Abstract
Computational Linguistics (CL) associated with the Internet of Multimedia Things (IoMT)-enabled multimedia computing applications brings several research challenges, such as real-time speech understanding, deep fake video detection, emotion recognition, home automation, and so on. Due to the emergence of machine translation, CL solutions have increased tremendously for different natural language processing (NLP) applications. Nowadays, NLP-enabled IoMT is essential for its success. Sarcasm detection, a recently emerging artificial intelligence (AI) and NLP task, aims at discovering sarcastic, ironic, and metaphoric information implied in texts that are generated in the IoMT. It has drawn much attention from the AI and IoMT research community. The advance of sarcasm detection and NLP techniques will provide a cost-effective, intelligent way to work together with machine devices and high-level human-to-device interactions. However, existing sarcasm detection approaches neglect the hidden stance behind texts, thus insufficient to exploit the full potential of the task. Indeed, the stance, i.e., whether the author of a text is in favor of, against, or neutral toward the proposition or target talked in the text, largely determines the text’s actual sarcasm orientation. To fill the gap, in this research, we propose a new task: stance-level sarcasm detection (SLSD), where the goal is to uncover the author’s latent stance and based on it to identify the sarcasm polarity expressed in the text. We then propose an integral framework, which consists of Bidirectional Encoder Representations from Transformers (BERT) and a novel stance-centered graph attention networks (SCGAT). Specifically, BERT is used to capture the sentence representation, and SCGAT is designed to capture the stance information on specific target. Extensive experiments are conducted on a Chinese sarcasm sentiment dataset we created and the SemEval-2018 Task 3 English sarcasm dataset. The experimental results prove the effectiveness of the SCGAT framework over state-of-the-art baselines by a large margin.
- [1] . 2015. Towards context-sensitive collaborative media recommender system. Multimed. Tools Appl. 74, 24 (2015), 11399–11428.Google ScholarDigital Library
- [2] . 2016. Cloud-assisted Industrial Internet of Things (IIoT). Enabled framework for health monitoring. Comput. Netw. 101 (2016), 192–202.Google ScholarDigital Library
- [3] . 2016. Stance detection with bidirectional conditional encoding. Retrieved from https://arXiv:1606.05464.Google Scholar
- [4] . 2019. Extension of the lexicon algorithm for sarcasm detection. In Proceedings of the 3rd International Conference on Computing Methodologies and Communication (ICCMC’19). IEEE, 1063–1068.Google ScholarCross Ref
- [5] . 2015. Contextualized sarcasm detection on twitter. In Proceedings of the 9th International AAAI Conference on Web and Social Media.Google Scholar
- [6] . 2015. Parsing-based sarcasm sentiment recognition in twitter data. In Proceedings of the IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining. ACM, 1373–1380.Google ScholarDigital Library
- [7] . 2019. Multi-modal sarcasm detection in twitter with hierarchical fusion model. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 2506–2515.Google ScholarCross Ref
- [8] . 2014. A fast and accurate dependency parser using neural networks. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’14). 740–750.Google ScholarCross Ref
- [9] . 2021. Machine learning and feature engineering-based study into sarcasm and irony classification with application to cyberbullying detection. Info. Process. Manage. 58, 4 (2021), 102600.Google ScholarDigital Library
- [10] . 2010. Semi-supervised recognition of sarcastic sentences in twitter and amazon. In Proceedings of the 14th Conference on Computational Natural Language Learning. Association for Computational Linguistics, 107–116.Google ScholarDigital Library
- [11] . 2018. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 4171–4186.Google Scholar
- [12] . 2021. Context-based feature technique for sarcasm identification in benchmark datasets using deep learning and BERT model. IEEE Access 9 (2021), 48501–48518.Google ScholarCross Ref
- [13] . 2016. Folksonomy-based visual ontology construction and its applications. IEEE Trans. Multimedia 18, 4 (2016), 702–713.Google ScholarDigital Library
- [14] . 2021. Sarcasm and sentiment detection in arabic language a hybrid approach combining embeddings and rule-based features. In Proceedings of the 6th Arabic Natural Language Processing Workshop. 351–356.Google Scholar
