through this study. Ongoing work is aimed at manually constructing an annotated sentiment corpus for Algerian dialect and comparing the results

Deep learning CNN–LSTM framework for Arabic sentiment analysis using textual information shared in social networks

Recently, the world has witnessed an exponential growth of social networks which have opened a venue for online users to express and share their opinions in different life aspects. Sentiment analysis has become a hot-trend research topic in the field of natural language processing due to its significant roles in analyzing the public’s opinion and deriving effective opinion-based decisions. Arabic is one of the widely used languages across social networks. However, its morphological complexities and varieties of dialects make it a challenging language for sentiment analysis. Therefore, inspired by the success of deep learning algorithms, in this paper, we propose a novel deep learning model for Arabic language sentiment analysis based on one layer CNN architecture for local feature extraction, and two layers LSTM to maintain long-term dependencies. The feature maps learned by CNN and LSTM are passed to SVM classifier to generate the final classification. This model is supported by FastText words embedding model. Extensive experiments carried out on a multi-domain corpus demonstrate the outstanding classification performance of this model with an accuracy of 90.75%. Furthermore, the proposed model is validated using different embedding models and classifiers. The results show that FastText skip-gram model and SVM classifier are more valuable alternatives for the Arabic sentiment analysis. The proposed model outperforms several well-established state-of-the-art approaches on relevant corpora with up to $$+\,20.71\%$$ accuracy improvement.

Arabic Sentiment Analysis (ASA) Using Deep Learning Approach

Sentiment analysis is one of the major fields in natural language processing whose main task is to extract sentiments, opinions, attitudes, and emotions from a subjective text. And for its importance in decision making and in people's trust with reviews on web sites, there are many academic researches to address sentiment analysis problems. Deep Learning (DL) is a powerful Machine Learning (ML) technique that has emerged with its ability of feature representation and differentiating data, leading to state-of-the-art prediction results. In recent years, DL has been widely used in sentiment analysis, however, there is scarce in its implementation in the Arabic language field. Most of the previous researches address other languages like English. The proposed model tackles Arabic Sentiment Analysis (ASA) by using a DL approach. ASA is a challenging field where Arabic language has a rich morphological structure more than other languages. In this work, Long Short-Term Memory (LSTM) as a deep neural network has been used for training the model combined with word embedding as a first hidden layer for features extracting. The results show an accuracy of about 82% is achievable using DL method.

Empirical study on imbalanced learning of Arabic sentiment polarity with neural word embedding

Empirical study on imbalanced learning of Arabic sentiment polarity with neural word embedding