Abstract
Aspect-based sentiment analysis (ABSA) is one of the most challenging problems in opinion mining especially for the language with a complex structure like Vietnamese. Many studies tackle this problem by separating it into two subtasks: opinion target extraction and sentiment polarity detection. These subtasks generally addressed by rule-based approaches or conventional machine learning approaches with hand-designed features. By contrast, we propose a sequence-labeling scheme associated with bidirectional recurrent neural networks (BRNN) and conditional random field (CRF) to extract opinion target and detect its sentiment simultaneously. Furthermore, we collect and construct a Vietnamese ABSA dataset specifically for smartphone domain. Experiments on this dataset show that BRNN-CRF architecture achieves a satisfied performance, outperforms CRF with hand-designed features. In addition, our framework requires no feature engineering efforts as well as linguistic resources, allows us to adapt to other languages easily.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Hu, M., Liu, B.: Mining and summarizing customer reviews. In: Proceedings of SIGKDD 2004, pp. 168–177. ACM, New York (2004)
Qiu, G., Liu, B., Bu, J., Chen, C.: Opinion word expansion and target extraction through double propagation. Comput. Linguist. 37(1), 9–27 (2011)
Irsoy, O., Cardie, C.: Opinion mining with deep recurrent neural networks. In: Proceedings of EMNLP, pp. 720–728. ACL, Doha (2014)
Liu, P., Joty, S., Meng, H.: Fine-grained opinion mining with recurrent neural networks and word embeddings. In: Proceedings of EMNLP, pp. 1433–1443. ACL, Lisbon (2015)
Socher, R., Perelygin, A., Wu, J., Chuang, J., Manning, C., Ng, A., Potts, C.: Recursive deep models for semantic compositionality over a sentiment treebank. In: Proceedings of EMNLP, pp. 1631–1642. Citeseer, Seattle (2013)
Hamdan, H., Bellot, P., Bechet, F.: Lsislif: CRF and logistic regression for opinion target extraction and sentiment polarity analysis. In: Proceedings of SemEval-2015, pp. 753–758. ACL, Denver (2015)
Brody, S., Elhadad, N.: An unsupervised aspect-sentiment model for online reviews. In: Proceedings of NAACL HLT, pp. 804–812. ACL, Los Angeles (2010)
Lu, B., Ott, M., Cardie, C., Tsou, B.: Multi-aspect sentiment analysis with topic models. In: Proceedings of ICDM Workshops, pp. 81–88. Washington (2011)
Lin, C., He, Y., Everson, R., Ruger, S.: Weakly supervised joint sentiment topic detection from text. IEEE TKDE 24(6), 1134–1145 (2012)
Huang, Z., Xu, W., Yu, K.: Bidirectional LSTM-CRF models for sequencetagging. arXiv arXiv:1508.01991 (2015)
Elman, 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)
Cho, K., Merrienboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: encoder-decoder approaches. arXiv arXiv:1409.1259 (2014)
Pham, T., Le, P.: End-to-end recurrent neural network models for vietnamese named entity recognition: word-level vs. character-level. arXiv arXiv:1705.04044 (2017)
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Proceedings of NIPS, pp. 3111–3119. Nevada (2013)
VnTokenizer toolkit. http://mim.hus.vnu.edu.vn/phuonglh/softwares/vnTokenizer
Brat rapid annotation tool. http://brat.nlplab.org/
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Mai, L., Le, B. (2018). Aspect-Based Sentiment Analysis of Vietnamese Texts with Deep Learning. In: Nguyen, N., Hoang, D., Hong, TP., Pham, H., Trawiński, B. (eds) Intelligent Information and Database Systems. ACIIDS 2018. Lecture Notes in Computer Science(), vol 10751. Springer, Cham. https://doi.org/10.1007/978-3-319-75417-8_14
Download citation
DOI: https://doi.org/10.1007/978-3-319-75417-8_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-75416-1
Online ISBN: 978-3-319-75417-8
eBook Packages: Computer ScienceComputer Science (R0)