Table 4 - uploaded by Ramy Baly
Content may be subject to copyright.
Source publication
![Table 5 : Results of training the SVM model [22] and the LSTM model...](profile/Ramy-Baly/publication/320831935/figure/tbl5/AS:613911577513994@1523379334241/Results-of-training-the-SVM-model-22-and-the-LSTM-model-50-on-the-Egyptian-and-UAE_Q320.jpg)
Sentiment analysis in Arabic is challenging due to the complex morphology of the language. The task becomes more challenging when considering Twitter data that contain significant amounts of noise such as the use of Arabizi, code-switching and different dialects that varies significantly across the Arab world, the use of non-textual objects to expr...
Context in source publication
Similar publications
In this paper, we present Arap-Tweet, which is a large-scale and multi-dialectal corpus of Tweets from 11 regions and 16 countries in the Arab world representing the major Arabic dialectal varieties. To build this corpus, we collected data from Twitter and we provided a team of experienced annotators with annotation guidelines that they used to ann...
Citations
... One popular method that has been designed for microblogs is VADER [26]. Although it has shown success in deriving accurate sentiment scores [10,[26][27][28], it also has major shortcomings. Given its rule-based approach, it cannot capture complex relations between individual words. ...
Recently, various methods to predict the future price of financial assets have emerged. One promising approach is to combine the historic price with sentiment scores derived via sentiment analysis techniques. In this article, we focus on predicting the future price of Bitcoin, which is currently the most popular cryptocurrency. More precisely, we propose a hybrid approach, combining time series forecasting and sentiment prediction from microblogs, to predict the intraday price of Bitcoin. Moreover, in addition to standard sentiment analysis methods, we are the first to employ a fine-tuned BERT model for this task. We also introduce a novel weighting scheme in which the weight of the sentiment of each tweet depends on the number of its creator’s followers. For evaluation, we consider periods with strongly varying ranges of Bitcoin prices. This enables us to assess the models w.r.t. robustness and generalization to varied market conditions. Our experiments demonstrate that BERT-based sentiment analysis and the proposed weighting scheme improve upon previous methods. Specifically, our hybrid models that use linear regression as the underlying forecasting algorithm perform best in terms of the mean absolute error (MAE of 2.67) and root mean squared error (RMSE of 3.28). However, more complicated models, particularly long short-term memory networks and temporal convolutional networks, tend to have generalization and overfitting issues, resulting in considerably higher MAE and RMSE scores.
... For NLP, many DL approaches are used, such as convolutional neural networks (CNNs) [12,16] and long short-term memory (LSTM) [17]. Although such DL techniques are frequently applied to English corpora, Arabic Sentiment Analysis deep learning models are not getting as much attention [18][19][20]. ...
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.
... Journal article International Journal of Application or Innovation in Engineering & Management (Hamouda and Akaichi, 2013) International Journal on Natural Language Computing (S. , (Al-Harbi, 2017) Research in Computing Science (Mataoui et al., 2016) International Journal of Advanced Computer Science and Applications (Alowaidi et al., 2017), (Mihi et al., 2020), (Alharbi, 2021) International Journal of Computer Science and Information Security (Abdouli et al., 2017) Journal of Theoretical and Applied Information Technology (Rouby et al., 2018) Journal of Information Science (Assiri et al., 2018), (Oussous et al., 2020) Computación y Sistemas (Abdellaoui and Zrigui, 2018), (Masmoudi et al., 2021), (Masmoudi et al., 2021) IEEE Access (Alali et al., 2019), (Alwehaibi et al., 2021), (Abdelminaam et al., 2021), (Wazrah and Alhumoud, 2021), (Alowisheq et al., 2021), (Alowisheq et al., 2021), (Obiedat et al., 2022) (Duwairi, 2015), (El Naggar et al., 2017), (Alzyout et al., 2021) International Conference on Computational Linguistics: Technical Papers (Dahou et al., 2016) IEEE International Conference on Big Data (Altowayan and Tao, 2016) Arabic Natural Language Processing Workshop (Baly et al., 2017a), (Medhaffar et al., 2017) Procedia Computer Science (Al-Twairesh et al., 2017, (Baly et al., 2017b), (Al-Thubaity et al., 2018), (Soumeur et al., 2018), (Elnagar et al., 2018), (Moudjari and Akli-Astouati, 2020), International Conference on Neural Information Processing (Al-Azani and El-Alfy, 2017) Proceedings of the Computational Methods in Systems and Software (Rahab et al., 2018) The International Conference on Advanced Intelligent Systems and Informatics (Abdelhade et al., 2018) International Conference on Brain Inspired Cognitive Systems (Guellil et al., 2018) International Conference on Computational and Experimental Science and Engineering (Alnawas and Arici, 2018) Computación y Sistemas (Mulki et al., 2018) International Conference on Computer, Control, Electrical, and Electronics Engineering (Ismail et al., 2018), (Abuuznien et al., 2021) Natural Language Processing in a Deep Learning World (Tobaili et al., (Duwairi et al., 2014) (continued on next page) timent polarity''). In Fig. 2, the most dominant source is conference articles, which constitutes almost 80% of the total sources. ...
