融合动态语义及静态结构特征的方面级情感分析

doi:10.3778/j.issn.1002-8331.2403-0338

摘要/Abstract

摘要： 方面级情感分析作为细粒度情感分析任务，其目标是判断给定句子中特定方面的情感极性。目前这项任务面临的主要挑战是能否准确地建模方面词与观点词之间的关系。为了解决这个问题，从获取句子的动态语义特征和静态结构特征两方面出发，对方面词与观点词之间的关系进行建模。该模型通过引入动态调整权重适配器，在结合上下文的基础上获取方面感知动态语义特征，同时按照短语-分句结构的句法层次与图注意力网络结合，从而利用更全面的句法信息来获取方面感知静态结构特征，通过融合动态语义特征和静态结构特征实现更准确的方面级情感极性预测。实验结果表明，该模型在Rest14、Laptop14、Twitter这3个公开数据集上，准确率和Macro-F1值相比于基线模型均有所提升，具有较好的方面级情感分析性能。

关键词: 方面级情感分析, 动态语义, 静态结构, 图注意力网络

Abstract: Aspect-based sentiment analysis, as a fine-grained sentiment analysis task, aims to determine the sentiment polarity of specific aspects in a given sentence. The primary challenge in this task is accurately modeling the relationship between aspect words and opinion words. To address this issue, this study focuses on obtaining dynamic semantic features and static structural features of sentences to model the relationship between aspect words and opinion words. Firstly, the model introduces a dynamic adjustment weight adapter to obtain aspect-aware dynamic semantic features by incorporating contextual information. Simultaneously, it utilizes a phrase-sub-sentence structure at the syntactic level and combines it with graph attention networks to leverage more comprehensive syntactic information for obtaining aspect-aware static structural features. Finally, by integrating dynamic semantic features and static structural features, the model achieves more accurate aspect-level sentiment polarity predictions. Experimental results indicate that the proposed model demonstrates improved accuracy and Macro-F1 scores compared to baseline models on three public datasets: Rest14, Laptop14, and Twitter. It exhibits strong performance in aspect-level sentiment analysis.

Key words: aspect-based sentiment analysis, dynamic semantics, static structure, graph attention network

尹文晓, 周建设, 马登豪, 吕学强. 融合动态语义及静态结构特征的方面级情感分析[J]. 计算机工程与应用, 2025, 61(12): 177-186.

YIN Wenxiao, ZHOU Jianshe, MA Denghao, LYU Xueqiang. Research on Aspect?Based Sentiment Analysis by Combining Dynamic Semantic and Static Structural Features[J]. Computer Engineering and Applications, 2025, 61(12): 177-186.