- [15] . 2021. Support vector machine classifier with principal component analysis and k mean for sarcasm detection. In Proceedings of the 7th International Conference on Advanced Computing and Communication Systems (ICACCS’21), Vol. 1. IEEE, 571–576.Google ScholarCross Ref
- [16] . 2012. Emotion as stance. Emotion in Interaction 16 (2012), 41.Google Scholar
- [17] . 2012. Current conceptions of stance. In Stance and Voice in Written Academic Genres. Springer, 15–33.Google ScholarCross Ref
- [18] . 2015. Applying basic features from sentiment analysis for automatic irony detection. In Proceedings of the Iberian Conference on Pattern Recognition and Image Analysis. Springer, 337–344.Google ScholarCross Ref
- [19] . 2021. Sarcasm detection using cognitive features of visual data by learning model. Expert Syst. Appl. 184 (2021), 115476.Google ScholarDigital Library
- [20] . 2018. Emotion-aware connected healthcare big data towards 5G. IEEE Internet Things J. 5, 4 (2018), 2399–2406.Google ScholarCross Ref
- [21] . 2019. Emotion recognition using deep-learning approach from audio-visual emotional big data. Info. Fusion 49 (2019), 69–78.Google ScholarDigital Library
- [22] . 2019. Smart healthcare monitoring: A voice pathology detection paradigm for smart cities. Multimedia Syst. 25, 5 (2019).Google ScholarCross Ref
- [23] . 2019. Syntax-aware aspect level sentiment classification with graph attention networks. Retrieved from https://arXiv:1909.02606.Google Scholar
- [24] et al. 2020. Privacy-enhanced data fusion for COVID-19 applications in intelligent Internet of medical Things. IEEE Internet Things J. 8, 21 (2020), 15683–15693.Google ScholarCross Ref
- [25] . 2021. Detecting sarcasm in multi-domain datasets using convolutional neural networks and long short-term memory network model. PeerJ Comput. Sci. 7 (2021), e645.Google ScholarCross Ref
- [26] . 2016. Are word embedding-based features useful for sarcasm detection? Retrieved from https://arXiv:1610.00883.Google Scholar
- [27] . 2021. Cat-bigru: Convolution and attention with bi-directional gated recurrent unit for self-deprecating sarcasm detection. Cogn. Comput. (2021), 1–19.Google Scholar
- [28] . 2015. Your sentiment precedes you: Using an author’s historical tweets to predict sarcasm. In Proceedings of the 6th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis. 25–30.Google ScholarCross Ref
- [29] . 2014. Convolutional neural networks for sentence classification. Retrieved from https://arXiv:1408.5882.Google Scholar
- [30] . 2018. Representing social media users for sarcasm detection. Retrieved from https://arXiv:1808.08470.Google Scholar
- [31] . 2013. Distinguishing sarcasm from literal language: Evidence from books and blogging. Disc. Process. 50, 8 (2013), 598–615.Google ScholarCross Ref
- [32] . 2007. Lexical influences on the perception of sarcasm. In Proceedings of the Workshop on Computational Approaches to Figurative Language. 1–4.Google ScholarDigital Library
- [33] . 2020. Stance detection: A survey. ACM Comput. Surveys 53, 1 (2020), 1–37.Google ScholarDigital Library
- [34] et al. 2020. Deep anomaly detection for time-series data in industrial IoT: A communication-efficient on-device federated learning approach. IEEE Internet Things J. 8, 8 (2020), 6348–6358.Google ScholarCross Ref
- [35] . 2019. Sarcasm detection using soft attention-based bidirectional long short-term memory model with convolution network. IEEE Access 7 (2019), 23319–23328.Google ScholarCross Ref
- [36] . 2020. Multilingual stance detection in social media political debates. Comput. Speech Lang. 63 (2020), 101075.Google ScholarCross Ref
- [37] . 2003. Is it harder to parse chinese, or the chinese treebank? In Proceedings of the 41st Annual Meeting on Association for Computational Linguistics. Association for Computational Linguistics, 439–446.Google ScholarDigital Library
- [38] . 2021. Multi-modal sarcasm detection with interactive in-modal and cross-modal graphs. In Proceedings of the 29th ACM International Conference on Multimedia. 4707–4715.Google ScholarDigital Library
- [39] . 2019. Sentiment and sarcasm classification with multitask learning. Retrieved from https://arXiv:1901.08014.Google Scholar
- [40] . 2019. Deep CNN-LSTM with word embeddings for news headline sarcasm detection. In Proceedings of the 16th International Conference on Information Technology-New Generations (ITNG’19). Springer, 495–498.Google ScholarCross Ref
- [41] . 2021. A lightweight and robust secure key establishment protocol for internet of medical things in COVID-19 patients care. IEEE Internet Things J. 8, 21 (2021), 15694–15703.
