SENTIMENT ANALYSIS FOR E-COMMERCE PRODUCT REVIEWS BASED ON FEATURE FUSION AND BIDIRECTIONAL LONG SHORT-TERM MEMORY
Abstract
E-commerce platforms would benefit from performing sentiment analysis of their customer's feedback. However, the vast amount of transaction data makes manual sentiment analysis of product reviews impractical. This research proposes an approach to automatically classify the sentiment of a given product review based on three major steps: data preprocessing, text representation, and classification model development. First, review data is cleaned to remove ambiguity and non-meaningful elements. Second, Word2Vec and GloVe features are combined to represent the words in a more unified vector space. Lastly, these combined features are classified to determine sentiment polarity using the Bidirectional Long Short-Term Memory Network (BiLSTM) model. The test results demonstrate that the proposed BiLSTM model achieves 91% uniform performance for all four metrics (accuracy, precision, recall, and F1-score), which is 3% higher than the results achieved by the standard LSTM model. Moreover, the BiLSTM model requires 9.91 seconds less training computation time than the LSTM.
Downloads
References
W. Medhat, A. Hassan, and H. Korashy, “Sentiment analysis algorithms and applications: A survey,” Ain Shams Eng. J., vol. 5, no. 4, pp. 1093–1113, 2014, doi: 10.1016/j.asej.2014.04.011.
L. J. Laki and Z. G. Yang, “Sentiment Analysis with Neural Models for Hungarian,” Acta Polytech. Hungarica, vol. 20, no. 5, 2023, doi: 10.12700/APH.20.5.2023.5.8.
A. Ahdiat, “Pengunjung Shopee Makin Banyak, Bagaimana E-Commerce Lain?,” databoks, 2023. https://databoks.katadata.co.id/datapublish/2023/10/11/pengunjung-shopee-makin-banyak-bagaimana-e-commerce-lain
J. Yordan, “Drop in Tokopedia’s market share led to TikTok deal: GoTo chief,” The Business Times, 2024. https://www.businesstimes.com.sg/startups-tech/startups/drop-tokopedia-s-market-share-led-tiktok-deal-goto-chief
U. Singh, A. Saraswat, H. K. Azad, K. Abhishek, and S. Shitharth, “Towards improving e-commerce customer review analysis for sentiment detection,” Sci. Rep., vol. 12, no. 1, p. 21983, 2022, doi: 10.1038/s41598-022-26432-3.
M. Hoang, O. A. Bihorac, and J. Rouces, “Aspect-based sentiment analysis using BERT,” in Proceedings of the 22nd nordic conference on computational linguistics, 2019, pp. 187–196. [Online]. Available: https://hdl.handle.net/10062/93001
D. M. E.-D. M. Hussein, “A survey on sentiment analysis challenges,” J. King Saud Univ. Sci., vol. 30, no. 4, pp. 330–338, 2018, doi: 10.1016/j.jksues.2016.04.002.
A. Alslaity and R. Orji, “Machine learning techniques for emotion detection and sentiment analysis: current state, challenges, and future directions,” Behav. & Inf. Technol., vol. 43, no. 1, pp. 139–164, 2024, doi: 10.1080/0144929X.2022.2156387.
M. S. U. Miah, M. M. Kabir, T. Bin Sarwar, M. Safran, S. Alfarhood, and M. F. Mridha, “A multimodal approach to cross-lingual sentiment analysis with ensemble of transformer and LLM,” Sci. Rep., vol. 14, no. 1, p. 9603, 2024, doi: 10.1038/s41598-024-60210-7.
H. Li, A. Guo, and Y. Li, “CCMA: CapsNet for audio--video sentiment analysis using cross-modal attention,” Vis. Comput., pp. 1–12, 2024, doi: 10.1007/s00371-024-03453-9.
H. Yang et al., “Large Language Models Meet Text-Centric Multimodal Sentiment Analysis: A Survey,” arXiv Prepr. arXiv2406.08068, 2024, doi: 10.48550/arXiv.2406.08068.
M. Bin Habib, M. F. Bin Hafiz, N. A. Khan, and S. Hossain, “Multimodal Sentiment Analysis using Deep Learning Fusion Techniques and Transformers.,” Int. J. Adv. Comput. Sci. & Appl., vol. 15, no. 6, 2024, doi: 10.14569/IJACSA.2024.0150686.
R. Meifitrah, I. Darmawan, and O. N. Pratiwi, “Sentiment analysis of tokopedia application review to service product recommender system using neural collaborative filtering for marketplace in Indonesia,” in IOP Conference Series: Materials Science and Engineering, 2020, vol. 909, no. 1, p. 12071. doi: 10.1088/1757-899X/909/1/012071.
S. Qaiser and R. Ali, “Text mining: use of TF-IDF to examine the relevance of words to documents,” Int. J. Comput. Appl., vol. 181, no. 1, pp. 25–29, 2018, doi: 10.5120/ijca2018917395.
