HYBRID CNN AND RNNS MODEL FOR SENTIMENT ANALYSIS
Abstract
In the realm of sentiment analysis, understanding public opinion and customer feedback is of paramount importance. This study researches into the performance of a hybrid model that fuses Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) for sentiment analysis, considering various datasets. The findings consistently highlight the remarkable enhancement in sentiment classification accuracy achieved by the hybrid model in comparison to basic models, owing to its ability to capture complex data patterns. While the hybrid models tend to require slightly more training time, the trade-off between accuracy and training time remains manageable. Furthermore, the hybrid models outperform basic models across datasets.
Keywords
Full Text:
PDFReferences
V. V. Nhlabano and P. E. N. Lutu, "Impact of Text Pre-Processing on the Performance of Sentiment Analysis Models for Social Media Data," 2018 International Conference on Advances in Big Data, Computing and Data Communication Systems (icABCD), Durban, South Africa, 2018, pp. 1-6, doi: 10.1109/ICABCD.2018.8465135.
Rahman and M. S. Hossen, "Sentiment Analysis on Movie Review Data Using Machine Learning Approach," 2019 International Conference on Bangla Speech and Language Processing (ICBSLP), Sylhet, Bangladesh, 2019, pp. 1-4, doi: 10.1109/ICBSLP47725.2019.201470.
K. K. Agustiningsih, E. Utami, and M. A. Alsyaibani, “Sentiment Analysis of COVID-19 Vaccines in Indonesia on Twitter Using Pre-Trained and Self-Training Word Embeddings,” Jurnal Ilmu Komputer dan Informasi, vol. 15, no. 1, pp. 39-46, Feb. 2022.
E. M. Dharma, F. L. Gaol, H. L. H. S. Warnars, and B. Soewito, "The Accuracy Comparison Among Word2Vec, Glove, and FastText Towards Convolution Neural Network (CNN) Text Classification," Journal of Theoretical and Applied Information Technology, vol. 100, no. 02, pp. 350-359, Jan. 31, 2022.
R. Catelli, S. Pelosi, and M. Esposito, "Lexicon-Based vs. Bert-Based Sentiment Analysis: A Comparative Study in Italian," Electronics, vol. 11, no. 3, art. no. 374, Jan. 2022. doi: 10.3390/electronics11030374.
R. Naquitasia, D. H. Fudholi, and L. Iswari, "Analisis Sentimen Berbasis Aspek pada Wisata Halal dengan Metode Deep Learning," JTI, vol. 16, no. 2, pp. 156, Jul. 2022, doi: 10.33365/jti.v16i2.1516.
R. Kusnadi, Y. Yusuf, A. Andriantony, R. Ardian Yaputra, and M. Caintan, "Analisis Sentimen Terhadap Game Genshin Impact Menggunakan BERT," Rabit, vol. 6, no. 2, pp. 122-129, Jul. 2021.
Z. Jianqiang and G. Xiaolin, "Comparison Research on Text Pre-processing Methods on Twitter Sentiment Analysis," in IEEE Access, vol. 5, pp. 2870-2879, 2017, doi: 10.1109/ACCESS.2017.2672677.
W. Widayat, "Analisis Sentimen Movie Review menggunakan Word2Vec dan metode LSTM Deep Learning," J. Media Informatika Budidarma, vol. 5, no. 3, pp. 1018-1026, Jul. 2021. doi: 10.30865/mib.v5i3.3111.
P. Jain, V. Saravanan, and R. Pamula, "A Hybrid CNN-LSTM: A Deep Learning Approach for Consumer Sentiment Analysis Using Qualitative User-Generated Contents," ACM Transactions on Asian and Low-Resource Language Information Processing, vol. 20, pp. 1-15, Sep. 2021. doi: 10.1145/3457206.
D. Hermanto, A. Setyanto, and E. Luthfi, "Algoritma LSTM-CNN untuk Binary Klasifikasi dengan Word2vec pada Media Online," Creative Information Technology Journal, vol. 8, pp. 64, Mar. 31, 2021. doi: 10.24076/citec.2021v8i1.264
A. L. Maas, R. E. Daly, P. T. Pham, D. Huang, A. Y. Ng, and C. Potts, "Learning Word Vectors for Sentiment Analysis," in Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Portland, Oregon, USA, June 2011, pp. 142-150, [Online]. Available: http://www.aclweb.org/anthology/P11-1015.
X. Zhang, J. Zhao, and Y. LeCun, "Character-level convolutional networks for text classification," in Advances in Neural Information Processing Systems, vol. 28, 2015.neurips.cc/paper_files/paper/2015/file/250cf8b51c773f3f8dc8b4be867a9a02-Paper.pdf
Barkha Bansal, “TripAdvisor Hotel Review Dataset”. Zenodo, Apr. 17, 2018. doi: 10.5281/zenodo.1219899.
DOI: https://doi.org/10.24167/proxies.v8i1.12473
Copyright (c) 2024 Proxies : Jurnal Informatika