Arabic Sentiment Analysis Using Naïve Bayes and CNN-LSTM

Abstract

Sentiment analysis (SA) is a useful NLP task. There are hundreds of Arabic sentiments analysis systems. However, because of the morphological nature of the Arabic languages, there are still many challenges that need more work. In this paper, two classifiers have been used: Naive Bayes and CNN-LSTM models. The experiments are conducted on Arabic tweets dataset that consists of 58k tweets written in several dialects, the same preprocessing steps have been done before fitting the models. The experimental results show that the deep Learning CNN-LSTM classifier fits better for this task which achieved an accuracy of 98% while Naive Bayes achieved 87.6%. Povzetek: .

A novel approach for Arabic business email classification based on deep learning machines

“…Comparing the results obtained from this work with the results from Abushaala & Elsheh (2022) and Suleiman, Odeh & Al-Sayyed (2022) gives:…”

“…The figure shows clearly that the values are very close with an average accuracy of about 92% with a loss of less than 8%. To verify the correctness and accuracy of the results, the results were compared to the values found in the comparative study for Arabic NLP Syntactic Tasks ( Abushaala & Elsheh, 2022 ) and a study of Arabic sentiment analysis using Naïve Bayes and CNN-LSTM ( Suleiman, Odeh & Al-Sayyed, 2022 ). The work in Suleiman, Odeh & Al-Sayyed (2022) showed also a complete comparison of the recently proposed sentiment analysis approaches.…”

“…To verify the correctness and accuracy of the results, the results were compared to the values found in the comparative study for Arabic NLP Syntactic Tasks ( Abushaala & Elsheh, 2022 ) and a study of Arabic sentiment analysis using Naïve Bayes and CNN-LSTM ( Suleiman, Odeh & Al-Sayyed, 2022 ). The work in Suleiman, Odeh & Al-Sayyed (2022) showed also a complete comparison of the recently proposed sentiment analysis approaches. The work in Abushaala & Elsheh (2022) concerns comparing different deep learning techniques based on data for Arabic NLP lexical and syntactic tasks.…”

“…The work in Abushaala & Elsheh (2022) concerns comparing different deep learning techniques based on data for Arabic NLP lexical and syntactic tasks. Table 4 shows the F1-score of the different models tested, while the work in Suleiman, Odeh & Al-Sayyed (2022) summarized most of the recently proposed Arabic sentiment analysis classifiers. Table 5 shows the accuracy values for the recently proposed sentiment analysis approaches.…”

Automatic Question Generation Monolingual Multilingual pre-trained Models using RNN and Transformer in Low Resource Indonesian Language

“…In addition, because the IndoNLU benchmark only covers NLU tasks in Indonesian, such as sentiment analysis [26,27,28,29,30], which is similar to the GLUE [31] benchmark for English Natural Language Understanding (NLU) tasks, while the Question Generation task is an NLG task, the GEM benchmark, which is a benchmark for various NLG tasks including Question Generation, should also be applied [32]. The resources of the GEM benchmark have selected and processed the most common dataset for the available NLG tasks.…”