Yan Xiang
Skip Abstract Section
Abstract
Opinion target classification of microblog comments is one of the most important tasks for public opinion analysis about an event. Due to the high cost of manual labeling, opinion target classification is generally considered as a weak-supervised task. This article attempts to address the opinion target classification of microblog comments through an event graph convolution network (EventGCN) in a weak-supervised manner. Specifically, we take microblog contents and comments as document nodes, and construct an event graph with three typical relationships of event microblogs, including the co-occurrence relationship of event keywords extracted from microblogs, the reply relationship of comments, and the document similarity. Finally, under the supervision of a small number of labels, both word features and comment features can be represented well to complete the classification. The experimental results on two event microblog datasets show that EventGCN can significantly improve the classification performance compared with other baseline models.
- [1] . 2012. Baselines and bigrams: Simple, good sentiment and topic classification. In Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 90–94. https://www.aclweb.org/anthology/P12-2018/.Google Scholar
Digital Library
- [2] . 2003. Latent Dirichlet allocation. Journal of Machine Learning Research 3 (2003), 993–1022. http://jmlr.org/papers/v3/blei03a.html.Google ScholarDigital Library
- [3] . 2008. BNS feature scaling: An improved representation over TF-IDF for SVM text classification. In Proceedings of the 17th ACM Conference on Information and Knowledge Management (CIKM’08).
ACM ,New York, NY , 263–270.DOI: DOI: http://dx.doi.org/10.1145/1458082.1458119Google ScholarDigital Library - [4] . 2010. Recurrent neural network based language model. In Proceedings of the 11th Annual Conference of the International Speech Communication Association (INTERSPEECH’10). 1045–1048. http://www.isca-speech.org/archive/interspeech_2010/i10_1045.html.Google ScholarCross Ref
- [5] . 2016. Recurrent neural network for text classification with multi-task learning. In Proceedings of the 25th International Joint Conference on Artificial Intelligence (IJCAI’16). 2873–2879. http://www.ijcai.org/Abstract/16/408.Google Scholar
- [6] . 2014. Convolutional neural networks for sentence classification. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP’14). 1746–1751.
DOI: DOI: http://dx.doi.org/10.3115/v1/d14-1181Google ScholarCross Ref - [7] . 2020. Chinese short text classification with mutual-attention convolutional neural networks. ACM Transactions on Asian and Low-Resource Language Information Processing 19, 5 (2020), Article 61, 13 pages. https://dl.acm.org/doi/10.1145/3388970.Google ScholarDigital Library
- [8] . 2018. Deep contextualized word representations. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT’18) (Volume 1: Long Papers). 2227–2237.
DOI: DOI: http://dx.doi.org/10.18653/v1/n18-1202Google ScholarCross Ref - [9] . 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies (NAACL-HLT’19) (Volume 1: Long and Short Papers). 4171–4186.
DOI: DOI: http://dx.doi.org/10.18653/v1/n19-1423Google Scholar - [10] . 2017. An unsupervised neural attention model for aspect extraction. In Proceedings of the 55th Annual Meeting ofthe Association for Computational Linguistics (ACL’17) (Volume 1: Long Papers). 388–397.
DOI: DOI: http://dx.doi.org/10.18653/v1/P17-1036Google Scholar - [11] . 2018. Summarizing opinions: Aspect extraction meets sentiment prediction and they are both weakly supervised. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.3675–3686.
DOI: DOI: http://dx.doi.org/10.18653/v1/d18-1403Google ScholarCross Ref - [12] . 2018. Variational sequential labelers for semi-supervised learning. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. 215–226.
DOI: DOI: http://dx.doi.org/10.18653/v1/d18-1020Google ScholarCross Ref - [13] . 2019. Variational pretraining for semi-supervised text classification. In Proceedings of the 57th Conference of the Association for Computational Linguistics (ACL’19) (Volume 1: Long Papers). 5880–5894.