DOI: Google ScholarCross Ref - [42] . 2022. Lightweight and anonymity-preserving user authentication scheme for IoT-based healthcare. IEEE Internet Things J. 9, 4 (2022), 2649–2656.Google ScholarCross Ref
- [43] . 2018. Automatic stance detection using end-to-end memory networks. Retrieved from https://arXiv:1804.07581.Google Scholar
- [44] . 2021. Machine learning-based model for sentiment and sarcasm detection. In Proceedings of the 6th Arabic Natural Language Processing Workshop. 386–389.Google Scholar
- [45] . 2020. Machine learning based sarcasm detection on twitter data. In Proceedings of the 5th International Conference on Communication and Electronics Systems (ICCES’20). IEEE, 957–961.Google ScholarCross Ref
- [46] . 2014. Glove: Global vectors for word representation. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’14). 1532–1543.Google ScholarCross Ref
- [47] . 2016. A deeper look into sarcastic tweets using deep convolutional neural networks. Retrieved from https://arXiv:1610.08815.Google Scholar
- [48] . 2018. Sarcasm detection using recurrent neural network. In Proceedings of the 2nd International Conference on Intelligent Computing and Control Systems (ICICCS’18). IEEE, 746–748.Google ScholarCross Ref
- [49] . 2015. Social event classification via boosted multimodal supervised latent dirichlet allocation. ACM Trans. Multimedia Comput. Commun. Appl. 11, 2, Article
27 (Jan. 2015), 27:1-27:22 pages.Google ScholarDigital Library - [50] . 2021. Adversarial examples-security threats to COVID-19 deep-learning systems in medical IoT devices. IEEE Internet Things J. 8, 12 (2021), 9603–9610.Google ScholarCross Ref
- [51] . 2019. Sentence-BERT: Sentence embeddings using siamese BERT-networks. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics. Retrieved from http://arxiv.org/abs/1908.10084.Google ScholarCross Ref
- [52] . 2018. Context-augmented convolutional neural networks for twitter sarcasm detection. Neurocomputing 308 (2018), 1–7.Google ScholarDigital Library
- [53] . 2019. Enforcing position-based confidentiality with machine learning paradigm through mobile edge computing in real-time industrial informatics. IEEE Trans. Industr. Inform. 15, 7 (2019), 4189–4196.Google ScholarCross Ref
- [54] . 2016. Detecting sarcasm in multimodal social platforms. In Proceedings of the 24th ACM International Conference on Multimedia (MM’16). Association for Computing Machinery, New York, NY, 1136–1145. Google ScholarDigital Library
- [55] . 2020. MetaCOVID: A siamese neural network framework with contrastive loss for n-shot diagnosis of COVID-19 patients. Pattern Recogn. (2020), 107700–107700.Google Scholar
- [56] . 2017. A dataset for multi-target stance detection. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics. 551–557.Google ScholarCross Ref
- [57] . 2020. A novel hierarchical BERT architecture for sarcasm detection. In Proceedings of the 2nd Workshop on Figurative Language Processing. 93–97.Google ScholarCross Ref
- [58] . 2018. Stance detection with hierarchical attention network. In Proceedings of the 27th International Conference on Computational Linguistics. 2399–2409.Google Scholar
- [59] . 2020. Multi-rule based ensemble feature selection model for sarcasm type detection in twitter. Comput. Intell. Neurosci. 2020 (2020).Google ScholarDigital Library
- [60] . 2015. Cloud-supported cyber.physical localization framework for patients monitoring. IEEE Syst J. 11, 1 (2015), 118–127.Google ScholarCross Ref
- [61] . 2021. DAPath: Distance-aware knowledge graph reasoning based on deep reinforcement learning. Neural Netw. 135 (2021), 1–12.Google ScholarCross Ref
- [62] . 2020. Fake news stance detection using deep-learning architecture (CNN-LSTM). IEEE Access 8 (2020), 156695–156706.Google ScholarCross Ref
- [63] . 2018. Semeval-2018 task 3: Irony detection in english tweets. In Proceedings of the 12th International Workshop on Semantic Evaluation. 39–50.Google Scholar
- [64] . 2017. Graph attention networks. Retrieved from https://arXiv:1710.10903.Google Scholar
- [65] . 2021. Real time sarcasm detection on twitter using ensemble methods. In Proceedings of the 3rd International Conference on Inventive Research in Computing Applications (ICIRCA’21). IEEE, 1292–1297.Google ScholarCross Ref
