Empirical Evaluation of Shallow and Deep Learning Classifiers for Arabic Sentiment Analysis

Nassif, Ali Bou; Darya, Abdollah Masoud; Elnagar, Ashraf

doi:10.1145/3466171

Cited by 14 publications

(16 citation statements)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 14 compares the best-achieved results of balanced and unbalanced HARD datasets using the proposed models after emoji and emoticon replacement and using the features with the results of other studies in the literature that predicted user opinions based on five levels of ratings. For the balanced HARD data, using the EDLB-MLP model with the total weight of emojis and emoticons, the proposed classifier has achieved an increase of 3.21% in accuracy over Nassif et al's [20] top five models: random forest, convolutional neural network, decision tree, gated recurrent unit, and bi-directional recurrent neural network. The percentage increase formula is derived from the concept of percentage increase, as follows: [(New Accuracy − Old Accuracy)/Old Accuracy] × 100.…”

Section: Resultsmentioning

confidence: 93%

“…Thus, the balanced HARD dataset has four rating levels, while the unbalanced version has five. In [20], the authors developed different deep and machine learning models for opinion mining in the reviews' domain. They used a subset of the HARD dataset, comprising 62,500 random reviews, to predict the five rating levels.…”

Section: Arabic Dataset and Opinion Mining Methodsmentioning

confidence: 99%

See 1 more Smart Citation

User Opinion Prediction for Arabic Hotel Reviews Using Lexicons and Artificial Intelligence Techniques

Al-Mutawa

Al-Aama

2023

Applied Sciences

View full text Add to dashboard Cite

Opinion mining refers to the process that helps to identify and to classify users’ emotions and opinions from any source, such as an online review. Thus, opinion mining provides organizations with an insight into their reputation based on previous customers’ opinions regarding their services or products. Automating opinion mining in different languages is still an important topic of interest for scientists, including those using the Arabic language, especially since potential customers mostly do not rate their opinion explicitly. This study proposes an ensemble-based deep learning approach using fastText embeddings and the proposed Arabic emoji and emoticon opinion lexicon to predict user opinion. For testing purposes, the study uses the publicly available Arabic HARD dataset, which includes hotel reviews associated with ratings, starting from one to five. Then, by employing multiple Arabic resources, it experiments with different generated features from the HARD dataset by combining shallow learning with the proposed approach. To the best of our knowledge, this study is the first to create a lexicon that considers emojis and emoticons for its user opinion prediction. Therefore, it is mainly a helpful contribution to the literature related to opinion mining and emojis and emoticons lexicons. Compared to other studies found in the literature related to the five-star rating prediction using the HARD dataset, the accuracy of the prediction using the proposed approach reached an increase of 3.21% using the balanced HARD dataset and an increase of 2.17% using the unbalanced HARD dataset. The proposed work can support a new direction for automating the unrated Arabic opinions in social media, based on five rating levels, to provide potential stakeholders with a precise idea about a service or product quality, instead of spending much time reading other opinions to learn that information.

show abstract

Section: Resultsmentioning

confidence: 93%

Section: Arabic Dataset and Opinion Mining Methodsmentioning

confidence: 99%

User Opinion Prediction for Arabic Hotel Reviews Using Lexicons and Artificial Intelligence Techniques

Al-Mutawa

Al-Aama

2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Natural Language Processing (NLP) for Arabic language has become a very interesting and challenging topic for researchers with its various topics and tasks [ 10 ]. In addition to the fake news detection and spam detection, there are many important and related tasks to begin with such as Arabic sentiment analysis (ASA), question answering system in Arabic language, etc.…”

