Multimodal Aspect-Based Sentiment Analysis for Vietnamese Reviews using Learnable Aspect Queries

Sneha Kaware; Rajeshri Shelke; Poonam Manjare

doi:10.35377/saucis...1951015

Multimodal Aspect-Based Sentiment Analysis for Vietnamese Reviews using Learnable Aspect Queries

Abstract

The field of Multimodal Aspect-Based Sentiment Analysis (MABSA) has attracted considerable interest due to its unique ability to jointly leverage both textual and visual modalities for better aspect-level sentiment prediction. Nonetheless, there is no consideration of the dependence on particular modalities in practical application, especially when textual information is vague or missing in the data. Such cases are typical in many areas, including hotel reviews and e-commerce, where people use multimodal data to express their opinions. In this study, we introduce an aspect-centric MABSA approach that combines a transformer-based text encoder (PhoBERT) with a Vision Transformer (ViT) in a single end-to-end system. To enable fine-grained interaction between modalities, we apply aspect queries that dynamically attend to modality-dependent features, implicitly aligning them to obtain aspect-related information. Additionally, our model is tested under uncertainty in textual content by applying several text masking methods, including random token-level masking, sentiment-based masking, and evaluation-time gating. Experimental results on the ViMACSA dataset showed promising results, with a Macro-F1 score of 0.87. Additionally, we perform experiments by ablating modality, assessing aspects individually, analyzing robustness to noisy inputs, and comparing against current multimodal architectures. Results suggest that the proposed approach achieves competitive performance compared with current methods, especially for aspects based on visual grounds.

Keywords

References

Q. H. Nguyen, M.-V. T. Nguyen, and K. Van Nguyen, “New benchmark dataset and fine-grained cross-modal fusion framework for Vietnamese multimodal aspect-category sentiment analysis,” Multimedia Systems, vol. 31, no. 1, p. 4, 2025, doi: 10.1007/s00530-024-01558-8.
S. R. Kaware, R. R. Shelke, and P. A. Manjare, “Enhancing sentiment prediction with AI: A comparative evaluation of unimodal vs. multimodal approaches,” in Proceedings of the 2025 8th Artificial Intelligence and Cloud Computing Conference, 2025, pp. 103–110, doi: 10.1145/3789982.3789996.
K. Van Nguyen, V. D. Nguyen, P. X. Nguyen, T. T. Truong, and N. L.-T. Nguyen, “UIT-VSFC: Vietnamese students’ feedback corpus for sentiment analysis,” in 2018 10th International Conference on Knowledge and Systems Engineering (KSE). IEEE, 2018, pp. 19–24, doi: 10.1109/KSE.2018.8573337.
V. A. Ho et al., “Emotion recognition for Vietnamese social media text,” in Computational Linguistics—16th International Conference of the Pacific Association for Computational Linguistics, PACLING 2019, Revised Selected Papers, ser. Communications in Computer and Information Science, vol. 1215. Springer Singapore, 2020, pp. 319–333, doi: 10.1007/978-981-15-6168-9_27.
T. A. Tran, J. Duangsuwan, and W. Wettayaprasit, “Automatic aspect-based sentiment summarization for visual, structured, and textual summaries,” ECTI Transactions on Computer and Information Technology (ECTI-CIT), vol. 15, no. 1, pp. 50–72, 2021, doi: 10.37936/ecti-cit.2021151.237565.
L. Luc Phan et al., “SA2SL: From aspect-based sentiment analysis to social listening system for business intelligence,” in International Conference on Knowledge Science, Engineering and Management. Springer, 2021, pp. 647–658, doi: 10.1007/978-3-030-82147-0_53.
L. Zhu, M. Xu, Y. Bao, Y. Xu, and X. Kong, “Deep learning for aspect-based sentiment analysis: a review,” PeerJ Computer Science, vol. 8, p. e1044, 2022, doi: 10.7717/peerj-cs.1044.
S. Alyami, A. Alhothali, and A. Jamal, “Systematic literature review of Arabic aspect-based sentiment analysis,” Journal of King Saud University-Computer and Information Sciences, vol. 34, no. 9, pp. 6524–6551, 2022, doi: 10.1016/j.jksuci.2022.07.001.

