Abstract
The existing end-to-end Aspect-Based Sentiment Analysis (ABSA) algorithms focus on feature extraction by a single model, which leads to the loss of the important local or global information. In order to capture both local and global information of sentences, an end-to-end ABSA method based on features fusion is proposed. Firstly, the pre-trained model BERT is applied to obtain word vectors; secondly, Iterated Dilated Convolutions Neural Networks (IDCNN) and Bi-directional Long Short-Term Memory (BiLSTM) with Self-Attention mechanism (BLSA) are adopted to capture local and global features of sentences, and the generated local and context dependency vectors are fused to yield feature vectors. Finally, Conditional Random Fields (CRF) is applied to predict aspect words and sentiment polarity simultaneously. On Laptop14 and Restaurant datasets, our model’s F1 scores increased by 0.51%, 3.11% respectively compared with the best model in the comparison experiment, and 0.74%, 0.78% respectively compared with the single model with the best effect in the ablation experiment. We removed each important module in turn in subsequent experiments and compared it with our model. The experimental results demonstrate the effectiveness of this method in aspect word recognition and its better generalization ability.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Yuan, J.H., Wu, Y., Lu, X.: Recent advances in deep learning based sentiment analysis. China Technol. 63(10), 1947–1970 (2020)
Chen, L., Guan, J.L., He, J.H., Peng, J.Y.: Advances in emotion classification research. Comput. Res. Dev. 54(06), 1150–1170 (2017)
Yadollahi, A., Shahraki, A.G., Zaiane, O.R.: Current state of text sentiment analysis is from opinion to emotion mining. ACM Comput. Surv. 50(2), 1–33 (2018)
Meena, A., Prabhakar, T.V.: Sentence level sentiment analysis in the presence of conjuncts using linguistic analysis. In: Amati, G., Carpineto, C., Romano, G. (eds.) ECIR 2007. LNCS, vol. 4425, pp. 573–580. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-71496-5_53
Mitchell, M., Aguilar, J., Wilson, T., Durme, B.V: Open domain targeted sentiment. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, USA, pp. 1643–1654. Association for Computational Linguistics (2013)
Tang, D., Qin, B., Feng, X.C., Liu, T.: Effective LSTMs for target-dependent sentiment classification. In: Matsumoto, Y., Prasead, R. (eds.) Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, COLING, Japan, vol. 1311, pp. 3298–3307. The COLING 2016 Organizing Committee (2016). https://doi.org/10.48550/arXiv.1512.01100
Wang, Y.Q., Huang, M., Zhu, X.Y., Zhao, L.: Attention-based LSTM for aspect-level sentiment classification. In: Su, J., Duh, K. (eds.) Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, EMNLP, vol. 1058, pp. 606–615. Association for Computational Linguistics, Texas (2016). https://doi.org/10.18653/v1/D16-1058
Xing, Y.P., Xiao, C.B., Wu, Y.F., Ding, Z.M.: A convolutional neural network for aspect-level sentiment classification. Int. J. Pattern Recogn. Artif. Intell. 33(14), 46–59 (2019)
Zhang, M., Zhang, Y., Vo, D.T.: Neural networks for open domain targeted sentiment. In: Marquez, L., Callison-Burch, C. (eds.) Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, EMNLP, Portugal, vol. 1073, pp. 612–621. Association for Computational Linguistics (2015). https://doi.org/10.18653/v1/D15-1073
Li, X., Bing, L., Li, P.J., Lam, W.: A unified model for opinion target extraction and target sentiment prediction. In: Pascal, V.H., Zhang, Z.H. (eds.) Proceedings of the AAAI Conference on Artificial Intelligence, AAAI, USA, vol. 33, pp. 6714–6721. Association for the Advancement of Artificial Intelligence (2019). https://doi.org/10.1609/aaai.v33i01.33016714
