This paper proposes a noise-aware multi-task transformer framework that jointly performs aspect extraction (AE) and aspect sentiment classification (ASC) using a shared BERT/RoBERTa encoder with dual task-specific heads. Robustness is promoted through a systematic noise-aware training (NAT) strategy that injects controlled synthetic perturbations (spelling errors, word dropout, synonym replacement, slang) according to a curriculum schedule, mixing clean and noisy instances in each batch. Experiments on SemEval-2014 (Restaurants, Laptops) and large-scale Amazon (Electronics, Apparel) and Yelp (Food) reviews demonstrate consistent gains over strong single-task, multi-task, and cross-domain baselines in in-domain, cross-domain, and multi-domain settings. On the SemEval Rest 14 dataset, the proposed model achieves improvements of +2.6 F1 (AE) and +2.9% accuracy (ASC) on the Rest14 benchmark over the strongest baseline. with maximum gains of +3.1 F1 (AE) and +3.3% (ASC) over the strongest cross-domain baseline (BGCA), reduces noise-induced performance degradation by up to 42% (NAT contribution vs. identical model without NAT), and improves cross-domain transfer with minimal additional parameters and a 22% training-time overhead. Ablation and error analyses show that multi-task learning and NAT are both critical to robustness, particularly under high noise and domain shift. These findings indicate that jointly learning multiple ABSA subtasks with noise-aware augmentation is an effective and efficient route to deployable, real-world ABSA systems.
References
[1]
Li, C., Tang, H., Zhang, J., Guo, X., Cheng, D. and Morimoto, Y. (2024) Advancing Aspect-Based Sentiment Analysis through Deep Learning Models. In: Lecture Notes in Computer Science, Springer, 228-242. https://doi.org/10.1007/978-981-96-0847-8_16
[2]
Zhang, W., Li, X., Deng, Y., Bing, L. and Lam, W. (2023) A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challenges. IEEE Transactions on Knowledge and Data Engineering, 35, 11019-11038. https://doi.org/10.1109/tkde.2022.3230975
[3]
Liu, N. and Zhao, J. (2022) A Bert-Based Aspect-Level Sentiment Analysis Algorithm for Cross-Domain Text. Computational Intelligence and Neuroscience, 2022, 1-11. https://doi.org/10.1155/2022/8726621
[4]
Nazir, A., Rao, Y., Wu, L. and Sun, L. (2022) Issues and Challenges of Aspect-Based Sentiment Analysis: A Comprehensive Survey. IEEE Transactions on Affective Computing, 13, 845-863. https://doi.org/10.1109/taffc.2020.2970399
[5]
Schouten, K. and Frasincar, F. (2016) Survey on Aspect-Level Sentiment Analysis. IEEE Transactions on Knowledge and Data Engineering, 28, 813-830. https://doi.org/10.1109/tkde.2015.2485209
[6]
Dubey, G., Chadha, A., Jyoti, A., Raj, G., Kaur, K. and Dubey, A.K. (2025) Contextualized Cross-Domain Aspect Sentiment Transformer: A Fine-Grained Aspect-Centric Approach for Enhanced Context-Aware Sentiment Analysis. Computational Intelligence, 41, e70081. https://doi.org/10.1111/coin.70081
[7]
Yu, J., Zhao, Q. and Xia, R. (2023) Cross-Domain Data Augmentation with Domain-Adaptive Language Modeling for Aspect-Based Sentiment Analysis. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Toronto, July 2023, 1456-1470. https://doi.org/10.18653/v1/2023.acl-long.81
[8]
Chen, C., Teng, Z., Wang, Z. and Zhang, Y. (2022) Discrete Opinion Tree Induction for Aspect-Based Sentiment Analysis. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Dublin, May 2022, 2051-2064. https://doi.org/10.18653/v1/2022.acl-long.145
[9]
Pontiki, M., Galanis, D., Pavlopoulos, J., et al. (2014) SemEval 2014 Task 4: Aspect Based Sentiment Analysis. Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014) at (COLING 2014), Dublin, August 2014, 27-35. http://www.aclweb.org/anthology/S14-2004
[10]
McAuley, J., Targett, C., Shi, Q. and van den Hengel, A. (2015). Image-Based Recommendations on Styles and Substitutes. Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval, Santiago, 9-13 August 2015, 43-52. https://doi.org/10.1145/2766462.2767755
[11]
Yelp. Yelp Open Dataset. https://business.yelp.com/data/resources/open-dataset/
[12]
Wu, C., Ma, B., Zhang, Z., Deng, N., He, Y. and Xue, Y. (2025) Evaluating Zero-Shot Multilingual Aspect-Based Sentiment Analysis with Large Language Models. International Journal of Machine Learning and Cybernetics, 16, 8079-8101. https://doi.org/10.1007/s13042-025-02711-z
[13]