J. Tian, W. Slamu, M. Xu, C. Xu, and X. Wang, “Research on aspect-level sentiment analysis based on text comments,” Symmetry, vol. 14, no. 5, p. 1072, 2022, doi: 10.3390/sym14051072.
K. Ahmed et al., “Breaking down linguistic complexities: A structured approach to aspect-based sentiment analysis,” Journal of King Saud University- Computer and Information Sciences, vol. 35, no. 8, p. 101651, 2023, doi: 10.1016/j.jksuci.2023.101651.
S. Gupta et al., “Aspect based feature extraction in sentiment analysis using Bi-GRU-LSTM model,” Journal of Mobile Multimedia, vol. 20, no. 4, pp. 935–960, 2024, doi: 10.13052/jmm1550-4646.2048.
A. Chauhan, A. Sharma, and R. Mohana, “An enhanced aspect-based sentiment analysis model based on RoBERTa for text sentiment analysis,” Informatica, vol. 49, no. 14, pp. 193–202, 2025, doi: 10.31449/inf.v49i14.5423.
A. Irumporai and G. Anitha, “Knowledge-enhanced BERT for aspect-based sentiment analysis of tourism destinations using social media data,” Engineering, Technology & Applied Science Research, vol. 15, no. 6, pp. 30 097–30 102, 2025, doi: 10.48084/etasr.13139.
N. A. Fauzan, “A zero-shot aspect-based sentiment analysis of public perception toward AI chatbots,” TIERS Information Technology Journal, vol. 6, no. 1, pp. 97–111, 2025, doi: 10.38043/tiers.v6i1.6488.
W. Kwon, “Aspect-based sentiment analysis through zero-shot text classification and impact-asymmetry analysis,” International Journal of Hospitality Management, vol. 133, p. 104397, 2026, doi: 10.1016/j.ijhm.2025.104397.
R. V. Santin and S. O. Rezende, “Systematic review on aspect-based sentiment analysis in cross-domain,” Artificial Intelligence Review, vol. 59, no. 1, p. 37, 2026, doi: 10.1007/s10462-025-11437-x.
J. Zhou, J. Zhao, J. X. Huang, Q. V. Hu, and L. He, “MASAD: A large-scale dataset for multimodal aspect-based sentiment analysis,” Neurocomputing, vol. 455, pp. 47–58, 2021, doi: 10.1016/j.neucom.2021.05.040.
G. Kontonatsios et al., “FABSA: An aspect-based sentiment analysis dataset of user reviews,” Neurocomputing, vol. 562, p. 126867, 2023, doi: 10.1016/j.neucom.2023.126867.
R. Zhou, W. Guo, X. Liu, S. Yu, Y. Zhang, and X. Yuan, “AoM: Detecting aspect-oriented information for multimodal aspect-based sentiment analysis,” in Findings of the Association for Computational Linguistics: ACL 2023, 2023, pp. 8184–8196, doi: 10.18653/v1/2023.findings-acl.519.
S. Lai, X. Hu, H. Xu, Z. Ren, and Z. Liu, “Multimodal sentiment analysis: A survey,” Displays, vol. 80, p. 102563, 2023, doi: 10.1016/j.displa.2023.102563.
A. Gandhi, K. Adhvaryu, and V. Khanduja, “Multimodal sentiment analysis: review, application domains and future directions,” in 2021 IEEE Pune Section International Conference (PuneCon). IEEE, 2021, pp. 1–5, doi: 10.1109/PuneCon52575.2021.9686504.
S. Patel, N. Shroff, and H. Shah, “Multimodal sentiment analysis using deep learning: a review,” in International Conference on Advancements in Smart Computing and Information Security. Springer, 2024, pp. 13–29, doi: 10.1007/978-3-031-59097-9_2.
H. Zhao, M. Yang, X. Bai, and H. Liu, “A survey on multimodal aspect-based sentiment analysis,” IEEE Access, vol. 12, pp. 12 039–12 052, 2024, doi: 10.1109/ACCESS.2024.3354844.
M. A. M. Halim, N. Zainuddin, K. A. F. A. Samah, M. Mohamad, and A. Selamat, “Fusion in multimodal sentiment analysis: A review of approaches and challenges,” in International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems. Springer, 2025, pp. 355–366, doi: 10.1007/978-981-96-8892-0_30.
L. Zhu, H. Sun, Q. Gao, Y. Liu, and L. He, “Aspect enhancement and text simplification in multimodal aspect-based sentiment analysis for multi- aspect and multi-sentiment scenarios,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, no. 2, 2025, pp. 1683–1691, doi: 10.1609/aaai.v39i2.32161.
J. Liu, Z. Liu, Z. Cen, Y. Zhou, Y. Zou, W. Zhang, H. Jiang, and T. Ruan, “Can multimodal large language models understand spatial relations?” in Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025, pp. 620–632, doi: 10.18653/v1/2025.acl- long.31.
M. L. Fujimoto, R. M. Marcacini, and S. O. Rezende, “Scoping review of multimodal sentiment analysis and summarization: State of the art, challenges and future directions,” Information Fusion, vol. 130, p. 104082, 2026, doi: 10.1016/j.inffus.2025.104082.
Y. Weng et al., “MIECF: Multi-faceted information extraction and cross-mixture fusion for multimodal aspect-based sentiment analysis,” Heliyon, vol. 10, no. 12, p. e32967, 2024, doi: 10.1016/j.heliyon.2024.e32967.
Y. Kong, “A multimodal sentiment classification study based on Mvsa-Single dataset,” ITM Web of Conferences, vol. 78, p. 04015, 2025, doi: 10.1051/itm- conf/20257804015.
H.-Q. Dang, D.-D.-A. Nguyen, and T.-H. Do, “Multi-task solution for aspect category sentiment analysis on Vietnamese datasets,” in 2022 IEEE International Conference on Cybernetics and Computational Intelligence (CyberneticsCom), 2022, pp. 404–409, doi: 10.1109/CyberneticsCom55287.2022.9865479.
H. N. Do and D. T. Pham, “ViMACSA-GAT: A graph attention network-based Vietnamese multimodal sentiment analysis model with cross-modal fusion,” VNU Journal of Science: Computer Science and Communication Engineering, vol. 42, no. 1, pp. 12–22, 2026, doi: 10.25073/2588-1086/vnucsce.6927.

