Computer Science

Computer Science ›› 2026, Vol. 53 ›› Issue (2): 300-311.doi: 10.11896/jsjkx.250500015

• Artificial Intelligence • Previous Articles     Next Articles

Dynamic Interaction Dual-channel Graph Attention Network for Chinese and English SarcasmDetection

TAN Pingping1,2, XU Ji2, LI Yijun3, WANG Hai3   

  1. 1 College of Computer Science and Technology,Guizhou University,Guiyang 550025,China
    2 State Key Laboratory of Public Big Data(Guizhou University),Guiyang 550025,China
    3 Baishan Cloud Technology Co.,Ltd.,Guiyang 550081,China
  • Received:2025-05-07 Revised:2025-07-04 Published:2026-02-10
  • About author:TAN Pingping,born in 1999,postgra-duate,is a student member of CCF(No.N8697G).Her main research in-terests include natural language processing and artificial intelligence.
    XU Ji,born in 1979.Ph.D,distinguished professor.His main research interests include data mining,granular computing and machine learning.
  • Supported by:
    National Natural Science Foundation of China(62366008,61966005).

PDF (PC)

84

Abstract: Due to the complexity of Chinese semantics and the nuanced expression of emotions,Chinese text sarcasm detection presents a challenging task.Existing sarcasm detection methods are predominantly developed for English and struggle to adapt to the unique expressions and cultural connotations of Chinese.Therefore,this paper proposes a novel dynamic interaction dual-channel graph attention network(DiDu-GAT),which utilizes a unique dual-channel structure to analyze syntactic dependencies and emotional features in texts.DiDu-GAT incorporates a dynamic interaction mechanism to enhance its cross-channel learning capabilities,enabling comprehensive extraction of emotional information and syntactic patterns,thereby significantly improving the accuracy of Chinese sarcasm detection.Experimental results on the HIT Chinese sarcasm dataset(GuanSarcasm) and two public English sarcasm datasets(IAC-V1 and IAC-V2) demonstrate that the proposed method significantly outperforms existing baseline methods across key performance metrics,validating its effectiveness and superiority in both Chinese and English sarcasm detection tasks.

Key words: Graph attention network, Chinese sarcasm detection, Dual-channel dynamic interaction, Sentiment analysis, Sarcasm text recognition

CLC Number: 

