基于层级知识增强和义原知识的中文隐式情感分析

Chinese Implicit Sentiment Analysis Based on Hierarchical Knowledge Enhancement and Sememe Knowledge

摘要

针对隐式情感分析中缺乏明显情感线索、存在混合情感特征、多义性特征以及语境依赖特征等问题,提出一种基于层级知识增强和义原知识的中文隐式情感分析方法,先引入基于转换器的双向编码器表示技术的情感预训练模型以增强情感线索识别能力,然后通过字符级信息获取、区域移动框学习、全局信息学习及多池化操作处理混合情感特征.同时,结合义原知识和密度矩阵,利用HowNet知识库缓解多义性问题,并与双向长短期记忆网络特征融合以应对语境依赖特征.实验结果表明,该方法在有效性、优越性和泛化性方面均表现优异,为中文隐式情感分析提供了可借鉴的技术路径,有助于提升社交媒体、用户评论等场景下的情感理解与决策支持能力.

Abstract

Aiming at the problems that there were the lack of explicit sentiment clues, mixed sentiment features, polysemy features and context dependence features in implicit sentiment analysis, we proposed a Chinese implicit sentiment analysis method based on hierarchical knowledge enhancement and sememe knowledge. We first introduced a sentiment pre-training model based on bidirectional encoder representation technology of converters to enhance the ability of sentiment clue recognition. Then we handled mixed sentiment features through character-level information acquisition, region moving box learning, global information learning, and multi-pooling operations. At the same time, we combined sememe knowledge and density matrix, utilized the HowNet knowledge base to allevite polysemy issues, and integrated with bidirectional long short-term memory network features to tackle context dependence features. Experimental results show that the proposed method performs excellently in terms of effectiveness, superiority, and generalizability, providing a valuable technical path for Chinese implicit sentiment analysis and helping to improve sentiment understanding and decision-making support capabilities in scenarios such as social media and user reviews.

关键词

隐式情感分析 / 外部知识 / 知识增强 / SentiBERT模型 / 层级知识 / 义原知识

Key words

implicit sentiment analysis / external knowledge / knowledge enhancement / SentiBERT model / hierarchical knowledge / sememe knowledge

参考文献

[1] LIU B. Sentiment Analysis and Opinion Mining[M]. Berlin: Springer Nature, 2022: 1-167.

[2] WANG H B, HOU M H, LI F, et al. Chinese Implicit Sentiment Analysis Based on Hierarchical Knowledge Enhancement and Multi-pooling[J]. IEEE Access, 2020, 8: 126051-126065.

[3] LIN Y, LI J P, YANG L, et al. Sentiment Analysis with Comparison Enhanced Deep Neural Network[J]. IEEE Access, 2020, 8: 78378-78384.

[4] ZHOU J, TIAN J F, WANG R, et al. Sentix: A Sentiment-Aware Pre-trained Model for Cross-Domain Sentiment Analysis[C]// Proceedings of the 28th International Conference on Computational Linguistics. Palo Alto: AAAI Press, 2020: 568-579.

[5] NIU Y L, XIE R B, LIU Z Y, et al. Improved Word Representation Learning with Sememes[C]// Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. [S. l.]: ACL, 2017: 2049-2058.

[6] MACKEY G W. Mathematical Foundations of Quantum Mechanics[M]. North Chelmsford: Courier Corporation, 2004: 1-160.

[7] ZHANG P, MA X D, SONG D W. A Survey of Quantum Language Models[J]. Scientia Sinica Informationis, 2018, 48(11): 1467-1486.

[8] DENG L J, WIEBE J. Mpqa 3.0: An Entity/Event-Level Sentiment Corpus[C]// Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. [S. l.]: ACL. 2015: 1323-1328.

[9] KIRITCHENKO S, ZHU X D, MOHAMMAD S M. Sentiment Analysis of Short Informal Texts[J]. Journal of Artificial Intelligence Research, 2014, 50: 723-762.

[10] DING H B, RILOFF E. Acquiring Knowledge of Affective Events from Blogs Using Label Propagation[C]// Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2016: 2935-2942.

[11] LIAO J, LI Y, WANG S G. The Constitution of a Fine-Grained Opinion Annotated Corpus on Weibo[C]// Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data. Berlin: Springer International Publishing, 2016: 227-240.

