Enhancing Arabic E-Commerce Review Sentiment Analysis Using a hybrid Deep Learning Model and FastText word embedding





hybrid model, Deep learning, Arabic sentiment analysis, FastText, E-Commerce Review


The usage of NLP is shown in sentiment analysis (SA). SA extracts textual views. Arabic SA is challenging because of ambiguity, dialects, morphological variation, and the need for more resources available. The application of convolutional neural networks to Arabic SA has shown to be successful. Hybrid models improve single deep learning models. By layering many deep learning ensembles, earlier deep learning models should achieve higher accuracy. This research successfully predicted Arabic sentiment using CNN, LSTM, GRU, BiGRU, BiLSTM, CNN-BiGRU, CNN-GRU, CNN-LSTM, and CNN-biLSTM. Two enormous datasets, including the HARD and BRAD datasets, are used to evaluate the effectiveness of the proposed model. The findings demonstrated that the provided model could interpret the feelings conveyed in Arabic. The proposed procedure kicks off with the extraction of Arabert model features. After that, we developed and trained nine deep-learning models, including CNN, LSTM, GRU, BiGRU, BiLSTM, CNN-BiGRU, CNN-GRU, CNN-LSTM, and CNN-biLSTM. Concatenating the FastText and GLOVE as word embedding models. By a margin of 0.9112, our technique surpassed both standard forms of deep learning.


Download data is not yet available.
<br data-mce-bogus="1"> <br data-mce-bogus="1">


N. Habbat, H. Anoun, et L. Hassouni, « Sentiment Analysis and Topic Modeling on Arabic Twitter Data during Covid-19 Pandemic », Indones. J. Innov. Appl. Sci. IJIAS, vol. 2, no 1, p. 60‑67, févr. 2022, doi: 10.47540/ijias.v2i1.432. DOI: https://doi.org/10.47540/ijias.v2i1.432

M. A. El-Affendi, K. Alrajhi, et A. Hussain, « A Novel Deep Learning-Based Multilevel Parallel Attention Neural (MPAN) Model for Multidomain Arabic Sentiment Analysis », IEEE Access, vol. 9, p. 7508‑7518, 2021, doi: 10.1109/ACCESS.2021.3049626. DOI: https://doi.org/10.1109/ACCESS.2021.3049626

G. Badaro et al., « A Survey of Opinion Mining in Arabic: A Comprehensive System Perspective Covering Challenges and Advances in Tools, Resources, Models, Applica-tions, and Visualizations », ACM Trans. Asian Low-Resour. Lang. Inf. Process., vol. 18, no 3, p. 1‑52, sept. 2019, doi: 10.1145/3295662. DOI: https://doi.org/10.1145/3295662

M. Wankhade, A. C. S. Rao, et C. Kulkarni, « A survey on sentiment analysis methods, applications, and challenges », Artif. Intell. Rev., vol. 55, no 7, p. 5731‑5780, oct. 2022, doi: 10.1007/s10462-022-10144-1. DOI: https://doi.org/10.1007/s10462-022-10144-1

N. Hicham et S. Karim, « Analysis of Unsupervised Machine Learning Techniques for an Efficient Customer Segmentation using Clustering Ensemble and Spectral Clustering », Int. J. Adv. Comput. Sci. Appl., vol. 13, no 10, p. 9, 2022, doi: 10.14569/ijacsa.2022.0131016. DOI: https://doi.org/10.14569/IJACSA.2022.0131016

A. Al-Hashedi et al., « Ensemble Classifiers for Arabic Sentiment Analysis of Social Network (Twitter Data) towards COVID-19-Related Conspiracy Theories », Appl. Com-put. Intell. Soft Comput., vol. 2022, p. 1‑10, janv. 2022, doi: 10.1155/2022/6614730. DOI: https://doi.org/10.1155/2022/6614730

M. Al Omari, M. Al-Hajj, A. Sabra, et N. Hammami, « Hybrid CNNs-LSTM Deep Ana-lyzer for Arabic Opinion Mining », in 2019 Sixth International Conference on Social Networks Analysis, Management and Security (SNAMS), Granada, Spain, oct. 2019, p. 364‑368. doi: 10.1109/SNAMS.2019.8931819. DOI: https://doi.org/10.1109/SNAMS.2019.8931819

L. Yang, Y. Li, J. Wang, et R. S. Sherratt, « Sentiment Analysis for E-Commerce Prod-uct Reviews in Chinese Based on Sentiment Lexicon and Deep Learning », IEEE Access, vol. 8, p. 23522‑23530, 2020, doi: 10.1109/ACCESS.2020.2969854. DOI: https://doi.org/10.1109/ACCESS.2020.2969854

M. Heikal, M. Torki, et N. El-Makky, « Sentiment Analysis of Arabic Tweets using Deep Learning », Procedia Comput. Sci., vol. 142, p. 114‑122, 2018, doi: 10.1016/j.procs.2018.10.466. DOI: https://doi.org/10.1016/j.procs.2018.10.466