  • TP311.13
[1]SINGH B,SHARMA D K.A survey of sarcasm detection techniques in natural language processing[C]//2023 6th International Conference on Information Systems and Computer Networks(ISCON).IEEE,2023:1-6.
[2]YAO B,ZHANG Y,LI Q,et al.Is sarcasm detection a step-by-step reasoning process in large language models?[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2025:25651-25659.
[3]LOU C,LIANG B,GUI L,et al.Affective dependency graph for sarcasm detection[C]//Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval.2021:1844-1849.
[4]DU Y,HE H,CHU Z.Cross-cultural nuances in sarcasm comprehension:a comparative study of Chinese and American perspectives[J].Frontiers in Psychology,2024,15:1349002.
[5]XIONG T,ZHANG P,ZHU H,et al.Sarcasm detection withself-matching networks and low-rank bilinear pooling[C]//The World Wide Web Conference.2019:2115-2124.
[6]WEN Z,GUI L,WANG Q,et al.Sememe knowledge and auxi-liary information enhanced approach for sarcasm detection[J].Information Processing & Management,2022,59(3):102883.
[7]ZHANG X,SHI N,HAUER B,et al.Bridging the Gap Between BabelNet and HowNet:Unsupervised Sense Alignment and Sememe Prediction[C]//Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics.2023:2789-2798.
[8]YANG L,JIA W,LI S,et al.Deep learning technique for human parsing:A survey and outlook[J].International Journal of Computer Vision,2024,132(8):3270-3301.
[9]WANKHADE M,RAO A C S,KULKARNI C.A survey onsentiment analysis methods,applications,and challenges[J].Artificial Intelligence Review,2022,55(7):5731-5780.
[10]CAI T T,MA R.Theoretical foundations of t-sne for visualizing high-dimensional clustered data[J].Journal of Machine Learning Research,2022,23(301):1-54.
[11]FRENDA S,CIGNARELLA A T,BASILE V,et al.The unbearable hurtfulness of sarcasm[J].Expert Systems with Applications,2022,193:1.
[12]REN H,ZHANG J,QUN N,et al.A Method for Chinese Sarcasm Detection Based on Enhanced Cross-Entropy and Regularization[C]//2024 IEEE 5th International Conference on Pattern Recognition and Machine Learning(PRML).IEEE,2024:133-137.
[13]LI K,ZHANG Y,LI K,et al.Image-text embedding learning via visual and textual semantic reasoning[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2022,45(1):641-656.
[14]JOSHI A,SHARMA V,BHATTACHARYYA P.Harnessingcontext incongruity for sarcasm detection[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing.2015:757-762.
[15]GHOSH A,VEALE T.Fracking sarcasm using neural network[C]//Proceedings of the 7th Workshop on Computational Approaches to Subjectivity,Sentiment and Social Media Analysis.2016:161-169.
[16]KATTENBORN T,LEITLOFF J,SCHIEFER F,et al.Review on Convolutional Neural Networks(CNN) in vegetation remote sensing[J].ISPRS Journal of Photogrammetry and Remote Sensing,2021,173:24-49.
[17]SHIRI F M,PERUMAL T,MUSTAPHA N,et al.A Comprehensive Overview and Comparative Analysis on Deep Learning Models[J].arXiv:2305.17473,2023.
[18]REN W Q,QU Y B,DONG C,et al.A survey on collaborative DNN inference for edge intelligence[J].Machine Intelligence Research,2023,20(3):370-395.
[19]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.2016:207-212.
[20]NIU Z,ZHONG G,YU H.A review on the attention mechanism of deep learning[J].Neurocomputing,2021,452:48-62.
[21]LUKIN S,WALKER M.Really? Well.Apparently Bootstrapping Improves the Performance of Sarcasm and Nastiness Classifiers for Online Dialogue[C]//Proceedings of the Workshop on Language Analysis in Social Media.2013:30-40.
[22]ZELIKMAN E,WU Y,MU J,et al.Star:Bootstrapping reaso-ning with reasoning[J].Advances in Neural Information Proces-sing Systems,2022,35:15476-15488.
[23]MANDAL P K,MAHTO R.Deep CNN-LSTM with word embeddings for news headline sarcasm detection[C]//16th International Conference on Information Technology-New Generations(ITNG 2019).Springer,2019:495-498.
