Arabic Sentiment Analysis: Reviews Of The Effective Used Algorithms

Öz

With the large number of pioneers of social networking sites and the large number of web users in general, many texts are formed in an unstructured way, but they may be useful in several areas if they are structured and processed using Natural Language Processing (NLP) techniques. Through these texts, comments, tweets, or even product reviews or books, we can get to know the author’s thoughts and viewpoint on a specific matter. From this principle came the idea of sentiment analysis (SA), which is an advanced and important science in artificial intelligence (AI) and machine learning (ML) and (NLP) that aims to know the aspirations and trends of people through their writings on websites in order to be used in improving a product, predicting the state of the stock market, knowing the public's political opinions, and many more applications. However, it is still at the beginning of its development in the processing of Arabic texts compared to English texts, due to the complexity of the Arabic language grammatically and morphologically, as well as the lack of Arabic corpus, so in this study we shed light on the latest literary and scientific studies that focused on Arabic sentiment analysis (ASA) to identify On the most important algorithms that have proven their quality and effectiveness in this field, where we noted the researchers’ interest in the experience of using deep learning algorithms (DL), which showed their efficiency in this field, in addition to the use of many text extraction techniques, which was the most prominent TF-IDF, CBOW and Skip-gram.

Anahtar Kelimeler

• Arabic sentiment analysis
• data mining
• deep learning
• NLP
• social media

Kaynakça

1. [1] K. Jiang and X. Lu, “Natural Language Processing and Its Applications in Machine Translation: A Diachronic Review,” Proc. 2020 IEEE 3rd Int. Conf. Safe Prod. Informatiz. IICSPI 2020, pp. 210–214, Nov. 2020, doi: 10.1109/IICSPI51290.2020.9332458.
2. [2] S. Al-Otaibi et al., “Customer Satisfaction Measurement using Sentiment Analysis,” IJACSA) Int. J. Adv. Comput. Sci. Appl., vol. 9, no. 2, 2018, Accessed: Mar. 05, 2022. [Online]. Available: www.ijacsa.thesai.org.
3. [3] A. Das, K. S. Gunturi, A. Chandrasekhar, A. Padhi, and Q. Liu, “Automated Pipeline for Sentiment Analysis of Political Tweets,” pp. 128–135, Jan. 2022, doi: 10.1109/ICDMW53433.2021.00022.
4. [4] R. Duwairi and F. Abushaqra, “Syntactic- and morphology-based text augmentation framework for Arabic sentiment analysis,” PeerJ Comput. Sci., vol. 7, pp. 1–25, 2021, doi: 10.7717/PEERJ-CS.469/.
5. [5] S. V. Pandey and A. V. Deorankar, “A Study of Sentiment Analysis Task and It’s Challenges,” Proc. 2019 3rd IEEE Int. Conf. Electr. Comput. Commun. Technol. ICECCT 2019, Feb. 2019, doi: 10.1109/ICECCT.2019.8869160.
6. [6] Y. Zahidi, Y. E. L. Younoussi, and Y. Al-Amrani, “Arabic Sentiment Analysis Problems and Challenges,” Proc. - 10th Int. Conf. Virtual Campus, JICV 2020, Dec. 2020, doi: 10.1109/JICV51605.2020.9375650.
7. [7] L. M. Alharbi and A. M. Qamar, “Arabic Sentiment Analysis of Eateries’ Reviews: Qassim region Case study,” Proc. - 2021 IEEE 4th Natl. Comput. Coll. Conf. NCCC 2021, Mar. 2021, doi: 10.1109/NCCC49330.2021.9428788.
8. [8] A. A. Sayed, E. Elgeldawi, A. M. Zaki, and A. R. Galal, “Sentiment Analysis for Arabic Reviews using Machine Learning Classification Algorithms,” Proc. 2020 Int. Conf. Innov. Trends Commun. Comput. Eng. ITCE 2020, pp. 56–63, Feb. 2020, doi: 10.1109/ITCE48509.2020.9047822.

