Leveraging reformers for enhanced detection and understanding of sarcastic statements
DOI:
https://doi.org/10.31117/neuroscirn.v9i4.580Keywords:
Sarcasm detection, Transformer-based model, Reformers, LSH attention, Natural language processingAbstract
Subtle sarcasm and contextual sarcasm are particularly important topics of research due to their nature as linguistic phenomena. Indeed, sarcasm detection is a complex NLP task because sarcasm conveys meaning beyond the literal one and depends heavily on context. Thus, it requires considering discourse-level features and long-term relations between statements. Machine learning and deep learning models often perform poorly in recognising sarcasm because they cannot effectively incorporate contextual cues and polarity shifts. To address this problem, this paper introduces an improved sarcasm detection framework based on the Reformer transformer model to improve efficiency in modelling long sequences and extracting semantic features. We evaluated the proposed model on benchmark datasets (news, social media texts, conversations), using accuracy, precision, recall, F1-score, and AUC-ROC as performance indicators. The results showed that the recommended model outperformed several other available frameworks (BiLSTM, BERT, RoBERTa, DistilBERT).
Downloads
References
Adek, R. T., Bustami, & Ula, M. (2021). Systematics Review on the Application of Social Media Analytics for Detecting Radical and Extremist Group. IOP Conference Series. IOP Conference Series: Materials Science and Engineering, 1071, 012029. https://doi.org/10.1088/1757-899X/1071/1/012029
Alrashidi, B., Jamal, A., Khan, I., & Alkhathlan, A. (2022). A review on abusive content automatic detection: approaches, challenges and opportunities. PeerJ Computer Science, 8, e1142. https://doi.org/10.7717/peerj-cs.1142
Baruah, A., Das, K., Barbhuiya, F. & Dey, K. (2020). Context-aware sarcasm detection using BERT. Proceedings of the Second Workshop on Figurative Language Processing, 83–87. https://doi.org/10.18653/v1/2020.figlang-1.12
Bodige, R., Akarapu, R., & Poladi, P. K. (2025). Transformer-based advances in sarcasm detection: A study of contextual models and methodologies. Knowledge and Information Systems, 67, 7399–7430. https://doi.org/10.1007/s10115-025-02469-4
Chen, W., Lin, F., Li, G., & Liu, B. (2024). A survey of automatic sarcasm detection: Fundamental theories, formulation, datasets, detection methods, and opportunities. Neurocomputing, 578, 127428. https://doi.org/10.1016/j.neucom.2024.127428
D’Mello, S. K., & Kory, J. K. (2015). A review and meta-analysis of multimodal affect detection systems. ACM Computing Surveys, 47(3), 1–36. https://doi.org/10.1145/2682899
Deliens, G., Stercq, F., Mary, A., Slama, H., Cleeremans, A., Peigneux, P., & Kissine, M. (2015). Impact of acute sleep deprivation on sarcasm detection. PLoS One, 10(11), e0140527. https://doi.org/10.1371/journal.pone.0140527
Garg M. (2023). Mental health analysis in social media posts: A survey. Archives of Computational Methods in Engineering, 30(3), 1819–1842. https://doi.org/10.1007/s11831-022-09863-z
Gupta, S., & Sandhane, R. (2022). Use of sentiment analysis in social media campaign design and analysis. Cardiometry, 22, 351-363. https://doi.org/10.18137/cardiometry.2022.22.351363
Helal, N. A., Hassan, A., Badr, N. L., & Afify, Y. M. (2024). A contextual-based approach for sarcasm detection. Scientific Reports, 14(1), 15415. https://doi.org/10.1038/s41598-024-65217-8
Ida, S., Kaneko, R., & Murata, K. (2018). SARC-F for screening of sarcopenia among older adults: A meta-analysis of screening test accuracy. Journal of the American Medical Directors Association, 19(8), 685–689. https://doi.org/10.1016/j.jamda.2018.04.001
Kalandadze, T., Norbury, C., Nærland, T., & Næss, K. B. (2018). Figurative language comprehension in individuals with autism spectrum disorder: A meta-analytic review. Autism, 22(2), 99–117. https://doi.org/10.1177/1362361316668652
Kantrowitz, J. T., Hoptman, M. J., Leitman, D. I., Silipo, G., & Javitt, D. C. (2014). The 5% difference: Early sensory processing predicts sarcasm perception in schizophrenia and schizo-affective disorder. Psychological Medicine, 44(1), 25–36. https://doi.org/10.1017/S0033291713000834
Khelifi, L., & Mignotte, M. (2020). Deep learning for change detection in remote sensing images. IEEE Access, 8, 126385–126400. https://doi.org/10.1109/access.2020.3008036
Kim, G., Kang, S. H., Kim, M. Y., & Baik, S. K. (2017). Prognostic value of sarcopenia in patients with liver cirrhosis: A systematic review and meta-analysis. PLoS One, 12(10), e0186990. https://doi.org/10.1371/journal.pone.0186990
Kitaev, N., Kaiser, Ł., & Levskaya, A. (2020). Reformer: The efficient transformer [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2001.04451
Kulkarni, V., Al-Rfou, R., Perozzi, B., & Skiena, S. (2015). Statistically significant detection of linguistic change. Proceedings of the 24th International Conference on World Wide Web (pp. 625–635). Association for Computing Machinery. https://doi.org/10.1145/2736277.2741627
Lee, K., Sidhu, D. M., & Pexman, P. M. (2021). Teaching sarcasm: Evaluating metapragmatic training for typically developing children. Canadian Journal of Experimental Psychology, 75(2), 139–145. https://doi.org/10.1037/cep0000228
Mardani, A., Nilashi, M., Zakuan, N., Loganathan, N., Soheilirad, S., Saman, M. Z., & Ibrahim, O. (2017). A systematic review and meta-analysis of SWARA and WASPAS methods: Theory and applications with recent fuzzy developments. Applied Soft Computing, 57(2017), 265–292. http://doi.org/10.1016/j.asoc.2017.03.045
Nath, D. (2024). Unveiling the impact of Indian government policies using aspect-based sentiment analysis with multi-criteria decision-making and hybrid deep learning. International Journal of Intelligent Systems and Applications in Engineering, 12(22s), 72–82.