[24]FAN X C,YANG L,LIN H F,et al.Irony Recognition Based on Multiple Semantic Fusion[J].Journal of Chinese Information Processing,2021,35(6):103-111.
[25]KRISHNAN D,DURAIRAJ T.Getsmartmsec at semeval-2022 task 6:Sarcasm detection using contextual word embeddingwith gaussian model for irony type identification[C]//Proceedings of the 16th International Workshop on Semantic Evaluation(SemEval-2022).2022:827-833.
[26]DEVLIN J,CHANG M W,LEE K,et al.Bert:Pre-training ofdeep bidirectional transformers for language understanding[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.2019:4171-4186.
[27]LIU Y,ZHANG R,FAN Y,et al.Prompt tuning with contradictory intentions for sarcasm recognition[C]//Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics.2023:328-339.
[28]GU Y,HAN X,LIU Z,et al.PPT:Pre-trained Prompt Tuning for Few-shot Learning[C]//Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics.2022:8410-8423.
[29]HELAL N A,HASSAN A,BADR N L,et al.A contextual-based approach for sarcasm detection[J].Scientific Reports,2024,14(1):15415.
[30]TAN K L,LEE C P,LIM K M.A survey of sentiment analysis:Approaches,datasets,and future research[J].Applied Sciences,2023,13(7):4550.
[31]TAY Y,LUU A T,HUI S C,et al.Reasoning with Sarcasm by Reading In-Between[C]//Proceedings of the 56th Annual Mee-ting of the Association for Computational Linguistics.2018:1010-1020.
[32]ZHANG S,ZHANG X,CHAN J,et al.Irony detection via sentiment-based transfer learning[J].Information Processing & Management,2019,56(5):1633-1644.
[33]BABANEJAD N,DAVOUDI H,AN A,et al.Affective and contextual embedding for sarcasm detection[C]//Proceedings of the 28th International Conference on Computational Linguistics.2020:225-243.
[34]CHIA Z L,PTASZYNSKI M,MASUI F,et al.Machine Lear-ning and feature engineering-based study into sarcasm and irony classification with application to cyberbullying detection[J].Information Processing & Management,2021,58(4):102600.
[35]CHEN W,LIN F,ZHANG X,et al.Jointly learning sentimental clues and context incongruity for sarcasm detection[J].IEEE Access,2022,10:48292-48300.
[36]LIU Y,WANG Y,SUN A,et al.A Dual-Channel Frameworkfor Sarcasm Recognition by Detecting Sentiment Conflict[C]//Findings of the Association for Computational Linguistics:NAACL 2022.2022:1670-1680.
[37]VITMAN O,KOSTIUK Y,SIDOROV G,et al.Sarcasm detection framework using context,emotion and sentiment features[J].Expert Systems with Applications,2023,234:121068.
[38]HUANG J,LIU Y,WANG Q F,et al.Dual-channel graph con-volutional network with word-order knowledge for aspect-based sentiment analysis[J].Application Research of Computers,2024,41(3):779-785.
[39]JI S,PAN S,CAMBRIA E,et al.A survey on knowledgegraphs:Representation,acquisition,and applications[J].IEEE Transactions on Neural Networks and Learning Systems,2021,33(2):494-514.
[40]LIANG B,LIN Z,QIN B,et al.Topic-Oriented Sarcasm Detection:New Task,New Dataset and New Method[C]//Procee-dings of the 21st Chinese National Conference on Computational Linguistics.2022:557-568.
[41]LIU P,YUAN W,FU J,et al.Pre-train,prompt,and predict:A systematic survey of prompting methods in natural language processing[J].ACM Computing Surveys,2023,55(9):1-35.
[42]MIN C,LI X,YANG L,et al.Just like a human would,direct access to sarcasm augmented with potential result and reaction[C]//Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics.2023:10172-10183.
[43]BOSSELUT A,RASHKIN H,SAP M,et al.COMET:Com-monsense Transformers for Automatic Knowledge Graph Construction[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics.Association for Computational Linguistics,2019.
[44]HE H,CHOI J D.The Stem Cell Hypothesis:Dilemma behind Multi-Task Learning with Transformer Encoders[C]//Procee-dings of the 2021 Conference on Empirical Methods in Natural Language Processing.2021:5555-5577.