M. Taboada, “Sentiment analysis: An overview from linguistics,” Annu. Rev. Linguist., vol. 2, no. 1, pp. 325–347, 2016, doi: 10.1146/annurev-linguistics-011415-040518.
B. Warsito, A. Prahutama, and others, “Sentiment analysis on tokopedia product online reviews using random forest method,” in E3S Web of Conferences, 2020, vol. 202, p. 16006. doi: 10.1051/e3sconf/202020216006.
R. Buyya, R. N. Calheiros, and A. V. Dastjerdi, Big data: principles and paradigms. Morgan Kaufmann, 2016. doi: 10.1016/C2015-0-04136-3 Authors.
R. A. E. V. T. Sapanji, D. Hamdani, P. Harahap, and others, “Sentiment Analysis of the Top 5 E-commerce Platforms in Indonesia using Text Mining and Natural Language Processing (NLP),” J. Appl. Informatics Comput., vol. 7, no. 2, pp. 202–211, 2023, doi: 10.30871/jaic.v7i2.6517.
D. Purnamasari, A. B. Aji, S. Madenda, I. M. Wiryana, and S. Harmanto, “Sentiment Analysis Methods for Customer Review of Indonesia E-Commerce,” Int. J. Innov. Comput. Inf. Control, vol. 20, no. 1, pp. 47–60, 2024, doi: 10.24507/ijicic.20.01.47.
A. Cardova and A. Hermawan, “Implementasi Metode LSTM Untuk Mengklasifikasi Berita Palsu Pada PolitiFact,” J. FASILKOM, vol. 13, no. 3, pp. 471–479, 2023, doi: 10.37859/jf.v13i3.6175.
R. D. Kurniawan and J. Muliawan, “Sentiment analysis of indonesian election 2024 using the k-nearest neighbor method,” J. Tek. Inform., vol. 5, no. 2, pp. 653–659, 2024.
M. Wahiddianty, G. Firmasyah, H. Akbar, and others, “ANALISIS SENTIMEN OMNIBUS LAW PADA UMKM MENGGUNAKAN SUPPORT VECTOR MACHINE, NAIVE BAYES BERBASIS PARTICLE SWARM OPTIMIZATION,” J. Bisnis dan Manaj., vol. 3, no. 5, pp. 1086–1096, 2023.
H. Akbar, “Analisis Sentimen Review Institusi Pendidikan Tinggi Dari Facebook Menggunakan Jaringan Saraf Tiruan,” J. Ilmu Komput., vol. 4, no. 1, pp. 19–30, 2019.
M. F. Aslim, G. Firmansyah, B. Tjahjono, H. Akbar, and A. M. Widodo, “Utilization of LSTM (Long Short Term Memory) Based Sentiment Analysis for Stock Price Prediction,” Asian J. Soc. Humanit., vol. 1, no. 12, pp. 1241–1255, 2023.
A. S. Widagdo, K. N. Qodri, F. E. N. Saputro, N. A. R. Putri, and others, “Analisis Sentimen Mobil Listrik di Indonesia Menggunakan Long-Short Term Memory (LSTM),” J. FASILKOM, vol. 13, no. 3, pp. 416–423, 2023, doi: 10.37859/jf.v13i3.6303.
F. Fitroh and F. Hudaya, “Systematic Literature Review: Analisis Sentimen Berbasis Deep Learning,” J. Nas. Teknol. dan Sist. Inf., vol. 9, no. 2, pp. 132–140, 2023, doi: 10.25077/TEKNOSI.v9i2.2023.132-140.
P. Demotte, K. Wijegunarathna, D. Meedeniya, and I. Perera, “Enhanced sentiment extraction architecture for social media content analysis using capsule networks,” Multimed. Tools Appl., vol. 82, no. 6, pp. 8665–8690, 2023, doi: 10.1007/s11042-021-11471-1.
R. Sutoyo et al., “Product Reviews Dataset for Emotions Classification Tasks - Indonesian (PRDECT-ID) Dataset,” Mendeley Data, 2022. https://data.mendeley.com/datasets/574v66hf2v/1
T. Mikolov, K. Chen, G. Corrado, and J. Dean, “Efficient estimation of word representations in vector space,” arXiv Prepr. arXiv1301.3781, 2013, doi: 10.48550/arXiv.1301.3781.
J. Pennington, R. Socher, and C. D. Manning, “GloVe: Global vectors for word representation,” in Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), 2014, pp. 1532–1543. doi: 10.3115/v1/D14-1162.
Copyright (c) 2024 Habibullah Akbar, Diah Aryani, Marwan Kadhim Mohammed Al-shammari, M. Bahrul Ulum
This work is licensed under a Creative Commons Attribution 4.0 International License.