DOI: DOI: http://dx.doi.org/10.18653/v1/p19-1590Google ScholarCross Ref - [14] . 2016. Convolutional neural networks on graphs with fast localized spectral filtering. In Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems. 3837–3845. https://proceedings.neurips.cc/paper/2016/hash/04df4d434d481c5bb723be1b6df1ee65-Abstract.html.Google Scholar
- [15] . 2017. Semi-supervised classification with graph convolutional networks. In Proceedings of the 5th International Conference on Learning Representations (ICLR’17). https://openreview.net/forum?id=SJU4ayYgl.Google Scholar
- [16] . 2019. Graph convolutional networks for text classification. In Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI’19). 7370–7377.
DOI: DOI: http://dx.doi.org/10.1609/aaai.v33i01.33017370Google Scholar - [17] . 2019. Session-based recommendation with graph neural networks. In Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI’19). 346–353.
DOI: DOI: http://dx.doi.org/10.1609/aaai.v33i01.3301346Google ScholarDigital Library - [18] . 2020. Every document owns its structure: Inductive text classification via graph neural networks. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL’20). 334–339.
DOI: DOI: http://dx.doi.org/10.18653/v1/2020.acl-main.31Google ScholarCross Ref - [19] . 2019. Text level graph neural network for text classification. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP’19). 3442–3448.
DOI: DOI: http://dx.doi.org/10.18653/v1/D19-1345Google ScholarCross Ref - [20] . 2018. Graph attention networks. In Proceedings of the 6th International Conference on Learning Representations (ICLR’18). https://openreview.net/forum?id=rJXMpikCZ.Google Scholar
- [21] . 2019. Heterogeneous graph attention networks for semi-supervised short text classification. In Proceedings ofthe 2019 Conference on Empirical Methods in Natural Language Processing and the 9thInternational Joint Conference on Natural Language Processing (EMNLP-IJCNLP’19). 4820–4829.
DOI: DOI: http://dx.doi.org/10.18653/v1/D19-1488Google Scholar - [22] . 2004. TextRank: Bringing order into text. In Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing (EMNLP’04). 404–411. https://www.aclweb.org/anthology/W04-3252/.Google Scholar
- [23] . 2011. LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology 2, 3 (2011), Article 27, 27 pages.
DOI: DOI: http://dx.doi.org/10.1145/1961189.1961199Google ScholarDigital Library - [24] . 2013. Hybrid speech recognition with deep bidirectional LSTM. In Proceedings of the 2013 IEEE Workshop on Automatic Speech Recognition and Understanding.
IEEE ,Los Alamitos, CA , 273–278.DOI: DOI: http://dx.doi.org/10.1109/ASRU.2013.6707742Google ScholarCross Ref - [25] . 2017. Bag of tricks for efficient text classification. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (EACL’17) (Volume 2: Short Papers). 427–431.
DOI: DOI: http://dx.doi.org/10.18653/v1/e17-2068Google ScholarCross Ref
Index Terms
- Event Graph Neural Network for Opinion Target Classification of Microblog Comments
Recommendations
A Structure for Opinion in Social Domains
SOCIALCOM '13: Proceedings of the 2013 International Conference on Social ComputingOpinion mining, as a sub-field of text mining, analyzes opinions expressed regarding an object, a topic, or an issue. An opinion is expressed by a person using some opinion terms or phrases regarding a target. Statistical studies show that the affective ...
Content and opinion-enhanced neural model for opinion sentence classification of Chinese microblog comments
Opinion sentence classification of Chinese microblog comments aims to recognise those comments with opinions about the specific microblog content, which is the basis of internet public opinion analysis and opinion mining. However, existing opinion ...
Joint Extraction of Opinion Targets and Opinion Expressions Based on Cascaded Model
PRICAI 2019: Trends in Artificial IntelligenceAbstractFine-grained opinion analysis is a very important task, especially identifying opinion target and opinion expression. In this paper, a new neural architecture is proposed for the sentence-level joint extraction of opinion target and opinion ...
Comments