[12] ZHANG D Y, LIN H F, YANG L, et al. Construction of a Chinese Corpus for the Analysis of the Emotionality of Metaphorical Expressions[C]// Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. [S. l.]: ACL, 2018: 144-150.

[13] LIAO J, ZHANG K, WANG S G, et al. Research on Implicit Sentiment Analysis Based on Heterogeneous User Knowledge Fusion[C]// Proceedings of the 21st Chinese National Conference on Computational Linguistics. [S. l.]: ACL, 2022: 523-534.

[14] AHMAD K M, LIU Q, KHAN A A, et al. SEntIMeld CL: Enhancing Explicit Knowledge via Uniform-Based Implicit Contrastive Mechanism for Aspect-Level Sentiment Analysis[J]. Neural Networks, 2025, 191: 107711-1-107711-15.

[15] HE B, ZHAO R Y, TANG D L. CABiLSTM-BERT: Aspect-Based Sentiment Analysis Model Based on Deep Implicit Feature Extraction[J]. Knowledge-Based Systems, 2025, 309: 112782-1-112782-13.

[16] MAO Y Y, LIU Q, ZHANG Y. Enhancing Implicit Sentiment Analysis via Knowledge Enhancement and Context Information[J]. Complex & Intelligent Systems, 2025, 11(5): 222-1-222-15.

[17] LI X, WANG X L, YAO C L, et al. Graph-Enhanced Implicit Aspect-Level Sentiment Analysis Based on Multi-prompt Fusion[J]. Scientific Reports, 2025, 15(1): 17460-1-17460-19.

[18] REN J, ZHOU W H, LI B W, et al. Causal Prompting for Implicit Sentiment Analysis with Large Language Models[EB/OL]. (2025-07-01)[2026-02-10]. https://arxiv.org/html/2507.00389v1.

[19] LAI W W, XIE H R, XU G D, et al. Rvisa: Reasoning and Verification for Implicit Sentiment Analysis[J]. IEEE Transactions on Affective Computing, 2025, 16(3): 1760-1771.

[20] WANG H B, HOU M H. Quantum-Like Implicit Sentiment Analysis with Sememes Knowledge[J]. Expert Systems with Applications, 2023, 232: 120720-1-120720-9.

[21] BALAHUR A, HERMIDA J M, MONTOYO A. Detecting Implicit Expressions of Emotion in Text: A Comparative Analysis[J]. Decision Support Systems, 2012, 53(4): 742-753.

[22] WANG H B, ZHANG F Z, WANG J L, et al. Ripplenet: Propagating User Preferences on the Knowledge Graph for Recommender Systems[C]// Proceedings of the 27th ACM International Conference on Information and Knowledge Management. New York: ACM, 2018: 417-426.

[23] LIU Z H, XIONG C Y, SUN M S, et al. Entity-Duet Neural Ranking: Understanding the Role of Knowledge Graph Semantics in Neural Information Retrieval[EB/OL]. (2018-05-19)[2025-01-01]. https://arxiv.org/abs/1805.07591.

[24] ZHANG Y, WANG J, YU L C, et al. Ma-bert: Learning Representation by Incorporating Multi-attribute Knowledge in Transformers[C]// Findings of the Association for Computational Linguistics. [S. l.]: ACL, 2021: 2338-2343.

[25] ZHANG Z Y, HAN X, LIU Z Y, et al. ERNIE: Enhanced Language Representation with Informative Entities[EB/OL]. (2019-05-17)[2024-12-20]. https://arxiv.org/abs/1905.07129.

[26] WANG Z K, LI L J, ZENG D. Knowledge-Enhanced Natural Language Inference Based on Knowledge Graphs[C]// Proceedings of the 28th International Conference on Computational Linguistics. [S. l.]: ACL, 2020: 6498-6508.

[27] JAIN D K, BOYAPATI P, VENKATESH J, et al. An Intelligent Cognitive-Inspired Computing with Big Data Analytics Framework for Sentiment Analysis and Classification[J]. Information Processing & Management, 2022, 59(1): 102758-1-102758-15.

[28] AXELSSON A, SKANTZE G. Using Large Language Models for Zero-Shot Natural Language Generation from Knowledge Graphs[EB/OL]. (2023-07-14)[2025-01-01]. https://arxiv.org/abs/2307.07312.