Nath, D., & Dwivedi, S. K. (2024a). Aspect category detection with attention mechanism. Proceedings of the 2024 IEEE International Conference on Intelligent Signal Processing and Effective Communication Technologies (INSPECT) (pp. 1–6). IEEE. https://doi.org/10.1109/INSPECT63485.2024.10896198
Nath, D., & Dwivedi, S. K. (2024b). Aspect-based sentiment analysis: Approaches, applications, challenges and trends. Knowledge and Information Systems, 66, 7261–7303. https://doi.org/10.1007/s10115-024-02200-9
Nath, D., & Dwivedi, S. K. (2024c). Transforming aspect-based sentiment analysis to domain-specific mining by integrating a machine learning ensemble (MLE) model. Proceedings of the 2024 International Conference on Signal Processing and Advance Research in Computing (SPARC) (pp. 1–6). IEEE. https://doi.org/10.1109/SPARC61891.2024.10828959
Nath, D., Srivastava, A., Pandey, R. K., Chauhan, M., & Satyarthi, A. (2025). A multi-aspect model for identifying people’s opinion on Indian government policies. AIP Conference Proceedings, 3261, 050011. https://doi.org/10.1063/5.0258608
Ngxande, M., Tapamo, J., & Burke, M. (2017). Driver drowsiness detection using behavioral measures and machine learning techniques: A review of state-of-art techniques. 2017 Pattern Recognition Association of South Africa and Robotics and Mechatronics Conference (pp. 156–161). IEEE. https://doi.org/10.1109/RoboMech.2017.8261140
Olkoniemi, H., & Kaakinen, J. K. (2021). Processing of irony in text: A systematic review of eye-tracking studies. Canadian Journal of Experimental Psychology, 75(2), 99–106. https://doi.org/10.1037/cep0000216
Potamias, R. A., Siolas, G., & Stafylopatis, A. (2020). A transformer-based approach to irony and sarcasm detection. Neural Computing and Applications, 32, 17309–17320. https://doi.org/10.1007/s00521-020-05102-3
Rahgouy, M., Giglou, H. B., Rahgooy, T., & Seals, C. (2022). NULL at SemEval-2022 Task 6: Intended sarcasm detection using stylistically fused contextualized representation and deep learning. Proceedings of the 16th International Workshop on Semantic Evaluation, 862–870. https://doi.org/10.18653/v1/2022.semeval-1.120
Rapp, A. M., Purr, F., & Felsenheimer, A. K. (2018). Sarcasm comprehension as a social cognition measure in schizophrenia - – A systematic literature search and meta-analysis on the use of the TASIT. Schizophrenia Bulletin, 44(Suppl 1), S136. https://doi.org/10.1093/schbul/sby016.334
Sharma, E., Gondhi, N. K., Chaahat, Murugappan, M., Naik, G., & Murugan, L. (2026). Toward effective sarcasm detection in social media: A review of artificial intelligence-based automated approaches. Expert Systems, 43(3), e70203. https://doi.org/10.1111/exsy.70203
Son, L. H., Kumar, A., Sangwan, S. R., Arora, A., Nayyar, A., & Abdel-Basset, M. (2019). Sarcasm detection using soft attention-based bidirectional long short-term memory model with convolution network. IEEE Access, 7, 23319–23328. https://doi.org/10.1109/access.2019.2899260
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 (pp. 39–50). Association for Computational Linguistics. https://doi.org/10.18653/v1/S18-1005
Downloads
Published
How to Cite
Issue
Section
Categories
License
Copyright (c) 2026 Ankur Srivastava, Sifatullah Siddiqi
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
The observations and associated materials published or posted by NeurosciRN are licensed by the authors for use and distribution in accord with the Creative Commons Attribution license CC BY-NC 4.0 international, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