[45]QI P,ZHANG Y,ZHANG Y,et al.Stanza:A Python Natural Language Processing Toolkit for Many Human Languages[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics:System Demonstrations.Association for Computational Linguistics,2020.
[46]VRAHATIS A G,LAZAROS K,KOTSIANTIS S.Graph attention networks:a comprehensivereview of methods and applications[J].Future Internet,2024,16(9):318.
[47]JIN X,XIE Y,WEI X S,et al.Delving deep into spatial pooling for squeeze-and-excitation networks[J].Pattern Recognition,2022,121:108159.
[48]GONG X,ZHAO Q,ZHANG J,et al.The design and construction of a Chinese sarcasm dataset[C]//Proceedings of the Twelfth Language Resources and Evaluation Conference.2020:5034-5039.
[49]MIN K,MA C,ZHAO T,et al.BosonNLP:An ensemble ap-proach for word segmentation and POS tagging[C]//4th CCF Conference Natural Language Processing and Chinese Computing(NLPCC 2015).Springer,2015:520-526.
[1] BU Yunyang, QI Binting, BU Fanliang. Multimodal Sentiment Analysis for Interactive Fusion of Dual Perspectives Under Cross-modalInconsistent Perception [J]. Computer Science, 2026, 53(1): 187-194.
[2] WANG Haoyan, LI Chongshou, LI Tianrui. Reinforcement Learning Method for Solving Flexible Job Shop Scheduling Problem Based onDouble Layer Attention Network [J]. Computer Science, 2026, 53(1): 231-240.
[3] GAO Long, LI Yang, WANG Suge. Sentiment Classification Method Based on Stepwise Cooperative Fusion Representation [J]. Computer Science, 2025, 52(9): 313-319.
[4] ZHU Shihao, PENG Kexing, MA Tinghuai. Graph Attention-based Grouped Multi-agent Reinforcement Learning Method [J]. Computer Science, 2025, 52(9): 330-336.
[5] ZHOU Tao, DU Yongping, XIE Runfeng, HAN Honggui. Vulnerability Detection Method Based on Deep Fusion of Multi-dimensional Features from Heterogeneous Contract Graphs [J]. Computer Science, 2025, 52(9): 368-375.
[6] LI Mengxi, GAO Xindan, LI Xue. Two-way Feature Augmentation Graph Convolution Networks Algorithm [J]. Computer Science, 2025, 52(7): 127-134.
[7] JIANG Kun, ZHAO Zhengpeng, PU Yuanyuan, HUANG Jian, GU Jinjing, XU Dan. Cross-modal Hypergraph Optimisation Learning for Multimodal Sentiment Analysis [J]. Computer Science, 2025, 52(7): 210-217.
[8] ZHENG Cheng, YANG Nan. Aspect-based Sentiment Analysis Based on Syntax,Semantics and Affective Knowledge [J]. Computer Science, 2025, 52(7): 218-225.
[9] WANG Youkang, CHENG Chunling. Multimodal Sentiment Analysis Model Based on Cross-modal Unidirectional Weighting [J]. Computer Science, 2025, 52(7): 226-232.
[10] FAN Xing, ZHOU Xiaohang, ZHANG Ning. Review on Methods and Applications of Short Text Similarity Measurement in Social Media Platforms [J]. Computer Science, 2025, 52(6A): 240400206-8.
[11] YE Jiale, PU Yuanyuan, ZHAO Zhengpeng, FENG Jue, ZHOU Lianmin, GU Jinjing. Multi-view CLIP and Hybrid Contrastive Learning for Multimodal Image-Text Sentiment Analysis [J]. Computer Science, 2025, 52(6A): 240700060-7.
[12] HUANG Zhiyong, LI Bicheng, WEI Wei. Aspect-level Sentiment Analysis Models Based on Syntax and Semantics [J]. Computer Science, 2025, 52(6A): 240400193-7.
[13] LI Yingjian, WANG Yongsheng, LIU Xiaojun, REN Yuan. Cloud Platform Load Data Forecasting Method Based on Spatiotemporal Graph AttentionNetwork [J]. Computer Science, 2025, 52(6A): 240700178-8.
[14] MENG Xiangfu, WANG Wanchun, ZHANG Yumeng, FAN Wenyi. Multiple Attention Mechanism News Recommendation Approach with Hypergraph Learning [J]. Computer Science, 2025, 52(11A): 250200067-7.
[15] PENG Junlong, FAN Jing. Hybrid Reinforcement Learning Algorithm Combined with 2-opt for Solving Traveling Salesman Problem [J]. Computer Science, 2025, 52(11A): 250200121-8.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
Add:18# Honghu West Rd., Yubei ,Chongqing,China    Post Code: 401121
Tel: 023-63500828/023-67039612/023-67039623
E-mail: jsjkx12@163.com
Powered by Beijing Magtech Co., Ltd.