Abstract
Sentiment analysis of literary book reviews is crucial for authors to understand the voice of readers and for humanities researchers to investigate the reader reception of the literary book. Constructing an automated sentiment analysis system can help us analyze literary reviews in a big-data way, achieving a complete view of the full understanding. The main challenge in developing such a system is the lack of large-scale datasets with precise annotations. Some related researches collect the star rates from social networks and convert them into corresponding sentiment annotations for data labeling. Such automatically generated annotations can greatly reduce the human labeling efforts but with two defects. The first is that such annotations are filling with a vast amount of noise. For example, different people have significantly different perceptions for sentiment markers (positive, neutral, and negative) of a five-star comment system. Besides, literary book reviews contain more positive emotions than neutral and negative. Namely, this task is also challenged by imbalanced data. This paper introduces an automatically generated sentiment analysis dataset for Chinese literary book reviews with parts of manual verification, containing 187 literary books with 109,286 reviews. Furthermore, we propose a novel meta-learning approach with Looking Back mechanism to build a robust BERT-based sentiment classification model. Specifically, we design an extra meta-model for learning a sample weighting function from the historical sample information, which mitigates the influence of noisy labels and class imbalance problems. The parameters of this meta-model are finely updated with the whole training process by the guidance of a small amount of unbiased meta data. The results show the F1 score raise of 13.51% with the Looking Back mechanism, showing that our method can significantly promote sentiment analysis performance with noisy labels and class imbalance data.
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
Boyd, R.L.: Psychological text analysis in the digital humanities. In: Hai-Jew, S. (ed.) Data Analytics in Digital Humanities. MSA, pp. 161–189. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-54499-1_7
Clanuwat, T., Bober-Irizar, M., Kitamoto, A., Lamb, A., Yamamoto, K., Ha, D.: Deep learning for classical japanese literature. arXiv preprint arXiv:1812.01718 (2018)
Moreno-Ortiz, A.: Lingmotif: sentiment analysis for the digital humanities. In: Proceedings of the Software Demonstrations of the 15th Conference of the European Chapter of the Association for Computational Linguistics, pp. 73–76 (2017)
Cao, Y., Xu, R., Chen, T.: Combining convolutional neural network and support vector machine for sentiment classification. In: Zhang, X., Sun, M., Wang, Z., Huang, X. (eds.) CNCSMP 2015. CCIS, vol. 568, pp. 144–155. Springer, Singapore (2015). https://doi.org/10.1007/978-981-10-0080-5_13
Fang, X., Zhan, J.: Sentiment analysis using product review data. J. Big Data 2(1), 1–14 (2015)
Lak, P., Turetken, O.: Star ratings versus sentiment analysis - a comparison of explicit and implicit measures of opinions. In: 2014 47th Hawaii International Conference on System Sciences, pp. 796–805 (2014). https://doi.org/10.1109/HICSS.2014.106
Haque, T.U., Saber, N.N., Shah, F.M.: Sentiment analysis on large scale amazon product reviews. In: 2018 IEEE International Conference on Innovative Research and Development (ICIRD), pp. 1–6 (2018). https://doi.org/10.1109/ICIRD.2018.8376299
Liu, H., Wang, J., Li, S., Li, J., Zhou, G.: Semi-supervised sentiment classification based on auxiliary task learning. In: Zhang, M., Ng, V., Zhao, D., Li, S., Zan, H. (eds.) NLPCC 2018. LNCS (LNAI), vol. 11109, pp. 372–382. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-99501-4_33
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)
Shu, J., et al.: Meta-weight-net: Learning an explicit mapping for sample weighting. In: Wallach, H., Larochelle, H., Beygelzimer, A., d’ Alché-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 32. Curran Associates, Inc. (2019)