Yang, L., Na, J. and Yu, J. (2022) Cross-Modal Multitask Transformer for End-To-End Multimodal Aspect-Based Sentiment Analysis. Information Processing & Management, 59, Article 103038. https://doi.org/10.1016/j.ipm.2022.103038
[14]
He, Z., Wang, H. and Zhang, X. (2023) Multi-Task Learning Model Based on BERT and Knowledge Graph for Aspect-Based Sentiment Analysis. Electronics, 12, Article 737. https://doi.org/10.3390/electronics12030737
[15]
Fadel, A., Saleh, M., Salama, R. and Abulnaja, O. (2024) MTL-AraBERT: An Enhanced Multi-Task Learning Model for Arabic Aspect-Based Sentiment Analysis. Computers, 13, 98. https://doi.org/10.3390/computers13040098
[16]
Alshuwaier, F., Areshey, A. and Poon, J. (2022) Applications and Enhancement of Document-Based Sentiment Analysis in Deep Learning Methods: Systematic Literature Review. Intelligent Systems with Applications, 15, Article 200090. https://doi.org/10.1016/j.iswa.2022.200090
[17]
Labeed, Q. and Liang, X. (2024) Multi-Task Learning Transformers: Comparative Analysis for Emotion Classification and Intensity Prediction in Social Media. 2024 14th International Conference on Pattern Recognition Systems (ICPRS), London, 15-18 July 2024, 1-7. https://doi.org/10.1109/icprs62101.2024.10677817
[18]
Aziz, K., Ji, D., Chakrabarti, P., Chakrabarti, T., Iqbal, M.S. and Abbasi, R. (2024) Unifying Aspect-Based Sentiment Analysis BERT and Multi-Layered Graph Convolutional Networks for Comprehensive Sentiment Dissection. Scientific Reports, 14, Article No. 14646. https://doi.org/10.1038/s41598-024-61886-7
[19]
Zhou, Y., Zhu, F., Song, P., Han, J., Guo, T. and Hu, S. (2021) An Adaptive Hybrid Framework for Cross-Domain Aspect-Based Sentiment Analysis. Proceedings of the AAAI Conference on Artificial Intelligence, 35, 14630-14637. https://doi.org/10.1609/aaai.v35i16.17719
[20]
Deng, Y., Zhang, W., Pan, S.J. and Bing, L. (2023) Bidirectional Generative Framework for Cross-Domain Aspect-Based Sentiment Analysis. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Toronto, July 2023, 12272-12285. https://doi.org/10.18653/v1/2023.acl-long.686
[21]
Zou, H. and Wang, Y. (2025) Large Language Model Augmented Syntax-Aware Domain Adaptation Method for Aspect-Based Sentiment Analysis. Neurocomputing, 625, Article 129472. https://doi.org/10.1016/j.neucom.2025.129472
[22]
Wei, J. and Zou, K. (2019) EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, November 2019, 6382-6388. https://doi.org/10.18653/v1/d19-1670
[23]
Xie, Q., Dai, Z., Hovy, E., Luong, M.T. and Le, Q.V. (2020) Unsupervised Data Augmentation for Consistency Training. Proceedings of the 34th International Conference on Neural Information Processing Systems, Vancouver 6-12 December 2020, 6256-6268.
[24]
Zhuang, S., Shou, L., Pei, J., Gong, M., Ren, H., Zuccon, G., et al. (2023) Typos-Aware Bottlenecked Pre-Training for Robust Dense Retrieval. Proceedings of the Annual International ACM SIGIR Conference on Research and Development in Information Retrieval in the Asia Pacific Region, Beijing, 26-28 November 2023, 212-222. https://doi.org/10.1145/3624918.3625324
[25]
Bashiri, H. and Naderi, H. (2024) Comprehensive Review and Comparative Analysis of Transformer Models in Sentiment Analysis. Knowledge and Information Systems, 66, 7305-7361. https://doi.org/10.1007/s10115-024-02214-3
[26]
Wang, H., Li, X., Ren, Z., Wang, M. and Ma, C. (2023) Multimodal Sentiment Analysis Representations Learning via Contrastive Learning with Condense Attention Fusion. Sensors, 23, Article 2679. https://doi.org/10.3390/s23052679
[27]
Yan, H., Dai, J., Ji, T., Qiu, X. and Zhang, Z. (2021) A Unified Generative Framework for Aspect-Based Sentiment Analysis. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), Online, August 2021, 2416-2429. https://doi.org/10.18653/v1/2021.acl-long.188
[28]
Wang, Z., Xia, R. and Yu, J. (2022) Unified ABSA: A Unified ABSA Framework Based on Multi-Task Instruction Tuning.
[29]
Fei, H., Li, F., Li, C., Wu, S., Li, J. and Ji, D. (2022) Inheriting the Wisdom of Predecessors: A Multiplex Cascade Framework for Unified Aspect-Based Sentiment Analysis. Proceedings of the 31st International Joint Conference on Artificial Intelligence, Vienna, 23-29 July 2022, 4096-4103. https://doi.org/10.24963/ijcai.2022/572
[30]
Liu, X.Y., Ding, Y., An, K.K., Xiao, C.Y., et al. (2023) Towards Robust Aspect-Based Sentiment Analysis through Non-Counterfactual Augmentations.
[31]
Wilson, S., Magdy, W., McGillivray, B., Garimella, K. and Tyson, G. (2020) Urban Dictionary Embeddings for Slang NLP Applications.