... This latter has been widely used in SA for the Arabic language. Some of the works that built a feature extractor based on prediction was Word2vec by (Le and Mikolov, 2014), as proved in the experiments conducted by (Altowayan and Tao, 2016), and (Baly et al., 2017b), Word2vec gave the best results. In the first experiment, the authors used a Tunisian dataset of 63,000 comments, that were trained through the logistic regression (LR) algorithm, scoring 81.88% in F1-score. ...
Sentiment analysis is the process of using natural language processing, computational linguistics, and other text analysis techniques to identify and extract subjective information in order to generate a judgment about the attitude or emotional state behind the text. It has been applied to many fields, including marketing, politics, and psychology. This paper presents a systematic literature review (SLR) of sentiment analysis for dialectical Arabic (DA). The variation among these dialects is primarily based on differences in grammar, vocabulary, and syntax, which makes it hard for researchers to perform polarity classification for DA. This is where our SLR comes in, assessing multiple aspects of sentiment analysis for DA as well as smoothing the advancement of researchers' works for related studies. We have identified all the steps that have a crucial influence on the machine learning model applied for dialect sentiment analysis, including text annotation, text preprocessing, feature extraction, and the approaches adopted. We have also determined the challenges and open issues of sentiment analysis for Arabic dialect (SAAD), where research efforts should be focused.
... CNN models to Roman, Spanish, and English have only been utilized in a small number of studies [42,43]. Arab Egyptian, Chinese, Emirati dialects, and Bengali have all had LSTM models applied to them [44,45]. ...
The task of analyzing sentiment has been extensively researched for a variety of languages. However, due to a dearth of readily available Natural Language Processing methods, Urdu sentiment analysis still necessitates additional study by academics. When it comes to text processing, Urdu has a lot to offer because of its rich morphological structure. The most difficult aspect is determining the optimal classifier. Several studies have incorporated ensemble learning into their methodology to boost performance by decreasing error rates and preventing overfitting. However, the baseline classifiers and the fusion procedure limit the performance of the ensemble approaches. This research made several contributions to incorporate the symmetries concept into the deep learning model and architecture: firstly, it presents a new meta-learning ensemble method for fusing basic machine learning and deep learning models utilizing two tiers of meta-classifiers for Urdu. The proposed ensemble technique combines the predictions of both the inter- and intra-committee classifiers on two separate levels. Secondly, a comparison is made between the performance of various committees of deep baseline classifiers and the performance of the suggested ensemble Model. Finally, the study’s findings are expanded upon by contrasting the proposed ensemble approach efficiency with that of other, more advanced ensemble techniques. Additionally, the proposed model reduces complexity, and overfitting in the training process. The results show that the classification accuracy of the baseline deep models is greatly enhanced by the proposed MLE approach.
... In the literature, several research efforts have been introduced to approach sentiment analysis using machine learning (Pontiki et al. 2016;Ahmed et al. 2013;Duwairi et al. 2014;Shoukry and Rafea 2012;Alomari et al. 2017). Extended efforts have used deep learning to handle bigger data and improve the classification's performance against classical machine learning models Chen et al. 2018;Pontiki et al. 2016;Heikal et al. 2018;Baly et al. 2017;Rojas-Barahona 2016). Deep learning techniques aim to overcome the limitations and problems of classical learning through efficient approaches in dealing with complex problems, large amounts of data, and its capacity to automatically extract the feature from the text (Habimana et al. 2020;Chan et al. 2020). ...
Sentiment analysis, commonly known as “opinion mining,” aims to identify sentiment polarities in opinion texts. Recent years have seen a significant increase in the acceptance of sentiment analysis by academics, businesses, governments, and several other organizations. Numerous deep-learning efforts have been developed to effectively handle more challenging sentiment analysis problems. However, the main difficulty with deep learning approaches is that they require a lot of experience and hard work to tune the optimal hyperparameters, making it a tedious and time-consuming task. Several recent research efforts have attempted to solve this difficulty by combining the power of ensemble learning and deep learning. Many of these efforts have concentrated on simple ensemble techniques, which have some drawbacks. Therefore, this paper makes the following contributions: First, we propose a meta-ensemble deep learning approach to improve the performance of sentiment analysis. In this approach, we train and fuse baseline deep learning models using three levels of meta-learners. Second, we propose the benchmark dataset “Arabic-Egyptian Corpus 2” as an extension of a previous corpus. The corpus size has been increased by 10,000 annotated tweets written in colloquial Arabic on various topics. Third, we conduct several experiments on six benchmark datasets of sentiment analysis in different languages and dialects to evaluate the performance of the proposed meta-ensemble deep learning approach. The experimental results reveal that the meta-ensemble approach effectively outperforms the baseline deep learning models. Also, the experiments reveal that meta-learning improves performance further when the probability class distributions are used to train the meta-learners.