Li, X., Bing, L., Li, P.J., Lam, W.: Exploiting BERT for end-to-end aspect-based sentiment analysis. In: 5th Workshop on Noisy User-Generated Text (W-NUT 2019), Hong Kong, pp. 34–41. Association for Computational Linguistics (2019). https://doi.org/10.18653/v1/D19-5505
Strubell, E., Verga, P., Belanger, D.: Fast and accurate entity recognition with iterated dilated convolutions. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, Denmark, pp. 2670–2680. Association for Computational Linguistics (2017)
Yang, B., Li, J., Wang, D.F.: Context-aware self-attention networks. In: Pascal, V.H., Zhihua, Z. (eds.) Proceedings of the AAAI Conference on Artificial Intelligence, AAAI, USA, vol. 33, pp. 387–394. Association for the Advancement of Artificial Intelligence (2019). https://doi.org/10.1609/aaai.v33i01.3301387
Shang, F.J., Ran, C.F.: An entity recognition model based on deep learning fusion of text feature. Inf. Process. Manag. 59(2), 16–30 (2022)
Yu, F., Koltun, V.: Multi-scale context aggregation by dilated convolutions. In: ICLR (2016). https://doi.org/10.48550/arXiv.1511.07122
Elman, J.L.: Finding structure in time. Cogn. Sci. 14(2), 179–211 (1990)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by joint learning to align and translate. Comput. Sci. (2014). https://doi.org/10.48550/arXiv:1409.0473
Vaswani, A., Shazeer, N., Parmar, N.: Attention is all you need. In: 31st International Conference on Neural Information Processing Systems. Curran Associates Inc., Long-Beach (2017)
He, K., Zhang, X.Y., Ren, S.H., Sun, J.: Deep residual learning for image recognition. In: CVPR, pp. 770–778 (2015)
Lafferty, J.D., Mccalum, A., Pereira, F.C.N.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: 18th International Conference on Machine Learning, pp. 282–289. Morgan Kaufmann Publishers Inc., San Francisco (2001)
Huang, Z.H., Xu, W., Yu, K.: Bidirectional LSTM-CRF models for the sequence tagging. Comput. Sci. (2015). https://doi.org/10.48550/arXiv.1508.01991
Lample, G., Ballesteros, M., Subramanian, S., Kawakami, K.: Neural architectures for named entity recognition. In: Kevin, K., Ani, N. (eds.) Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL, California, vol. 1030, pp. 260–270. Association for Computational Linguistics (2016). https://doi.org/10.18653/v1/N16-1030
Ma, X.Z., Hovy, E.: End-to-end sequence labeling via bi-directional LSTM-CNNs-CRF. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics, Berlin, pp. 1064–1074. Association for Computational Linguistics (2016)
Acknowledgement
The work is supported by National Key Research and Development Program Project “Research on data-driven comprehensive quality accurate service technology for small medium and micro enterprises” (Grant No. 2019YFB1405303).
The Project of Cultivation for Young Top-motch Talents of Beijing Municipal Institutions “Research on the comprehensive quality intelligent service and optimized technology for small medium and micro enterprises” (Grant No. BPHR202203233).
National Natural Science Foundation of China “Research on the influence and governance strategy of online review manipulation with the perspective of E-commerce ecosystem” (Grant No. 72174018).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Liu, X., Chen, J., Zhang, W. (2023). End-to-End Aspect-Based Sentiment Analysis Based on IDCNN-BLSA Feature Fusion. In: Chen, J., Huynh, VN., Tang, X., Wu, J. (eds) Knowledge and Systems Sciences. KSS 2023. Communications in Computer and Information Science, vol 1927. Springer, Singapore. https://doi.org/10.1007/978-981-99-8318-6_4
Download citation
DOI: https://doi.org/10.1007/978-981-99-8318-6_4
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8317-9
Online ISBN: 978-981-99-8318-6
eBook Packages: Computer ScienceComputer Science (R0)