Details

Primary Language

English

Subjects

Computer Software, Software Architecture

Journal Section

Research Article

Authors

Sneha Kaware ^*
India

Rajeshri Shelke
0000-0002-1023-8261
India

Poonam Manjare
0009-0007-9246-9998
India

Early Pub Date

October 28, 2026

Publication Date

October 30, 2026

Submission Date

May 14, 2026

Acceptance Date

August 27, 2026

Published in Issue

Year 2026 Volume: 9 Number: 5

DOI

https://doi.org/10.35377/saucis...1951015

IZ

https://izlik.org/JA45BG27BY

Cite

RIS / Bibtex

APA

Kaware, S., Shelke, R., & Manjare, P. (2026). Multimodal Aspect-Based Sentiment Analysis for Vietnamese Reviews using Learnable Aspect Queries. Sakarya University Journal of Computer and Information Sciences, 9(5), 1581-1596. https://doi.org/10.35377/saucis...1951015

AMA

1.Kaware S, Shelke R, Manjare P. Multimodal Aspect-Based Sentiment Analysis for Vietnamese Reviews using Learnable Aspect Queries. SAUCIS. 2026;9(5):1581-1596. doi:10.35377/saucis.1951015

Chicago

Kaware, Sneha, Rajeshri Shelke, and Poonam Manjare. 2026. “Multimodal Aspect-Based Sentiment Analysis for Vietnamese Reviews Using Learnable Aspect Queries”. Sakarya University Journal of Computer and Information Sciences 9 (5): 1581-96. https://doi.org/10.35377/saucis. 1951015.

EndNote

Kaware S, Shelke R, Manjare P (October 1, 2026) Multimodal Aspect-Based Sentiment Analysis for Vietnamese Reviews using Learnable Aspect Queries. Sakarya University Journal of Computer and Information Sciences 9 5 1581–1596.

IEEE

[1]S. Kaware, R. Shelke, and P. Manjare, “Multimodal Aspect-Based Sentiment Analysis for Vietnamese Reviews using Learnable Aspect Queries”, SAUCIS, vol. 9, no. 5, pp. 1581–1596, Oct. 2026, doi: 10.35377/saucis...1951015.

ISNAD

Kaware, Sneha - Shelke, Rajeshri - Manjare, Poonam. “Multimodal Aspect-Based Sentiment Analysis for Vietnamese Reviews Using Learnable Aspect Queries”. Sakarya University Journal of Computer and Information Sciences 9/5 (October 1, 2026): 1581-1596. https://doi.org/10.35377/saucis. 1951015.

JAMA

1.Kaware S, Shelke R, Manjare P. Multimodal Aspect-Based Sentiment Analysis for Vietnamese Reviews using Learnable Aspect Queries. SAUCIS. 2026;9:1581–1596.

MLA

Kaware, Sneha, et al. “Multimodal Aspect-Based Sentiment Analysis for Vietnamese Reviews Using Learnable Aspect Queries”. Sakarya University Journal of Computer and Information Sciences, vol. 9, no. 5, Oct. 2026, pp. 1581-96, doi:10.35377/saucis. 1951015.

Vancouver

1.Sneha Kaware, Rajeshri Shelke, Poonam Manjare. Multimodal Aspect-Based Sentiment Analysis for Vietnamese Reviews using Learnable Aspect Queries. SAUCIS. 2026 Oct. 1;9(5):1581-96. doi:10.35377/saucis. 1951015