Sarcasm Detection in Social Media Using Contrastive Semantic Representation Learning
Keywords:
sarcasm detection; contrastive learning; social media; representation learning; natural language processing; AI governanceAbstract
Sarcasm in social media presents a persistent challenge for sentiment analysis and content moderation because speakers routinely express negative evaluative intent through positive or incongruous surface language. This paper presents a system-level examination of sarcasm detection using contrastive semantic representation learning. Rather than treating sarcasm as a simple supervised classification problem over pretrained embeddings, the approach constructs positive and negative semantic views of utterances and shapes representation spaces so that sarcastic and literal expressions become separable while preserving topic, user, and platform context. The paper analyzes architectural structure, data infrastructure, training objectives, evaluation, deployment, robustness, fairness, and governance. It discusses trade-offs between lexical invariance and pragmatic sensitivity, centralized and federated training, high-throughput moderation and community fairness, and model quality and environmental cost. The analysis draws on cross-domain illustrations from content moderation, brand analytics, and social listening. It argues that robust sarcasm detection requires not only improved representation learning but also institutional mechanisms for documentation, auditing, and policy alignment. The paper further identifies open challenges concerning dialect variation, multilingual sarcasm, label uncertainty, temporal drift, and sustainability. Overall, contrastive semantic representation learning is positioned as a promising foundation for sarcasm detection systems that are both technically resilient and socially accountable.
References
1. Davidov, D., Tsur, O., & Rappoport, A. (2010). Semi-supervised recognition of sarcasm in Twitter and Amazon. Proceedings of the Fourteenth Conference on Computational Natural Language Learning, 107–116.
2. Sulis, E., Irazú Hernández Farías, D., Rosso, P., Patti, V., & Ruffo, G. (2016). Figurative messages and affect in Twitter: Differences between #irony, #sarcasm and #not. Knowledge-Based Systems, 108, 132–143.
3. Riloff, E., Qadir, A., Surve, P., De Silva, L., Gilbert, N., & Huang, R. (2013). Sarcasm as contrast between a positive sentiment and negative situation. Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, 704–714.
4. Oprea, S., & Magdy, W. (2020). iSarcasm: A dataset of self-annotated sarcasm in social media. Proceedings of the International AAAI Conference on Web and Social Media, 14(1), 720–729.
5. Van Hee, C., Lefever, E., & Hoste, V. (2018). SemEval-2018 Task 3: Irony detection in English tweets. Proceedings of the 12th International Workshop on Semantic Evaluation, 39–50.
6. Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A simple framework for contrastive learning of visual representations. Proceedings of the 37th International Conference on Machine Learning, 1597–1607.
7. Gao, T., Yao, X., & Chen, D. (2021). SimCSE: Simple contrastive learning of sentence embeddings. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 6894–6910.
8. Li, Q. (2026). Dynamic Adaptive Attention and Supervised Contrastive Learning: A Novel Hybrid Framework for Text Sentiment Classification. arXiv preprint arXiv:2604.10459.
9. Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 4171–4186.
10. Reimers, N., & Gurevych, I. (2019). Sentence-BERT: Sentence embeddings using Siamese BERT-networks. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, 3982–3992.
11. van den Oord, A., Li, Y., & Vinyals, O. (2018). Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748.
12. He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020). Momentum contrast for unsupervised visual representation learning. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 9729–9738.
13. Ribeiro, M. T., Wu, T., Guestrin, C., & Singh, S. (2020). Beyond accuracy: Behavioral testing of NLP models with CheckList. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 4902–4912.
14. Barocas, S., & Selbst, A. D. (2016). Big data's disparate impact. California Law Review, 104(3), 671–732.
15. Mitchell, M., Wu, S., Zaldivar, A., Barnes, P., Vasserman, L., Hutchinson, B., Spitzer, E., Raji, I. D., & Gebru, T. (2019). Model cards for model reporting. Proceedings of the Conference on Fairness, Accountability, and Transparency, 220–229.
16. Raji, I. D., Smart, A., White, R. N., Mitchell, M., Gebru, T., Hutchinson, B., Smith-Loud, J., Theron, D., & Barnes, P. (2020). Closing the AI accountability gap: Defining an end-to-end framework for internal algorithmic auditing. Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, 33–44.
17. Strubell, E., Ganesh, A., & McCallum, A. (2019). Energy and policy considerations for deep learning in NLP. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 3645–3650.
18. Gorwa, R., Binns, R., & Katzenbach, C. (2020). Algorithmic content moderation: Technical and political challenges in the automation of platform governance. Big Data & Society, 7(1), 1–15.
19. McMahan, B., Moore, E., Ramage, D., Hampson, S., & Agüera y Arcas, B. (2017). Communication-efficient learning of deep networks from decentralized data. Proceedings of the 20th International Conference on Artificial Intelligence and Statistics, 1273–1282.
20. Gama, J., Žliobaitė, I., Bifet, A., Pechenizkiy, M., & Bouchachia, A. (2014). A survey on concept drift adaptation. ACM Computing Surveys, 46(4), Article 44.
21. Bender, E. M., & Friedman, B. (2018). Data statements for natural language processing: Toward mitigating system bias and enabling better science. Transactions of the Association for Computational Linguistics, 6, 587–604.
22. Wieringa, M. (2020). What to account for when accounting for algorithms: A systematic literature review on algorithmic accountability. Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, 1–18.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 International Journal of Artificial Intelligence Engineering and Systems
This work is licensed under a Creative Commons Attribution 4.0 International License.
This article is published under the Creative Commons Attribution 4.0 International License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
