A powerful comparison of deep learning frameworks for Arabic sentiment analysis

Zahidi, Youssra; Younoussi, Yacine El; Al-Amrani, Yassine

doi:10.11591/ijece.v11i1.pp745-752

Cited by 14 publications

(11 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, results in other studies on ALSA emphasize the efficiency of deep learning approaches in gaining high performance in the state-of-art deep learning models in the sentiment analysis domain as compared to traditional machine learning classifiers and methods (Ain et al [9]; Al-Amrani [13]; Baali and Ghneim [29]; Heikal et al [43]; Zahidi et al [63]). One possible reason could be associated with the fact that there are no studies on ALSA in any Arabic sub-dialect, not to mention the lack of studies on the language of poetry which is rich with rhetoric and figurative speech.…”

Section: Tool Python Majazakmentioning

confidence: 70%

“…One more point to add here is about the methods and tools used to investigate sentiment in Arabic. Many studies have used deep learning techniques in ALSA as well as other Sklearn tools such as decision trees, NB, and SVM (Al-Amrani [13]; Baali and Ghneim [29]; Elfaik and Nfaoui [35]; Zahidi et al [63]). A comparison is made between different supervised learning classifiers vs. CNN and RNN and reported a significantly high-test accuracy level when using CNNs and RNNs.…”

Section: The Significance Of the Current Projectmentioning

confidence: 99%

See 1 more Smart Citation

Sentiment Analysis in Poems in Misurata Sub-dialect

Abugharsa

2021

IJCT

View full text Add to dashboard Cite

Over the recent decades, there has been a significant increase and development of resources for Arabic natural language processing. This includes the task of exploring Arabic Language Sentiment Analysis (ALSA) from Arabic utterances in both Modern Standard Arabic (MSA) and different Arabic dialects. This study focuses on detecting sentiment in poems written in Misurata Arabic sub-dialect spoken in Misurata, Libya. The tools used to detect sentiment from the dataset are Sklearn as well as Mazajak sentiment tool1. Logistic Regression, Random Forest, Naive Bayes (NB), and Support Vector Machines (SVM) classifiers are used with Sklearn, while the Convolutional Neural Network (CNN) is implemented with Mazajak. The results show that the traditional classifiers score a higher level of accuracy as compared to Mazajak which is built on an algorithm that includes deep learning techniques. More research is suggested to analyze Arabic sub-dialect poetry in order to investigate the aspects that contribute to sentiments in these multi-line texts; for example, the use of figurative language such as metaphors.

show abstract

Section: Tool Python Majazakmentioning

confidence: 70%

Section: The Significance Of the Current Projectmentioning

confidence: 99%

Sentiment Analysis in Poems in Misurata Sub-dialect

Abugharsa

2021

IJCT

View full text Add to dashboard Cite

show abstract

“…BERT post-training has been performed for aspect-based sentiment analysis [43]. A powerful comparison of effective approaches [44] and deep learning frameworks [45] for Arabic sentiment analysis has been performed. Different valuable tools [46] as well as challenges and trends of sentiment analysis [45] have been presented.…”

Section: Previous Workmentioning

confidence: 99%

“…A powerful comparison of effective approaches [44] and deep learning frameworks [45] for Arabic sentiment analysis has been performed. Different valuable tools [46] as well as challenges and trends of sentiment analysis [45] have been presented. The semi-supervised learning algorithms develop patterns with great generalizability from a limited labeled sample [47].…”

Section: Previous Workmentioning

confidence: 99%

The construction of an accurate Arabic sentiment analysis system based on resources alteration and approaches comparison

Touahri

2022

ACI

View full text Add to dashboard Cite

PurposeThis paper purposed a multi-facet sentiment analysis system.Design/methodology/approachHence, This paper uses multidomain resources to build a sentiment analysis system. The manual lexicon based features that are extracted from the resources are fed into a machine learning classifier to compare their performance afterward. The manual lexicon is replaced with a custom BOW to deal with its time consuming construction. To help the system run faster and make the model interpretable, this will be performed by employing different existing and custom approaches such as term occurrence, information gain, principal component analysis, semantic clustering, and POS tagging filters.FindingsThe proposed system featured by lexicon extraction automation and characteristics size optimization proved its efficiency when applied to multidomain and benchmark datasets by reaching 93.59% accuracy which makes it competitive to the state-of-the-art systems.Originality/valueThe construction of a custom BOW. Optimizing features based on existing and custom feature selection and clustering approaches.

show abstract

“…To collect Twitter posts related to the topic of COVID-19 vaccination, we utilized Twitter application programming interface (API) in Python programming language to pull tweets [49], [50]. A combination of keywords "Corona", "COVID-19"," Coronavirus", and "vaccines" are used to retrieve tweets post in January 2021.…”

Section: Sentiment Analysis Framework 31 Collecting the Datasetmentioning

confidence: 99%

Sentiment analysis of Twitter posts related to the COVID-19 vaccines

Alabid

Katheeth

2021

IJEECS

View full text Add to dashboard Cite

A real threat to the people of the world has appeared as a result of the spread of the Coronavirus disease of 2019 (COVID-19) disease. A lot of scientific and financial support has been made to devote vaccines capable of ending this epidemic. However, these vaccines have become a subject of debate between individuals, as some people tend to support taking vaccines and others rejecting them. This paper aims to create a framework model to classify the sentiment and opinions of individuals that published in Twitter regarding the COVID-19 vaccines. Identify those opinions can help public health institutions to know public opinions and direct their efforts towards promoting taking vaccinations. Two of the machines learning classification models which are the support vector machine (SVM) and naive Bayes (NB) classifier are applied here. Other pre-processing methods were applied as well to filter unstructured tweets.

show abstract

A powerful comparison of deep learning frameworks for Arabic sentiment analysis

Cited by 14 publications

References 7 publications

Sentiment Analysis in Poems in Misurata Sub-dialect

Sentiment Analysis in Poems in Misurata Sub-dialect

The construction of an accurate Arabic sentiment analysis system based on resources alteration and approaches comparison

Sentiment analysis of Twitter posts related to the COVID-19 vaccines

Contact Info

Product

Resources

About