Towards Improving E-Commerce Customer Review Analysis for Arabic Language Opinion Mining
Keywords:
hybrid deep learning, sentiment analysis, Arabic language, classification, AraBERTAbstract
In recent years, the rapid development of Internet-related technologies has facilitated the widespread adoption of online purchasing as a convenient means of satisfying consumer needs. Conducting sentiment analysis on user reviews on e-commerce platforms can substantially improve customer satisfaction. In order to resolve this issue, we propose a novel model for sentiment analysis that employs hybrid deep learning ensembles, combining RNN and TreeLSTM with AraBERT as the word embedding. Our research concentrates on creating a hybrid deep-learning model to predict Arabic sentiment accurately. We employ deep learning models with various word embeddings, such as RNN, LSTM, BiLSTM, TreeLSTM, RNN-LSTM, RNN-BiLSTM, and RNN-TreeLSTM. Multiple open-access datasets are used to evaluate the efficacy of the proposed model, including the BRAD dataset, the ARD dataset, and merged datasets containing 610,600 items. The experimental findings indicate that our proposed model is well-suited for evaluating the sentiments expressed in Arabic texts. Our strategy starts with extracting features using the Arabert model, followed by developing and training five hybrid deep-learning models. We attained a significant accuracy improvement of 0.9409 when comparing our method to traditional and hybrid deep learning techniques. This demonstrates that our proposed model precisely analyzes sentiment. These findings are important for enhancing the comprehension of emotions conveyed in Arabic text and have practical implications for various applications, especially e-commerce. By accurately assessing sentiment, businesses can better comprehend customer preferences and enhance consumer satisfaction by enhancing their offerings.
References
A. O. J. Ibitoye, and O. F.W. Onifade, “Utilizing RoBERTa Model for Churn Prediction through Clustered Contextual Conversation Opinion Mining,” Int. J. Intell. Syst. Appl., vol. 15, no. 6, pp. 1–8, 2023, https://doi.org/10.5815/ijisa.2023.06.01.
S. Sultana, S. Rahman Eva, N. Hasan Moon, A. Islam Jony, and D. Nandi, “A Comparison of Opinion Mining Algorithms by Using Product Review Data,” Int. J. Inf. Eng. Electron. Bus., vol. 14, no. 4, pp. 28–38, 2022, https://doi.org/10.5815/ijieeb.2022.04.04.
H. Elzayady, K. M. Badran, and G. I. Salama, “Arabic Opinion Mining Using Combined CNN – LSTM Models,” Int. J. Intell. Syst. Appl., vol. 12, no. 4, pp. 25–36, 2020, https://doi.org/10.5815/ijisa.2020.04.03.
N. Hicham, S. Karim, N. Habbat, “Customer sentiment analysis for Arabic social media using a novel ensemble machine learning approach,” IJECE, vol. 13, no 4, pp. 4504, 2023, https://doi.org/10.11591/ijece.v13i4.pp4504-4515.
N. Hicham, S. Karim, N. Habbat, “Enhancing Arabic sentiment analysis in e-commerce reviews on social media through a stacked ensemble deep learning approach,” MMEP, vol. 10, no 3, pp. 790‑798, 2023, https://doi.org/10.18280/mmep.100308.
N. Hicham, S. Karim, and N. Habbat, “An efficient approach for improving customer sentiment analysis in the Arabic language using an Ensemble machine learning technique,” Proceedings of the 2022 5th International Conference on Advanced Communication Technologies and Networking (CommNet), 2022, pp. 1–6. https://doi.org/10.1109/CommNet56067.2022.9993924.
A. Al-Hashedi et al., “Ensemble classifiers for Arabic sentiment analysis of social network (Twitter data) towards COVID-19-related conspiracy theories,” Applied Computational Intelligence and Soft Computing, vol. 2022, pp. 1‑10, 2022, https://doi.org/10.1155/2022/6614730.
G. Alwakid, T. Osman, M. E. Haj, S. Alanazi, M. Humayun, N. U. Sama, “MULDASA: Multifactor lexical sentiment analysis of social-media content in nonstandard Arabic social media,” Applied Sciences, vol. 12, no. 8, pp. 3806, 2022, https://doi.org/10.3390/app12083806.
S. Albahli, “Twitter sentiment analysis: An Arabic text mining approach based on COVID-19,” Front. Public Health, vol. 10, pp. 966779, 2022, https://doi.org/10.3389/fpubh.2022.966779.
