Enhanced TextCNN dengan Gated Mechanism dan Aspect Fusion untuk Klasifikasi Rating Film Berdasarkan Ulasan Pengguna
Keywords:
TextCNN, Gated Mechanism, Aspect Fusion, Sentiment Analysis, Rating ClassificationAbstract
This research proposes an Enhanced TextCNN architecture, integrating a Gated Mechanism and Aspect Fusion to address challenges in automatic movie rating classification from user reviews, such as text complexity and the need to understand sentiment towards specific aspects (e.g., plot, acting). The proposed model incorporates Gated Linear Units (GLU) as an adaptive filter in the convolutional layers to suppress noise and enhance key features, alongside an aspect fusion layer that employs multi-head self-attention to explicitly extract and weight information relevant to specific movie aspects from the text, enabling context-aware classification. Experimental results on a dataset of 50,000 movie reviews show the model achieves an accuracy of 85.67% and a weighted F1 score of 85.55%, significantly outperforming the baseline TextCNN (78.34% accuracy) by a 7.33% improvement, while also demonstrating robustness across reviews of varying lengths and offering better computational efficiency compared to more complex models like BERT.
References
Chen, T., Xu, R., He, Y., & Wang, X. (2022). Aspect-fused text convolutional neural network for rating prediction. Expert Systems with Applications, 187, 115912. https://doi.org/10.1016/j.eswa.2021.115912
Chollet, F. (2021). Deep learning with Python (2nd ed.). Manning Publications.
Dauphin, Y. N., Fan, A., Auli, M., & Grangier, D. (2017). Language modeling with gated convolutional networks. Proceedings of the 34th International Conference on Machine Learning (ICML), 933-941. https://proceedings.mlr.press/v70/dauphin17a.html
Devlin, J., Chang, M., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), 4171–4186. https://doi.org/10.18653/v1/N19-1423
Grandini, M., Bagli, E., & Visani, G. (2020). Metrics for multi-class classification: an overview. arXiv preprint arXiv:2008.05756. https://doi.org/10.48550/arXiv.2008.05756
He, R., Lee, W. S., Ng, H. T., & Dahlmeier, D. (2019). An interactive multi-task learning network for end-to-end aspect-based sentiment analysis. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL), 504–515. https://doi.org/10.18653/v1/P19-1048
Kim, Y. (2014). Convolutional neural networks for sentence classification. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), 1746–1751. https://doi.org/10.3115/v1/D14-1181
Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. Proceedings of the 3rd International Conference on Learning Representations (ICLR).
Li, Y., & Li, Z. (2021). Aspect-aware convolutional neural network for aspect-based sentiment analysis. Knowledge-Based Systems, 227, 107229. https://doi.org/10.1016/j.knosys.2021.107229
Liu, B. (2020). Sentiment analysis: Mining opinions, sentiments, and emotions (2nd ed.). Cambridge University Press. https://doi.org/10.1017/9781108639286
Luo, H., Li, T., Liu, B., & Zhang, J. (2022). A multi-head self-attention fusion network for aspect-based sentiment analysis. Neurocomputing, 468, 1–10. https://doi.org/10.1016/j.neucom.2021.10.028
Maas, A. L., Daly, R. E., Pham, P. T., Huang, D., Ng, A. Y., & Potts, C. (2011). Learning word vectors for sentiment analysis. Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL-HLT), 142–150.