H. Saleh, S. Mostafa, A. Alharbi, S. El-Sappagh, et T. Alkhalifah, « Heterogeneous Ensemble Deep Learning Model for Enhanced Arabic Sentiment Analysis », Sensors, vol. 22, no 10, p. 3707, mai 2022, doi: 10.3390/s22103707. DOI: https://doi.org/10.3390/s22103707

H. A. Galal Elsayed, S. Chaffar, S. Brahim Belhaouari, et H. Raissouli, « A two-level deep learning approach for emotion recognition in Arabic news headlines », Int. J. Comput. Appl., vol. 44, no 7, p. 604‑613, juill. 2022, doi: 10.1080/1206212X.2020.1851501. DOI: https://doi.org/10.1080/1206212X.2020.1851501

N. Hicham, S. Karim, et N. Habbat, « An efficient approach for improving customer Sentiment Analysis in the Arabic language using an Ensemble machine learning tech-nique », in 2022 5th International Conference on Advanced Communication Technolo-gies and Networking (CommNet), 2022, p. 1‑6. doi: 10.1109/CommNet56067.2022.9993924. DOI: https://doi.org/10.1109/CommNet56067.2022.9993924

S. Ardabili, A. Mosavi, et A. R. Várkonyi-Kóczy, « Advances in Machine Learning Modeling Reviewing Hybrid and Ensemble Methods », MATHEMATICS & COMPUTER SCIENCE, preprint, août 2019. doi: 10.20944/preprints201908.0203.v1. DOI: https://doi.org/10.20944/preprints201908.0203.v1

O. Sagi et L. Rokach, « Ensemble learning: A survey », WIREs Data Min. Knowl. Dis-cov., vol. 8, no 4, p. e1249, 2018, doi: https://doi.org/10.1002/widm.1249. DOI: https://doi.org/10.1002/widm.1249

Y. Freund et R. E. Schapire, « A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting », J. Comput. Syst. Sci., vol. 55, no 1, p. 119‑139, août 1997, doi: 10.1006/jcss.1997.1504. DOI: https://doi.org/10.1006/jcss.1997.1504

K. Sarkar, « A Stacked Ensemble Approach to Bengali Sentiment Analysis », in Intelli-gent Human Computer Interaction, Cham, 2020, p. 102‑111. DOI: https://doi.org/10.1007/978-3-030-44689-5_10

M. A. Omari, « OCLAR: logistic regression optimisation for Arabic customers’ reviews », Int. J. Bus. Intell. Data Min., vol. 20, no 3, p. 251‑273, 2022, doi: 10.1504/IJBIDM.2022.122177. DOI: https://doi.org/10.1504/IJBIDM.2022.122177

M. Hadwan, M. A. Al-Hagery, M. Al-Sarem, et F. Saeed, « Arabic Sentiment Analysis of Users’ Opinions of Governmental Mobile Applications », Comput. Mater. Contin., vol. 72, no 3, p. 4675‑4689, 2022, doi: 10.32604/cmc.2022.027311. DOI: https://doi.org/10.32604/cmc.2022.027311

I. Abu Farha et W. Magdy, « Mazajak: An Online Arabic Sentiment Analyser », in Pro-ceedings of the Fourth Arabic Natural Language Processing Workshop, Florence, Italy, 2019, p. 192‑198. doi: 10.18653/v1/W19-4621. DOI: https://doi.org/10.18653/v1/W19-4621

A. Dahou, S. Xiong, J. Zhou, M. H. Haddoud, et P. Duan, « Word Embeddings and Convolutional Neural Network for Arabic Sentiment Classification », p. 11.

M. Kang, J. Ahn, et K. Lee, « Opinion mining using ensemble text hidden Markov mod-els for text classification », Expert Syst. Appl., vol. 94, p. 218‑227, mars 2018, doi: 10.1016/j.eswa.2017.07.019. DOI: https://doi.org/10.1016/j.eswa.2017.07.019

Ghosh, H., Tusher, M.A., Rahat, I.S., Khasim, S., Mohanty, S.N. (2023). Water Quality Assessment Through Predictive Machine Learning. In: Intelligent Computing and Networking. IC-ICN 2023. Lecture Notes in Networks and Systems, vol 699. Springer, Singapore. https://doi.org/10.1007/978-981-99-3177-4_6 DOI: https://doi.org/10.1007/978-981-99-3177-4_6

Alenezi, F.; Armghan, A.; Mohanty, S.N.; Jhaveri, R.H.; Tiwari, P. Block-Greedy and CNN Based Underwater Image Dehazing for Novel Depth Estimation and Optimal Ambient Light. Water 2021, 13, 3470. https://doi.org/10.3390/w13233470 DOI: https://doi.org/10.3390/w13233470

G. P. Rout and S. N. Mohanty, "A Hybrid Approach for Network Intrusion Detection," 2015 Fifth International Conference on Communication Systems and Network Technologies, Gwalior, India, 2015, pp. 614-617, doi: 10.1109/CSNT.2015.76. DOI: https://doi.org/10.1109/CSNT.2015.76




How to Cite

N. Hicham, H. Nassera, and S. Karim, “Enhancing Arabic E-Commerce Review Sentiment Analysis Using a hybrid Deep Learning Model and FastText word embedding ”, EAI Endorsed Trans IoT, vol. 10, Dec. 2023.