M. Heikal, M. Torki, N. El-Makky, “Sentiment analysis of Arabic tweets using deep learning,” Procedia Computer Science, vol. 142, pp. 114‑122, 2018, https://doi.org/10.1016/j.procs.2018.10.466.
A. Alharbi, M. Kalkatawi, M. Taileb, “Arabic sentiment analysis using deep learning and ensemble methods,” Arab J Sci Eng, vol. 46, no 9, pp. 8913‑8923, 2021, https://doi.org/10.1007/s13369-021-05475-0.
A. Oussous, A. A. Lahcen, S. Belfkih, “Impact of text pre-processing and ensemble learning on Arabic sentiment analysis,” Proceedings of the 2nd International Conference on Networking, Information Systems & Security, NISS19, Rabat, Morocco: ACM Press, 2019, pp. 1‑9. https://doi.org/10.1145/3320326.3320399.
S. Al-Saqqa, N. Obeid, A. Awajan, “Sentiment analysis for Arabic text using ensemble learning,” Proceedings of the 2018 IEEE/ACS 15th IEEE International Conference on Computer Systems and Applications (AICCSA), Aqaba, October 2018, pp. 1‑7. https://doi.org/10.1109/AICCSA.2018.8612804.
S. Al-Azani E.-S. M. El-Alfy, “Using word embedding and ensemble learning for highly imbalanced data sentiment analysis in short Arabic text,” Procedia Computer Science, vol. 109, pp. 359‑366, 2017, https://doi.org/10.1016/j.procs.2017.05.365.
C. Sitaula, A. Basnet, A. Mainali, T. B. Shahi, “Deep learning-based methods for sentiment analysis on Nepali COVID-19-related tweets,” Computational Intelligence and Neuroscience, vol. 2021, pp. 1‑11, 2021, https://doi.org/10.1155/2021/2158184.
C. Sitaula, T. B. Shahi, “Multi-channel CNN to classify Nepali Covid-19 related tweets using hybrid features,” 2022, https://doi.org/10.1007/s12652-023-04692-9.
A. Dahou, S. Xiong, J. Zhou, M. H. Haddoud, P. Duan, “Word Embeddings and Convolutional Neural Network for Arabic Sentiment Classification" p. 11.
J. Devlin, M.-W. Chang, K. Lee, K. Toutanova, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” arXiv, 2019. [Online]. Available at: http://arxiv.org/abs/1810.04805.
M. Artetxe, H. Schwenk, “Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond,” 2018, https://doi.org/10.1162/tacl_a_00288.
A. Sherstinsky, “Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network,” 2018, doi: 10.48550/ARXIV.1808.03314.
S. Hochreiter, J. Schmidhuber, “Long short-term memory,” Neural Computation, vol. 9, no 8, pp. 1735‑1780, 1997, https://doi.org/10.1162/neco.1997.9.8.1735.
Z. Huang, W. Xu, K. Yu, “Bidirectional LSTM-CRF models for sequence tagging,” 2015, doi: 10.48550/ARXIV.1508.01991.
K. S. Tai, R. Socher, C. D. Manning, “Improved semantic representations from tree-structured long short-term memory networks,” 2015, https://doi.org/10.3115/v1/P15-1150.
A. Elnagar, O. Einea, “BRAD 1.0: Book reviews in Arabic dataset,” Proceedings of the 2016 IEEE/ACS 13th International Conference of Computer Systems and Applications (AICCSA), 2016, p. 1‑8. https://doi.org/10.1109/AICCSA.2016.7945800.
“Arabic 100k reviews,” [Online]. Available at: https://www.kaggle.com/datasets/abedkhooli/arabic-100k-reviews
M. A. Muslim et al., “New model combination meta-learner to improve accuracy prediction P2P lending with stacking ensemble learning,” Intelligent Systems with Applications, vol. 18, article 200204, 2023. https://doi.org/10.1016/j.iswa.2023.200204.
M. M. Abdelgwad, T. H. A. Soliman, A. I. Taloba, and M. F. Farghaly, “Arabic aspect based sentiment analysis using bidirectional GRU based models,” Journal of King Saud University – Computer and Information Sciences, vol. 34, no. 9, pp. 6652–6662, 2022, https://doi.org/10.1016/j.jksuci.2021.08.030.
Downloads
Published
How to Cite
Issue
Section
License
International Journal of Computing is an open access journal. Authors who publish with this journal agree to the following terms:• Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
• Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
• Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.