Section: Related Workmentioning

confidence: 99%

Arabic fake news detection based on deep contextualized embedding models

Nassif

Elnagar

Elgendy

et al. 2022

Neural Comput & Applic

Self Cite

View full text Add to dashboard Cite

Social media is becoming a source of news for many people due to its ease and freedom of use. As a result, fake news has been spreading quickly and easily regardless of its credibility, especially in the last decade. Fake news publishers take advantage of critical situations such as the Covid-19 pandemic and the American presidential elections to affect societies negatively. Fake news can seriously impact society in many fields including politics, finance, sports, etc. Many studies have been conducted to help detect fake news in English, but research conducted on fake news detection in the Arabic language is scarce. Our contribution is twofold: first, we have constructed a large and diverse Arabic fake news dataset. Second, we have developed and evaluated transformer-based classifiers to identify fake news while utilizing eight state-of-the-art Arabic contextualized embedding models. The majority of these models had not been previously used for Arabic fake news detection. We conduct a thorough analysis of the state-of-the-art Arabic contextualized embedding models as well as comparison with similar fake news detection systems. Experimental results confirm that these state-of-the-art models are robust, with accuracy exceeding 98%.

show abstract

“…For RNN, we experimented with both the Bidirectional Long Short-Term Memory (BiLSTM) layer and Bidirectional Gated Recurrent Unit (BiGRU). We selected these three models because of their good performance on similar tasks (Al Qadi et al 2019;Al Qadi et al 2020;Elnagar et al 2020;Nassif, Darya, and Elnagar 2021a;El Rifai, Al Qadi, and Elnagar 2022).…”

Section: Extrinsic Assessmentmentioning

confidence: 99%

A benchmark for evaluating Arabic word embedding models

2022

View full text Add to dashboard Cite

Modelling the distributional semantics of such a morphologically rich language as Arabic needs to take into account its introflexive, fusional, and inflectional nature attributes that make up its combinatorial sequences and substitutional paradigms. To evaluate such word distributional models, the benchmarks that have been used thus far in Arabic have mimicked those in English. This paper reports on a benchmark that we designed to reflect linguistic patterns in both Contemporary Arabic and Classical Arabic, the first being a cover term for written and spoken Modern Standard Arabic, while the second for pre-modern Arabic. The analogy items we included in this benchmark are chosen in a transparent manner such that they would capture the major features of nouns and verbs; derivational and inflectional morphology; high-, middle-, and low-frequency patterns and lexical items; and morphosemantic, morphosyntactic, and semantic dimensions of the language. All categories included in this benchmark are carefully selected to ensure proper representation of the language. The benchmark consists of 45 roots of the trilateral, all-consonantal, and semivowel-inclusive types; six morphosemantic patterns (’af‘ala; ifta‘ala; infa‘ala; istaf‘ala; tafa‘‘ala; and tafā‘ala); five derivations (the verbal noun, active participle, and the contrasts in Masculine-Feminine; Feminine-Singular-Plural; Masculine-Singular-Plural); and morphosyntactic transformations (perfect and imperfect verbs conjugated for all pronouns); and lexical semantics (synonyms, antonyms, and hyponyms of nouns, verbs, and adjectives), as well as capital cities and currencies. All categories include an equal proportion of high-, medium-, and low-frequency items. For the purpose of validating the proposed benchmark, we developed a set of embedding models from different textual sources. Then, we tested them intrinsically using the proposed benchmark and extrinsically using two natural language processing tasks: Arabic Named Entity Recognition and Text Classification. The evaluation leads to the conclusion that the proposed benchmark is truly reflective of this morphologically rich language and discriminatory of word embeddings.

show abstract

Empirical Evaluation of Shallow and Deep Learning Classifiers for Arabic Sentiment Analysis

Cited by 14 publications

References 56 publications

User Opinion Prediction for Arabic Hotel Reviews Using Lexicons and Artificial Intelligence Techniques

User Opinion Prediction for Arabic Hotel Reviews Using Lexicons and Artificial Intelligence Techniques

Arabic fake news detection based on deep contextualized embedding models

A benchmark for evaluating Arabic word embedding models

Contact Info

Product

Resources

About