参考文献

[1] CHAUHAN G S, NAHTA R, MEENA Y K, et al. Aspect based sentiment analysis using deep learning approaches: a survey[J]. Computer Science Review, 2023, 49: 100576.
[2] BENSOLTANE R, ZAKI T. Aspect-based sentiment analysis: an overview in the use of Arabic language[J]. Artificial Intelligence Review, 2023, 56(3): 2325-2363.
[3] 徐学锋, 韩虎. 面向方面级情感分析的多视图表示模型[J]. 计算机工程与应用, 2024, 60(5): 112-121.
XU X F, HAN H. Multi-view representation model for aspect-level sentiment analysis[J]. Computer Engineering and Applications, 2024, 60(5): 112-121.
[4] XU H, SHU L, YU P, et al. Understanding pre-trained BERT for aspect-based sentiment analysis[C]//Proceedings of the 28th International Conference on Computational Linguistics. International Committee on Computational Linguistics, 2020: 244-250.
[5] ZHANG Z, ZHOU Z L, WANG Y N. SSEGCN: syntactic and semantic enhanced graph convolutional network for aspect-based sentiment analysis[C]//Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg: ACL, 2022: 4916-4925.
[6] AHMED K, NADEEM M I, ZHENG Z Y, et al. Breaking down linguistic complexities: a structured approach to aspect-based sentiment analysis[J]. Journal of King Saud University-Computer and Information Sciences, 2023, 35(8): 101651.
[7] WANG X, ZHU M, BO D, et al. AM-GCN: adaptive multi-channel graph convolutional networks[C]//Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2020: 1243-1253.
[8] XU G T, LIU P Y, ZHU Z F, et al. Attention-enhanced graph convolutional networks for aspect-based sentiment classification with multi-head attention[J]. Applied Sciences, 2021, 11(8): 3640.
[9] ZHAO M, YANG J, ZHANG J P, et al. Aggregated graph convolutional networks for aspect-based sentiment classification[J]. Information Sciences, 2022, 600: 73-93.
[10] ZARANDI A K, MIRZAEI S. A survey of aspect-based sentiment analysis classification with a focus on graph neural network methods[J]. Multimedia Tools and Applications, 2024, 83(19): 56619-56695.
[11] WANG Y Q, HUANG M L, ZHU X Y, et al. Attention-based LSTM for aspect-level sentiment classification[C]//Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: ACL, 2016: 606-615.
[12] MA D H, LI S J, ZHANG X D, et al. Interactive attention networks for aspect-level sentiment classification[C]//Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, 2017: 4068-4074.
[13] ZHANG K, LIU Q, QIAN H, et al. EATN: an efficient adaptive transfer network for aspect-level sentiment analysis[J]. IEEE Transactions on Knowledge and Data Engineering, 2023, 35(1): 377-389.
[14] ZHANG Kai, ZHANG Kun, ZHANG M D, et al. Incorporating dynamic semantics into pre-trained language model for aspect-based sentiment analysis[C]//Findings of the Association for Computational Linguistics: ACL 2022. Stroudsburg: ACL, 2022: 3599-3610.
[15] SHI X F, HU M, REN F J, et al. Prompted and integrated textual information enhancing aspect-based sentiment analysis[J]. Journal of Intelligent Information Systems, 2024, 62(1): 91-115.
[16] DU K, XING F, CAMBRIA E. Incorporating multiple knowledge sources for targeted aspect-based financial sentiment analysis[J]. ACM Transactions on Management Information Systems, 2023, 14(3): 1-24.
[17] ZHAO X S, PENG H, DAI Q, et al. RDGCN: reinforced dependency graph convolutional network for aspect-based sentiment analysis[J]. arXiv:2311.04467, 2023.
[18] 韩虎, 范雅婷, 徐学锋. 面向方面情感分析的多通道增强图卷积网络[J]. 电子与信息学报, 2024, 46(3): 1022-1032.
HAN H, FAN Y T, XU X F. Multi-channel enhanced graph convolutional network for aspect-based sentiment analysis[J]. Journal of Electronics & Information Technology, 2024, 46(3): 1022-1032.
[19] WANG K, SHEN W Z, YANG Y Y, et al. Relational graph attention network for aspect-based sentiment analysis[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg: ACL, 2020: 3229-3238.
[20] 刘漳辉, 杨耀东, 陈羽中. 一种用于方面级情感分析的关系注意力图卷积网络[J]. 小型微型计算机系统, 2023, 44(4): 752-758.
LIU Z H, YANG Y D, CHEN Y Z. Relational attention based graph convolutional network for aspect-level sentiment analysis[J]. Journal of Chinese Computer Systems, 2023, 44(4): 752-758.
[21] LIANG S, WEI W, MAO X L, et al. BiSyn-GAT+: bi-syntax aware graph attention network for aspect-based sentiment analysis[C]//Findings of the Association for Computational Linguistics: ACL 2022. Stroudsburg: ACL, 2022: 1835-1848.
[22] HAZARIKA D, PORIA S, VIJ P, et al. Modeling inter-aspect dependencies for aspect-based sentiment analysis[C]//Proceedings of the 2018 Conference of the North American Chapter Ofthe Association for Computational Linguistics: Human Language Technologies, Volume 2. Stroudsburg: ACL, 2018: 266-270.
[23] HU M T, ZHAO S W, ZHANG L, et al. CAN: constrained attention networks for multi-aspect sentiment analysis[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Stroudsburg: ACL, 2019: 4600-4609.
[24] LIANG B, YIN R D, GUI L, et al. Jointly learning aspect-focused and inter-aspect relations with graph convolutional networks for aspect sentiment analysis[C]//Proceedings of the 28th International Conference on Computational Linguistics, 2020: 150-161.
[25] ZHAO P L, HOU L L, WU O. Modeling sentiment dependencies with graph convolutional networks for aspect-level sentiment classification[J]. Knowledge-Based Systems, 2020, 193: 105443.
[26] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Advances in Neural Information Processing Systems, 2017: 5998-6008.
[27] SEN C S, HARTVIGSEN T, YIN B, et al. Human attention maps for text classification: do humans and neural networks focus on the same words? [C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg: ACL, 2020: 4596-4608.
[28] BAI X F, LIU P B, ZHANG Y. Investigating typed syntactic dependencies for targeted sentiment classification using graph attention neural network[J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2020, 29: 503-514.
[29] PONTIKI M, GALANIS D, PAVLOPOULOS J, et al. SemEval-2014 task 4: aspect based sentiment analysis[C]//Proceedings of the 8th International Workshop on Semantic Evaluation. Stroudsburg: ACL, 2014: 27-35.
[30] DONG L, WEI F R, TAN C Q, et al. Adaptive recursive neural network for target-dependent twitter sentiment classification[C]//Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics. Stroudsburg: ACL, 2014: 49-54.
[31] ZHANG Y, ZHOU H Q, LI Z H. Fast and accurate neural CRF constituency parsing[C]//Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, 2020: 4046-4053.
[32] DOZAT T, MANNING C D. Deep biaffine attention for neural dependency parsing[C]//Proceedings of the 5th International Conference on Learning Representations, 2017: 24-26.
[33] FAN F F, FENG Y S, ZHAO D Y. Multi-grained attention network for aspect-level sentiment classification[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Stroudsburg: ACL, 2018: 3433-3442.
[34] 孙天伟, 杨长春, 顾晓清, 等. 结合共现网络的方面级情感分析研究[J]. 计算机工程与应用, 2023, 59(20): 111-118.
SUN T W, YANG C C, GU X Q, et al. Research on aspect-level sentiment analysis combined with co-existing networks[J]. Computer Engineering and Applications, 2023, 59(20): 111-118.
[35] SHUVO M M H, ISLAM S K, CHENG J L, et al. Efficient acceleration of deep learning inference on resource-constrained edge devices: a review[J]. Proceedings of the IEEE, 2023, 111(1): 42-91.
[36] 郭小宇, 马静, 陈杰. 多模态分级特征映射与融合表征方法研究[J]. 计算机工程与应用, 2025, 61(6): 171-182.
GUO X Y, MA J, CHEN J. Research on multimodal hierarchical feature mapping and fusion representation method[J]. Computer Engineering and Applications, 2025, 61(6): 171-182.