面向细粒度情感分类任务的双通道分类模型
Dual-Channel Classification Model for Fine-Grained Sentiment Classification Task
DOI: 10.12677/SEA.2023.121014, PDF,    国家自然科学基金支持
作者: 汪 伟, 李 想：上海理工大学机器智能研究院，上海；上海理工大学光电信息与计算机工程学院，上海；马致远：上海理工大学机器智能研究院，上海；南京大学计算机软件新技术国家重点实验室，江苏 南京；李清都：上海理工大学机器智能研究院，上海；韩士洋：上海理工大学机器智能研究院，上海；上海理工大学机械工程学院，上海
关键词: 双通道；情感分类；句法信息；情感关键词；Dual Channel； Sentiment Classification； Syntactic Information； Sentiment Keywords
摘要: 句法信息对情感分类任务十分重要，使用GCN来建模这种信息有助于模型关注情感关键词。然而这类模型仅是利用基本语义信息辅助学习句法信息，且单一地从句法依存角度捕获情感关键词，忽略了从语义角度发掘情感关键词。另外，此类模型过于依赖句法信息，没考虑到使用句法提取工具对分类效果造成的负面影响。针对以上问题，提出一种双通道分类模型。该模型利用双通道分类结构减弱对于句法信息的依赖性，同时采用语义情感通道从语义上捕获情感关键词，进而提升模型获取情感信息的能力。在两个常用中文情感分类数据集上的实验表明，该模型的Micro_F值和Macro_F值相较于现有模型均有提升，模型对比和消融实验验证了双通道分类结构在提升模型分类任务性能上的有效性。
Abstract: Syntactic information plays an important role in sentiment classification, using GCN to model the information can help the model learn sentiment keywords. However, such models only use semantic information to assist learning syntactic information, and capture sentiment keywords from the perspective of syntactic dependency, ignoring the semantic perspective. In addition, such models rely on syntactic information and do not consider the negative impact of using syntax extraction tools on classification results. Giving the aforementioned issues, a dual-channel classification model is proposed. The model uses a dual-channel classification to reduce the dependence on syntactic information, and adopts an attention mechanism to capture semantic sentiment words, thereby improving the ability of the model to obtain sentiment information. Experiments on two commonly used Chinese sentiment classification datasets show that both Micro_F and Macro_F are improved compared with existing model. Comparative and ablation experiments illustrate the effectiveness of dual-channel classification structure to improve the model’s classification performance.
文章引用：汪伟, 马致远, 李清都, 李想, 韩士洋. 面向细粒度情感分类任务的双通道分类模型[J]. 软件工程与应用, 2023, 12(1): 134-146. https://doi.org/10.12677/SEA.2023.121014

参考文献

[1] 齐嵩喆, 黄贤英, 朱小飞. 基于权重增强的方面级情感分析模型[J]. 小型微型计算机系统, 2022, 43(4): 747-753.
[2] 李然, 林政, 林海伦, 等. 文本情绪分析综述[J]. 计算机研究与发展, 2018, 55(1): 30-52.
[3] Bhutekar, S.D., Chandak, M.B. and Agrawal, A.J. (2012) Emotion Extraction: Machine Learning for Text-Based Emotion. Proceedings on National Conference on Recent Trends in Computing, Vol. 1, 20-23.
[4] 郑诚, 沈磊, 代宁. 基于类序列规则的中文微博情感分类[J]. 计算机工程, 2016, 42(2): 184-189, 194.
[5] Zhang, L., Wang, S. and Liu, B. (2018) Deep Learning for Sentiment Analysis: A Survey. WIREs Data Mining and Knowledge Discovery, 8, e1253. [Google Scholar] [CrossRef] 
[6] 柴源. 基于Word2vec和SVM的在线图书评论情感识别系统实现[J]. 电子设计工程, 2022, 30(6): 179-183.
[7] 刘鑫, 祁瑞华, 徐琳宏, 等. 融合多级特征的俄语推特文本情感分析[J]. 小型微型计算机系统, 2021, 42(6): 1176-1183.
[8] Ke, P., Ji, H., Liu, S., et al. (2020) SentiLARE: Sentiment-Aware Language Representation Learning with Linguistic Knowledge. Proceedings on Empirical Methods in Natural Language Processing, November 2020, 6975-6988. [Google Scholar] [CrossRef] 
[9] Huang, B.-X. and Kathleen, C. (2019) Syntaxaware Aspect Level Sentiment Classification with Graph Attention Networks. Proceedings on Empirical Methods in Natural Language Processing and the International Joint Conference on Natural Language Processing, Hong Kong, November 2019, 5469-5477. [Google Scholar] [CrossRef] 
[10] Kipf, T.N. and Welling, M. (2017) Semi-Supervised Classification with Graph Convolutional Networks. Proceedings on Learning Representations, Toulon.
[11] Lai, Y., Zhang, L., Han, D., et al. (2020) Fine-Grained Emotion Classification of Chinese Microblogs Based on Graph Convolution Networks. World Wide Web, 23, 2771-2787. [Google Scholar] [CrossRef] 
[12] Shou, Y.-T., Meng, T., Ai, W., et al. (2022) Conversational Emotion Recognition Studies Based on Graph Convolutional Neural Networks and a Dependent Syntactic Analysis. Neurocomputing, 501, 629-639. [Google Scholar] [CrossRef] 
[13] Zhang, J., Chen, C., Liu, P., et al. (2020) Target-Guided Structured Attention Network for Target-Dependent Sentiment Analysis. Proceedings of the Annual Meeting of the Association for Computational Linguistics, Cambridge, 5-10 July 2020, 172-182. [Google Scholar] [CrossRef] 
[14] Letarte, G., Paradis, F., Giguère, P., et al. (2018) Importance of Self-Attention for Sentiment Analysis. Proceedings on Empirical Methods in Natural Language Processing, Brussels, 31 October-4 November 2018, 267-275. [Google Scholar] [CrossRef] 
[15] 张文轩, 殷雁君. 基于依存树增强注意力模型的方面级情感分析[J]. 计算机应用研究, 2022, 39(6): 1656-1662.
[16] Dai, J., Yan, H., Sun, T., et al. (2021) Does Syntax Matter? A Strong Baseline for Aspect-Based Sentiment Analysis with RoBERTa. Proceedings of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Online, June 2021, 1816-1829. [Google Scholar] [CrossRef] 
[17] Dai, A., Hu, X., Nie, J., et al. (2022) Learning from Word Semantics to Sentence Syntax by Graph Convolutional Networks for Aspect-Based Sentiment Analysis. International Journal of Data Science and Analytics, 14, 17-26. [Google Scholar] [CrossRef] 
[18] Che, W., Li, Z. and Liu, T. (2010) LTP: A Chinese Language Technology Platform. Proceedings on Computational Linguistics, Beijing, August 2010, 13-16.
[19] Marcheggiani, D. and Titov, I. (2017) Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling. Proceedings on Empirical Methods in Natural Language Processing, Copenhagen, September 2017, 1506-1515. [Google Scholar] [CrossRef] 
[20] Ji, Y.L. and Dernoncourt, F. (2016) Sequential Short-Text Classification with Recurrent and Convolutional Neural Networks. Proceedings of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, San Diego, June 2016, 515-520.

为你推荐