[29] WEI Y B, HUANG Q S, KWOK J T, et al. KICGPT: Large Language Model with Knowledge in Context for Knowledge Graph Completion[EB/OL]. (2024-02-04)[2025-01-10]. https://arxiv.org/html/2402.02389v1.

[30] DONG Z D, DONG Q. HowNet-a Hybrid Language and Knowledge Resource[C]// International Conference on Natural Language Processing and Knowledge Engineering. Piscataway, NJ: IEEE, 2003: 820-824.

[31] QIAO C, HUANG B, NIU G C, et al. A New Method of Region Embedding for Text Classification[EB/OL]. (2018-02-15)[2024-12-30]. https://openreview.net/pdf?id=BKSDMA36z.

[32] CHEN Y B, XU L H, LIU K, et al. Event Extraction via Dynamic Multi-pooling Convolutional Neural Networks[C]// Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. [S. l.]: ACL, 2015: 167-176.

[33] LAI S W, XU L H, LIU K, et al. Recurrent Convolutional Neural Networks for Text Classification[C]// Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto: AAAI Press, 2015: 2267-2273.

[34] ZHOU P, SHI W, TIAN J, et al. Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification[C]// Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. [S. l.]: ACL, 2016: 207-212.

[35] WEI J Y, LIAO J, YANG Z F, et al. BiLSTM with Multi-polarity Orthogonal Attention for Implicit Sentiment Analysis[J]. Neurocomputing, 2020, 383: 165-173.

[36] ZUO E G, ZHAO H, CHEN B, et al. Context-Specific Heterogeneous Graph Convolutional Network for Implicit Sentiment Analysis[J]. IEEE Access, 2020, 8: 37967-37975.

[37] 王素格, 王敏, 廖健, 等. 融合上下文信息的隐式情感句判别方法[J]. 山西大学学报(自然科学版), 2022, 45(2):380-386.

[38] (WANG S G, WANG M, LIAO J, et al. An Implicit Sentiment Sentence Identification Method Base on Context Information[J]. Journal of Shanxi University (Natural Science Edition), 2022, 45(2): 380-386.)

[39] XU M H, WANG D L, FENG S, et al. KC-ISA: An Implicit Sentiment Analysis Model Combining Knowledge Enhancement and Context Features[C]// Proceedings of the 29th International Conference on Computational Linguistics. [S. l.]: ACL, 2022: 6906-6915.

[40] LIAO J, WANG M, CHEN X, et al. Dynamic Commonsense Knowledge Fused Method for Chinese Implicit Sentiment Analysis[J]. Information Processing & Management, 2022, 59(3): 102934-1-102934-15.

[41] PONTIKI M, GALANIS D, PAPAGEORGIOU H, et al. SemEval-2014 Task 4: Aspect Based Sentiment Analysis[C]// International Workshop on Semantic Evaluation. [S. l.]: ACL, 2014: 27-35.

[42] ZHANG C, LI Q C, SONG D W. Aspect-Based Sentiment Classification with Aspect-Specific Graph Convolutional Networks[EB/OL]. (2019-09-08)[2024-12-10]. https://arxiv.org/abs/1909.03477.

[43] 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. [S. l.]: ACL, 2016: 606-615.

[44] MA D H, LI S J, ZHANG X D, et al. Interactive Attention Networks for Aspect-Level Sentiment Classification[EB/OL]. (2017-09-04)[2025-01-10]. https://arxiv.org/abs/1709.00893.

[45] CHEN P, SUN Z Q, BING L D, et al. Recurrent Attention Network on Memory for Aspect Sentiment Analysis[C]// Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. [S. l.]: ACL, 2017: 452-461.

[46] 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. [S. l.]: ACL, 2018: 3433-3442.

[47] CHEN Z, QIAN T. Transfer Capsule Network for Aspect Level Sentiment Classification[C]// Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. [S. l.]: ACL, 2019: 547-556.

[48] LI Z Y, ZOU Y C, ZHANG C, et al. Learning Implicit Sentiment in Aspect-Based Sentiment Analysis with Supervised Contrastive Pre-training[EB/OL]. (2021-11-03)[2025-01-03]. https://arxiv.org/abs/2111.02194.

基金资助

国家自然科学基金(61966020)

云南省基础研究面上项目(202201AT070157)