Aug 2026· Information· Vol 17, pp. 761· 0 citations· 32 references
TL;DR
QMPN, Quality-Aware Memory Prompting Network, is proposed, that stores sample-specific prompts derived from a small support set, retrieves relevant prompting evidence for each query, and uses the retrieved prompts to guide aspect-aware context generation.
Abstract
Multimodal aspect-based sentiment analysis (MABSA) predicts the sentiment polarity associated with a specified aspect by jointly exploiting textual and visual information. Existing models may be sensitive to limited prompting examples, cross-modal noise, and unreliable generated context. This paper proposes QMPN, Quality-Aware Memory Prompting Network, that stores sample-specific prompts derived from a small support set, retrieves relevant prompting evidence for each query, and uses the retrieved prompts to guide aspect-aware context generation. A task-oriented quality gate, learned indirectly through the sentiment classification objective, controls the contribution of the generated context to the final prediction. Under the fixed protocol used in this study, QMPN employs 50 labeled support instances for prompt-memory construction and achieves 78.6% accuracy and 74.8% macro-F1 on Twitter-2015, and 72.0% accuracy and 70.5% macro-F1 on Twitter-2017. Relative to the variant without context generation, the complete model improves accuracy/macro-F1 by 3.31/2.83 percentage points on Twitter-2015 and 3.84/3.22 percentage points on Twitter-2017. Ablation and parameter analyses further show the contributions of memory retrieval, adaptive prompt selection, context generation, and quality-aware fusion. Because the evaluation is limited to two historical Twitter benchmarks and a single fixed seed, the reported results should be interpreted within this experimental scope rather than as evidence of universal cross-domain generalization.
Multimodal aspect-based sentiment analysis (MABSA) predicts the sentiment expressed toward a target aspect by jointly using textual and visual information, supporting fine-grained opinion analysis in product reviews, brand monitoring, and customer feedback. However, existing approaches remain sensitive to irrelevant visual regions, weak text–image alignment, and limited use of external knowledge. Motivated by these challenges, this study systematically evaluated two text-only large language models and four open-weight large vision-language models for aspect-level sentiment classification. The open-weight models were adapted using 4-bit quantized low-rank adaptation, while GPT-4o was assessed under zero-shot, one-shot, and five-shot in-context learning without parameter updates. Experiments were conducted on Twitter-2015, Twitter-2017, and the seven-domain MASAD dataset and evaluated using accuracy and macro-F1. Among the evaluated multimodal models, Qwen3-VL-8B-Instruct achieves the strongest performance, reaching 83.22% accuracy and 81.72% macro-F1 on Twitter-2015, 79.50% and 78.93% on Twitter-2017, and up to 99.84% and 99.83% in the Plant domain of MASAD. From a symmetry perspective, semantically aligned text–image–aspect inputs provide consistent cross-modal evidence, whereas shuffled images introduce asymmetric, symmetry-breaking information. The resulting performance degradation under shuffled-image ablation indicates that reliable aspect-level sentiment prediction depends on preserving cross-modal semantic correspondence. These findings demonstrate the effectiveness of parameter-efficient LVLM adaptation for MABSA.
Ismail Ifakir, E. Nfaoui, Abderrahim Zannou· Symmetry· 0 citations
This work suggests an improved prompt-based multi-modal sentiment analysis (IPMMSA) strategy that incorporates multi-view and diversified knowledge augmentation that yields robust and expressive multimodal embedding’s to boost aspect-based sentiment analysis performance during multimodal integration with multi-modal fashion dataset.
M. Yuvaraja, C. Kumuthini· International journal of com...· 0 citations
This work proposes LLM-Augmented Prompt Learning for Multimodal Sentiment Analysis with Reward Adaptation (LAPM-RA), a unified framework integrating LLM-based sentiment-aware augmentation, reward-guided prompt selection, and context-aware multimodal fusion.
This paper introduces an efficient DistilBERT-Attention model for aspect-based sentiment analysis (ABSA), designed to balance classification accuracy against computational cost. Unlike general sentiment analysis, which assigns a single polarity to a complete review, ABSA identifies the product aspects discussed within individual sentences or clauses, such as design, quality, and price, and determines the sentiment polarity expressed toward each of them. The proposed model combines DistilBERT, a compact transformer encoder, with a modified aspect-focused attention layer that captures fine-grained sentiment signals efficiently. Experiments were conducted on 3,152 valid textual reviews, drawn from an initial collection of 3,259 Amazon India reviews of Titan watches published in 2024, across five aspect categories: design, quality, price, functionality, and comfort. The proposed model achieved an accuracy of 84.7% and an F1-score of 0.81. Compared with traditional baselines, it improved accuracy by 13.5 percentage points over a support vector machine and by 13.9 percentage points over logistic regression. Although BERT-base achieved a slightly higher accuracy of 86.1%, the proposed model retained approximately 98.4% of BERT-base accuracy while reducing memory consumption by about 40% and lowering relative processing time from 2.5x to 1.5x. The main contribution of the proposed model is therefore not absolute superiority over large transformer models, but an improved balance between accuracy, interpretability, and computational efficiency for resource-constrained ABSA applications.
Mohammad Abu Kausar, M. Nasar, Sallam O. f. Khairy et al.· Journal of Computers, Mechan...· 0 citations
This work proposes the SENSE model, a confidence-aware soft sentiment assignment and a sentiment exchange mechanism to quantify fine-grained preferences and explicitly model sentiment interaction, and employs a confidence-aware soft sentiment assignment and a sentiment exchange mechanism to quantify fine-grained preferences and explicitly model sentiment interaction.
Ying-Jie Chen, Xiang Li, Dong Chen et al.· 0 citations
This paper presents a framework that preserves semantics in LLM-based opinion summarization while minimizing token usage and computational cost and demonstrates that this method significantly reduces token usage and computational cost while consistently outperforming traditional AI-based and standard LLM summarization baselines in terms of content coverage, balance, and semantic preservation.