... The efforts to create a dataset, especially on tweets, are limited to particular dialects such as those of Jordan and the Gulf [19]. Creating annotated corpora requires a more intensive effort in the Arab world [14], and incorporating more dialects is necessary to achieve better results [5]. ...
Sentiment analysis is a crucial Natural Language Processing task to analyze the user’s emotions and opinions towards events, entities, services, or products. Arabic NLP faces numerous challenges, some of which include: (1) the scarcity of resources, especially in modern standard Arabic and Arabic dialects, particularly the Bahraini one; (2) lack of multilingual deep learning models; and (3) transfer learning studies on Arabic dialects in general and Bahraini dialects specifically. This research aims to create a balanced dataset of Bahraini dialects that covers product reviews by translating English Amazon product reviews to modern standard Arabic, which were then converted to Bahraini dialects. Another aim of this research is to provide a reusable multilingual deep learning long short term memory model to analyze the parallel dataset of English, modern standard Arabic, and Bahraini dialects, which differ in linguistic properties. Many experiments were conducted using train-validate-test split and k-fold cross-validation to evaluate the model performance using accuracy, F1 score, and AUC metrics. The model runs average accuracy on all datasets ranging from 96.72% to 97.04%, 97.91% to 97.93% in F1 score, while in AUC was 98.46% to 98.7% when utilizing an augmentation technique. Moreover, a pre-trained Long Short Term Memory model was created to exploit and transfer the knowledge gained from analyzing the product reviews in Bahraini dialects to perform sentiment analysis on a small dataset of movie comments in the same dialects. The Pre-trained model performance was 96.97% accuracy, 96.65% F1 score, and 97.94% AUC.
... The machine learning methods are more accurate than the other methods when it comes to binary classification. A deep learning framework proposed by [17] identified the polarity of tweets in a 5scale classification that spans from extremely positive to extremely negative. They collected a total of about 470 thousand tweets from twelve Arab nations in four regions (North Africa, Egypt, the Levant and the Arab Gulf). ...
Social networks are popular for advertising, idea sharing, and opinion formation. Due to COVID-19, coronavirus information disseminated on social media affects people's lives directly. Individuals sometimes managed it well, but it often hampered daily activities. As a result, analyzing people's feelings is important. Sentiment analysis identifies opinions or sentiments from text. In this paper, we present an effective model that leverages the benefits of Convolutional Neural Network (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) to categorize Arabic tweets using a stacked ensemble learning model. First, the tweets are represented as vectors using a word embedding model, then the text feature is extracted by CNN, and finally the context information of the text is acquired by BiLSTM. Aravec, FastText, and ArWordVec are employed separately to assess the impact of the word embedding on the our model. We also compare the proposed method to various deep learning models: CNN, LSTM, and BiLSTM. Experiments are performed on three different Arabic datasets related to COVID-19 and vaccines. Empirical findings show that the proposed model outperformed the other models' results by achieving F-measures of 76.76\%, 87.\%, and 80.5\% on the SenWave, AraCOVID19-SSD, and ArCovidVac datasets, respectively.
... Sentiment analysis S.A. plays an important role in many real-world applications. S.A. aids business intelligence in evaluating consumer reviews about a product [1], helps in decision making for stock market prediction [2], and in the classification of different dialects in different languages, as in Arabic [3]. The spam identification on social media is successfully checked by automatically identifying spam terms across many forums, emails, and blogs through S.A. systems [4], opinion summarization, and public opinion analysis [5,6]. ...