Turney, P.D.: Thumbs up or thumbs down? semantic orientation applied to unsupervised classification of reviews. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics (2002)
Pang, B., Lee, L.: A sentimental education: Sentiment analysis using subjectivity summarization based on minimum cuts. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL-04), pp. 271–278 (2004)
Hu, M., Liu, B.: Mining and summarizing customer reviews. In: Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 168–177 (2004)
Kim, S.M., Hovy, E.: Determining the sentiment of opinions. In: COLING 2004: Proceedings of the 20th International Conference on Computational Linguistics, pp. 1367–1373 (2004)
Wilson, T., Wiebe, J., Hoffmann, P.: Recognizing contextual polarity in phrase-level sentiment analysis. In: Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, pp. 347–354 (2005)
Agarwal, A., Biadsy, F., Mckeown, K.: Contextual phrase-level polarity analysis using lexical affect scoring and syntactic n-grams. In: Proceedings of the 12th Conference of the European Chapter of the ACL (EACL 2009), pp. 24–32 (2009)
Barbosa, L., Feng, J.: Robust sentiment detection on twitter from biased and noisy data. In: Coling 2010: Posters, pp. 36–44 (2010)
Yang, L., Li, Y., Wang, J., Sherratt, R.S.: Sentiment analysis for e-commerce product reviews in Chinese based on sentiment lexicon and deep learning. IEEE Access 8, 23522–23530 (2020)
Goldberger, J., Ben-Reuven, E.: Training deep neural-networks using a noise adaptation layer. In: ICLR (2017)
Vahdat, A.: Toward robustness against label noise in training deep discriminative neural networks (2017)
Hendrycks, D., Mazeika, M., Wilson, D., Gimpel, K.: Using trusted data to train deep networks on labels corrupted by severe noise (2018)
Sun, Y., Kamel, M.S., Wong, A.K., Wang, Y.: Cost-sensitive boosting for classification of imbalanced data. Pattern Recogn. 40(12), 3358–3378 (2007)
Lin, T.Y., Goyal, P., Girshick, R., He, K., Dollár, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980–2988 (2017)
Malisiewicz, T., Gupta, A., Efros, A.A.: Ensemble of exemplar-svms for object detection and beyond. In: 2011 International Conference on Computer Vision, pp. 89–96. IEEE (2011)
Kumar, M.P., Packer, B., Koller, D.: Self-paced learning for latent variable models. In: NIPS, vol. 1, p. 2 (2010)
De La Torre, F., Black, M.J.: A framework for robust subspace learning. Int. J. Comput. Vis. 54(1), 117–142 (2003)
Qiu, X., Sun, T., Xu, Y., Shao, Y., Dai, N., Huang, X.: Pre-trained models for natural language processing: A survey. Sci. China Technol. Sci. 1–26 (2020)
Gao, Z., Feng, A., Song, X., Wu, X.: Target-dependent sentiment classification with bert. IEEE Access 7, 154290–154299 (2019)
Socher, R., et al.: Recursive deep models for semantic compositionality over a sentiment treebank. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pp. 1631–1642 (2013)
Shivaprasad, T., Shetty, J.: Sentiment analysis of product reviews: a review. In: 2017 International Conference on Inventive Communication and Computational Technologies (ICICCT), pp. 298–301. IEEE (2017)
Zhang, S., Wei, Z., Wang, Y., Liao, T.: Sentiment analysis of Chinese micro-blog text based on extended sentiment dictionary. Future Gener. Comput. Syst. 81, 395–403 (2018)
Acknowledgements
This work has been supported by the National Social Science Fund of China Project (19BZW024).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Bao, H. et al. (2021). BERT-Based Meta-Learning Approach with Looking Back for Sentiment Analysis of Literary Book Reviews. In: Wang, L., Feng, Y., Hong, Y., He, R. (eds) Natural Language Processing and Chinese Computing. NLPCC 2021. Lecture Notes in Computer Science(), vol 13029. Springer, Cham. https://doi.org/10.1007/978-3-030-88483-3_18
Download citation
DOI: https://doi.org/10.1007/978-3-030-88483-3_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-88482-6
Online ISBN: 978-3-030-88483-3
eBook Packages: Computer ScienceComputer Science (R0)
