Abstract
With the rapid development of contemporary e-commerce and social media, the need of better understanding and exploring users’ evaluations on e-commercial products is becoming urgent and crucial, which results in the emergence of a new research hot-spot aiming at analysing and mining latent features of customer reviews on e-commercial products. In order to analyse the associations among semantic features with different lengths in e-commercial reviews, a text sentiment analysis method, named as ALBERT-SACR, is proposed based on self-adaptive context reasoning mechanism in this paper. Firstly, the global contextual features are extracted using the Transformer blocks of ALBERT. Then, semantic features with different lengths are extracted on the basis of multi-channel CNN combined with self-attention mechanism to perform context reasoning and adaptive adjustment of relational weights. Finally, a fully connected neural network is used for sentiment classification. public Chinese datasets Waimai and Shopping, where the performance of our method is qualitatively compared with five other methods. Simulation results verify both the effectiveness and efficiency of our proposed ALBERT-SACR, and the adaptive nature of our proposed SACR is effective in contextual inference for semantic features of different lengths.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Awwalu, J., Bakar, A.A., Yaakub, M.R.: Hybrid N-gram model using Naïve Bayes for classification of political sentiments on Twitter. Neural Comput. Appl. 31(12), 9207–9220 (2019). https://doi.org/10.1007/s00521-019-04248-z
Balakrishnan, V., Khan, S., Arabnia, H.: Improving cyberbullying detection using twitter users’ psychological features and machine learning. Comput. Secur. 90, 101710 (2020). https://doi.org/10.1016/j.cose.2019.101710
Chen, H., et al.: Country image in covid-19 pandemic: a case study of china. IEEE Trans. Big Data 1 (2020). https://doi.org/10.1109/TBDATA.2020.3023459
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding, pp. 4171–4186. Association for Computational Linguistics (2019). https://doi.org/10.18653/v1/N19-1423
Ding, Z., Qi, Y., Lin, D.: Alberta-based sentiment analysis of movie review. In: 2021 4th International Conference on Advanced Electronic Materials, Computers and Software Engineering (AEMCSE), pp. 1243–1246 (2021). https://doi.org/10.1109/AEMCSE51986.2021.00254
Guo, B., Zhang, C.X., Liu, J., Ma, X.: Improving text classification with weighted word embeddings via a multi-channel textcnn model. Neurocomputing 363 (2019). https://doi.org/10.1016/j.neucom.2019.07.052
Kim, Y.: Convolutional neural networks for sentence classification. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (2014). https://doi.org/10.3115/v1/D14-1181
Lan, Z., Chen, M., Goodman, S., Gimpel, K., Sharma, P., Soricut, R.: Albert: a lite bert for self-supervised learning of language representations. ArXiv:abs/1909.11942 (2020)
Li, M., Chen, L., Zhao, J., Li, Q.: Sentiment analysis of Chinese stock reviews based on BERT model. Appl. Intell. 51(7), 5016–5024 (2021). https://doi.org/10.1007/s10489-020-02101-8
Li, Z., He, L., Guo, W., Jin, Z.: Research on sentiment analysis method based on weibo comments. East Asian Math. J. 37(5), 599–612 (2021)
Liu, W., Pang, J., Li, N., Zhou, X., Yue, F.: Research on Multi-label Text Classification Method Based on tALBERT-CNN. Int. J. Comput. Intell. Syst. 14(1), 1–12 (2021). https://doi.org/10.1007/s44196-021-00055-4
Lv, Y., et al.: Aspect-level sentiment analysis using context and aspect memory network. Neurocomputing 428 (2020). https://doi.org/10.1016/j.neucom.2020.11.049
Radford, A., Narasimhan, K.: Improving language understanding by generative pre-training (2018)
Vaswani, A., et al.: Attention is all you need, pp. 6000–6010 (2017)
Wang, Y., Yu, H., Wang, G., Xie, Y.: Cross-domain recommendation based on sentiment analysis and latent feature mapping. Entropy 22, 473 (2020). https://doi.org/10.3390/e22040473
Wei, J., Liao, J., Yang, Z., Wang, S., Zhao, Q.: Bilstm with multi-polarity orthogonal attention for implicit sentiment analysis. Neurocomputing 383 (2019). https://doi.org/10.1016/j.neucom.2019.11.054
Wu, Y., He, J.: Sentiment analysis of barrage text based on albert-att-bilstm model, pp. 152–156 (2021). https://doi.org/10.1109/PRAI53619.2021.9551040
Wu, Z., Ong, D.: Context-guided bert for targeted aspect-based sentiment analysis (2020)
Ye, X., Xu, Y., Luo, M.: Albertc-CNN based aspect level sentiment analysis. IEEE Access 1 (2021). https://doi.org/10.1109/ACCESS.2021.3094026
Yin, Z., Kou, Y., Wang, G., Shen, D., Nie, T.: Explainable recommendation via neural rating regression and fine-grained sentiment perception. In: Xing, C., Fu, X., Zhang, Y., Zhang, G., Borjigin, C. (eds.) WISA 2021. LNCS, vol. 12999, pp. 580–591. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87571-8_50
Zhang, M., Wang, S., Yuan, K.: Sentiment Analysis of Barrage Text Based on ALBERT and Multi-channel Capsule Network, pp. 718–726 (2022). https://doi.org/10.1007/978-3-030-89698-0_74
Acknowledgement
This work was supported by CCF Opening Project of Information System (CCFIS2021-03-01) and the Natural Science Project of Education Department of Shaanxi Province (No.21JK0646).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Hou, S., Zhao, X., Liu, N., Shi, X., Wang, Y., Zhang, G. (2022). Self-adaptive Context Reasoning Mechanism for Text Sentiment Analysis. In: Zhao, X., Yang, S., Wang, X., Li, J. (eds) Web Information Systems and Applications. WISA 2022. Lecture Notes in Computer Science, vol 13579. Springer, Cham. https://doi.org/10.1007/978-3-031-20309-1_17
Download citation
DOI: https://doi.org/10.1007/978-3-031-20309-1_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20308-4
Online ISBN: 978-3-031-20309-1
eBook Packages: Computer ScienceComputer Science (R0)