Nguyen, T. H., & Shirai, K. (2021). Aspect-based sentiment analysis using gated convolutional networks with syntactic dependency. Proceedings of the 2021 International Conference on Asian Language Processing (IALP), 45–50. https://doi.org/10.1109/IALP54817.2021.9675263
Pennington, J., Socher, R., & Manning, C. D. (2014). GloVe: Global vectors for word representation. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), 1532–1543. https://doi.org/10.3115/v1/D14-1162
Pontiki, M., Galanis, D., Papageorgiou, H., Androutsopoulos, I., Manandhar, S., AL-Smadi, M., ... & Zhao, J. (2016). SemEval-2016 task 5: Aspect based sentiment analysis. Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016), 19–30. https://doi.org/10.18653/v1/S16-1002
Rosyani, P., & Anggraeni, D. (2023). Analisis performa model transformer untuk deteksi emosi pada teks bahasa Indonesia. Journal of Natural Language Processing (JNLP), 5(1), 56–67. https://doi.org/10.14710/jnlp.2023.5112
Rosyani, P., & Febriyanti, N. (2020). Implementasi algoritma naive Bayes dan support vector machine untuk analisis sentimen pada ulasan aplikasi mobile. Jurnal Media Informatika Budidarma, 4(3), 678–685. https://doi.org/10.30865/mib.v4i3.2211
Rosyani, P., & Hidayat, R. (2022). Peningkatan akurasi klasifikasi rating film dengan hybrid model LSTM-CNN pada dataset IMDb. Journal of Computer Science and Information Systems (JCSIS), 9(1), 78–89. https://doi.org/10.33050/jcsis.v9i1.245
Rosyani, P., & Nurjanah, S. (2022). Sistem rekomendasi film berbasis collaborative filtering dan content-based filtering menggunakan algoritma K-NN. Journal of Information Technology and Computer Science (JITeCS), 7(2), 211–222. https://doi.org/10.25126/jitecs.2022.7212
Rosyani, P., & Pratama, H. (2024). Penggunaan attention mechanism dalam convolutional neural network untuk klasifikasi teks multidomain. Journal of Artificial Intelligence Research (JAIR), 6(1), 88–99. https://doi.org/10.16194/jair.v6i1.345
Rosyani, P., & Sari, Y. (2021). Analisis sentimen ulasan film menggunakan metode convolutional neural network (CNN) dengan word embedding GloVe. Jurnal Ilmiah Teknologi Informasi, 15(2), 45-56. https://doi.org/10.25126/jti.2021.152.123
Rosyani, P., & Septyan, R. (2021). Klasifikasi berita hoax menggunakan metode deep learning dengan pretrained model BERT. Journal of Intelligent Systems and Data Science (JISD), 2(1), 34–45. https://doi.org/10.35912/jisd.v2i1.567
Rosyani, P., & Wijaya, A. (2023). Optimasi hyperparameter pada model deep learning untuk analisis sentimen ulasan produk e-commerce. Journal of Artificial Intelligence and Engineering Applications (JAIEA), 4(2), 112–125. https://doi.org/10.59934/jaiea.v4i2.89
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems (NeurIPS), 30, 5998–6008.
Wang, J., Yu, L., Lai, K. R., & Zhang, X. (2020). Tree-structured regional CNN-LSTM model for dimensional sentiment analysis. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 28, 581–591. https://doi.org/10.1109/TASLP.2019.2959251
Wang, Y., Huang, M., Zhu, X., & Zhao, L. (2020). Attention-based LSTM for aspect-level sentiment classification. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 3428–3437. https://doi.org/10.18653/v1/2020.emnlp-main.276
Yang, Z., Yang, D., Dyer, C., He, X., Smola, A., & Hovy, E. (2016). Hierarchical attention networks for document classification. Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), 1480–1489. https://doi.org/10.18653/v1/N16-1174
Zhang, L., Wang, S., & Liu, B. (2023). Gated TextCNN with adaptive pooling for sentiment analysis of short texts. Information Processing & Management, 60(2), 103245. https://doi.org/10.1016/j.ipm.2022.103245
Zhang, X., Zhao, J., & LeCun, Y. (2015). Character-level convolutional networks for text classification. Advances in Neural Information Processing Systems (NeurIPS), 28, 649–657.
Zhang, Y., & Wallace, B. C. (2017). A sensitivity analysis of (and practitioners' guide to) convolutional neural networks for sentence classification. Proceedings of the 8th International Joint Conference on Natural Language Processing (IJCNLP), 253–263.