9. [9] S. Abuuznien, Z. Abdelmohsin, E. Abdu, and I. Amin, “Sentiment Analysis for Sudanese Arabic Dialect Using comparative Supervised Learning approach,” Proc. 2020 Int. Conf. Comput. Control. Electr. Electron. Eng. ICCCEEE 2020, Feb. 2021, doi: 10.1109/ICCCEEE49695.2021.9429560.
10. [10] A. K. Al-Tamimi, A. Shatnawi, and E. Bani-Issa, “Arabic sentiment analysis of YouTube comments,” 2017 IEEE Jordan Conf. Appl. Electr. Eng. Comput. Technol. AEECT 2017, vol. 2018-January, pp. 1–6, Jul. 2017, doi: 10.1109/AEECT.2017.8257766.
11. [11] M. Alassaf and A. M. Qamar, “Aspect-Based Sentiment Analysis of Arabic Tweets in the Education Sector Using a Hybrid Feature Selection Method,” Proc. 2020 14th Int. Conf. Innov. Inf. Technol. IIT 2020, pp. 178–185, Nov. 2020, doi: 10.1109/IIT50501.2020.9299026.
12. [12] E. Omara, M. Mosa, and N. Ismail, “Deep Convolutional Network for Arabic Sentiment Analysis,” 2018 Proc. Japan-Africa Conf. Electron. Commun. Comput. JAC-ECC 2018, pp. 155–159, Apr. 2019, doi: 10.1109/JEC-ECC.2018.8679558.
13. [13] A. Abdelli, F. Guerrouf, O. Tibermacine, and B. Abdelli, “Sentiment Analysis of Arabic Algerian Dialect Using a Supervised Method,” Proc. - 2019 Int. Conf. Intell. Syst. Adv. Comput. Sci. ISACS 2019, Dec. 2019, doi: 10.1109/ISACS48493.2019.9068897.
14. [14] A. H. Ombabi, W. Ouarda, and A. M. Alimi, “Deep learning CNN–LSTM framework for Arabic sentiment analysis using textual information shared in social networks,” Soc. Netw. Anal. Min. 2020 101, vol. 10, no. 1, pp. 1–13, Jul. 2020, doi: 10.1007/S13278-020-00668-1.
15. [15] N. Khalid Bolbol and A. Y. Maghari, “Sentiment analysis of arabic tweets using supervised machine learning,” Proc. - 2020 Int. Conf. Promis. Electron. Technol. ICPET 2020, pp. 89–93, Dec. 2020, doi: 10.1109/ICPET51420.2020.00025.
16. [16] W. Al-Sorori et al., “Arabic Sentiment Analysis towards Feelings among Covid-19 Outbreak Using Single and Ensemble Classifiers,” pp. 1–6, Nov. 2021, doi: 10.1109/ITSS-IOE53029.2021.9615256.
17. [17] N. F. Alshammari and A. A. Almansour, “Aspect-based Sentiment Analysis for Arabic Content in Social Media,” 2nd Int. Conf. Electr. Commun. Comput. Eng. ICECCE 2020, Jun. 2020, doi: 10.1109/ICECCE49384.2020.9179327.
18. [18] H. Elfaik and E. H. Nfaoui, “Deep attentional bidirectional LSTM for arabic sentiment analysis in Twitter,” 2021 1st Int. Conf. Emerg. Smart Technol. Appl. eSmarTA 2021, Aug. 2021, doi: 10.1109/ESMARTA52612.2021.9515751.
19. [19] A. Alharbi, M. Kalkatawi, and M. Taileb, “Arabic Sentiment Analysis Using Deep Learning and Ensemble Methods,” Arab. J. Sci. Eng. 2021 469, vol. 46, no. 9, pp. 8913–8923, May 2021, doi: 10.1007/S13369-021-05475-0.
20. [20] M. Fawzy, M. W. Fakhr, and M. A. Rizka, “Word Embeddings and Neural Network Architectures for Arabic Sentiment