Multilabel emotion classification is a high priority because it mimics real-life scenarios in which people display a variety of emotions. The text could express a collection of emotions such as happiness, love, and optimism, or sadness, anger, and pessimism. In this framework, the Arabic tweets data provided by SemEval 2018-Task1, E-c subtask have been first preprocessed through different normalization steps, including stemming, stop word removal, special characters, and digits removal. An emotion lexicon has been built to replace the emotions with their meaning related to emotion classes. A word embedding pre-trained model Aravec has been implemented for the feature extraction process because word embedding performed better in this task than other features such as the N-gram model. In the classification process of our framework, different machine learning techniques have been implemented, including Multi-Layer Perceptron (MLP), Support Vector Machine SVM, K Nearest Neighbor (KNN), Ensemble Random Forest (RF), and Ensemble Extra Tree. The best performance was achieved using MLP, whereas SVM proved to perform best over other Traditional machine learning techniques such as KNN, RF, and Extra tree. Extra tree achieved a multilabel Jaccard accuracy of 26.2%, Nearest Neighbor (KNN) of 37.5%, Ensemble Random Forest (RF) of 29.1%, and SVM accuracy of 46.3%. A neural network model Multi-Layer Perceptron (MLP), achieved an accuracy of 48%. The proposed framework has been compared with different previous machine learning models built for this task; the results obtained by the proposed framework outperform other previous models in most cases.
... Recently, as for Dialect Identification, researchers and developers started using deep learning networks for Sentiment Analysis with word embeddings and pretrained language models. A CNN feature extractor and transformation network was proposed in (Soumeur et al., 2018) to determine the sentiment of Algerian users' comments on various Facebook brand pages of companies in Algeria, while (Baly et al., 2017) present an LSTM network with pre-trained word embeddings to build a 5-scale Sentiment Analysis model for 4 Arabic dialects. A combination of word and document embeddings in addition to a set of semantic features were used in (Abdullah et al., 2018) for Arabic tweets. ...
The usage of social media platforms has resulted in the proliferation of work on Arabic Natural Language Processing (ANLP), including the development of resources. There is also an increased interest in processing Arabic dialects and a number of models and algorithms have been utilized for the purpose of Dialectal Arabic Natural Language Processing (DANLP). In this paper, we conduct a comparison study between some of the most well-known and most commonly used methods in NLP in order to test their performance on different corpora and two NLP tasks: Dialect Identification and Sentiment Analysis. In particular, we compare three general classes of models: a) traditional Machine Learning models with features, b) classic Deep Learning architectures (LSTMs) with pre-trained word embeddings and lastly c) different Bidirectional Encoder Representations from Transformers (BERT) models such as (Multilingual-BERT, Ara-BERT, and Twitter-Arabic-BERT). The results of the comparison show that using feature-based classification can still compete with BERT models in these dialectal Arabic contexts. The use of transformer models have the ability to outperform traditional Machine Learning approaches, depending on the type of text they have been trained on, in contrast to classic Deep Learning models like LSTMs which do not perform well on the tasks.
... Some public datasets consist of positive and negative classes such as the Large-Scale Arabic Book Review [27] and Ar-Twitter, proposed by [28]. The rest of the available dataset consists of four more classes, such as [29], which proposed four classes, and ArsenTb, which employs five classes [10,30,31]. ...
... They used the English dataset translated into Arabic, carried out the classification using RCNN, and achieved 94% prediction accuracy. Ref. [30] implemented LSTM on a small corpus with five classes in two Arabic dialects: Emirati and Egyptian. They achieved accuracies of 70% on Egyptian dialects and 63.7% on Emirati dialects. ...
Arabic is one of the official languages recognized by the United Nations (UN) and is widely used in the middle east, and parts of Asia, Africa, and other countries. Social media activity currently dominates the textual communication on the Internet and potentially represents people’s views about specific issues. Opinion mining is an important task for understanding public opinion polarity towards an issue. Understanding public opinion leads to better decisions in many fields, such as public services and business. Language background plays a vital role in understanding opinion polarity. Variation is not only due to the vocabulary but also cultural background. The sentence is a time series signal; therefore, sequence gives a significant correlation to the meaning of the text. A recurrent neural network (RNN) is a variant of deep learning where the sequence is considered. Long short-term memory (LSTM) is an implementation of RNN with a particular gate to keep or ignore specific word signals during a sequence of inputs. Text is unstructured data, and it cannot be processed further by a machine unless an algorithm transforms the representation into a readable machine learning format as a vector of numerical values. Transformation algorithms range from the Term Frequency–Inverse Document Frequency (TF-IDF) transform to advanced word embedding. Word embedding methods include GloVe, word2vec, BERT, and fastText. This research experimented with those algorithms to perform vector transformation of the Arabic text dataset. This study implements and compares the GloVe and fastText word embedding algorithms and long short-term memory (LSTM) implemented in single-, double-, and triple-layer architectures. Finally, this research compares their accuracy for opinion mining on an Arabic dataset. It evaluates the proposed algorithm with the ASAD dataset of 55,000 annotated tweets in three classes. The dataset was augmented to achieve equal proportions of positive, negative, and neutral classes. According to the evaluation results, the triple-layer LSTM with fastText word embedding achieved the best testing accuracy, at 90.9%, surpassing all other experimental scenarios.