- [66] . 2020. Building a bridge: A method for image-text sarcasm detection without pretraining on image-text data. In Proceedings of the 1st International Workshop on Natural Language Processing Beyond Text. 19–29.Google ScholarCross Ref
- [67] . 2015. Twitter sarcasm detection exploiting a context-based model. In Proceedings of the International Conference on Web Information Systems Engineering. Springer, 77–91.Google ScholarDigital Library
- [68] . 2018. Thu_ngn at semeval-2018 task 3: Tweet irony detection with densely connected lstm and multi-task learning. In Proceedings of the 12th International Workshop on Semantic Evaluation. 51–56.Google ScholarCross Ref
- [69] . 2021. Modeling incongruity between modalities for multimodal sarcasm detection. IEEE MultiMedia 28, 2 (2021), 86–95.Google ScholarCross Ref
- [70] . 2019. Sarcasm detection with self-matching networks and low-rank bilinear pooling. In Proceedings of the World Wide Web Conference. ACM, 2115–2124.Google ScholarDigital Library
- [71] . 2015. Automatic visual concept learning for social event understanding. IEEE Trans. Multimedia 17, 3 (2015), 346–358.Google ScholarDigital Library
- [72] . 2016. Deep relative attributes. IEEE Trans. Multimedia 18, 9 (2016), 1832–1842.Google ScholarDigital Library
- [73] . 2019. IoT big data analytics for smart homes with fog and cloud computing. Future Gen. Comput. Syst. 91 (2019), 563–573.Google ScholarDigital Library
- [74] . 2021. Multi-task deep neural networks for joint sarcasm detection and sentiment analysis. Pattern Recogn. Image Anal. 31, 1 (2021), 103–108.Google ScholarDigital Library
- [75] . 2019. Aspect-based sentiment classification with aspect-specific graph convolutional networks. Retrieved from https://arXiv:1909.03477.Google Scholar
- [76] . 2019. Quantum-inspired interactive networks for conversational sentiment analysis. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI’19). 5436–5442. https://academic.microsoft.com/paper/2963533390.Google ScholarCross Ref
- [77] . 2021. CFN: A complex-valued fuzzy network for sarcasm detection in conversations. IEEE Trans. Fuzzy Syst. 29, 12 (2021), 3696–3710.Google ScholarDigital Library
- [78] . 2020. A quantum-like multimodal network framework for modeling interaction dynamics in multiparty conversational sentiment analysis. Inform. Fusion 62 (2020), 14–31.Google ScholarCross Ref
- [79] . 2018. A quantum-inspired multimodal sentiment analysis framework. Theoret. Comput. Sci. 752 (2018), 21–40.Google ScholarCross Ref
- [80] . 2021. Learning interaction dynamics with an interactive LSTM for conversational sentiment analysis. Neural Netw. 133 (2021), 40–56.Google ScholarCross Ref
- [81] et al. 2020. EEG-based pathology detection for home health monitoring. IEEE J. Sel. Areas Commun. 39, 2 (2020), 603–610.Google ScholarCross Ref
- [82] . 2022. A collaborative AI-enabled pretrained language model for AIoT domain question answering. IEEE Trans. Industr. Inform. 18, 5 (2022), 3387–3396.Google ScholarCross Ref
Index Terms
- Stance-level Sarcasm Detection with BERT and Stance-centered Graph Attention Networks
Recommendations
Automatic Sarcasm Detection: A Survey
Automatic sarcasm detection is the task of predicting sarcasm in text. This is a crucial step to sentiment analysis, considering prevalence and challenges of sarcasm in sentiment-bearing text. Beginning with an approach that used speech-based features, ...
Quantifying controversy from stance, sentiment, offensiveness and sarcasm: a fine-grained controversy intensity measurement framework on a Chinese dataset
AbstractControversy measurement on social media plays an important part in understanding public opinion. Various topics are frequently hotly debated on social media platforms including Twitter and Sina Weibo. People sometimes use offensive or sarcastic ...
The unbearable hurtfulness of sarcasm
AbstractIn the last decade, the need to detect automatically irony to correctly recognize the sentiment and hate speech involved in online texts increased the investigation on humorous figures of speech in NLP. The slight boundaries among ...
Highlights- Hurtful language is consistently found in a corpus of Italian sarcastic language.
Comments