Probabilistic Syntax-Aware Joint Span–Sentiment Learning for Aspect-Based Sentiment Analysis

Cross-domain aspect-based sentiment analysis using DeBERTaV3 and bio-CRF: a syntactic-aware span extraction approach

The results demonstrate that incorporating explicit syntactic knowledge, adaptive feature fusion, and structured decoding substantially improves cross-domain generalization in fine-grained sentiment analysis.

Large Language Model-Driven Hard Negatives Generation for Contrastive Aspect-Based Sentiment Analysis

While sentiment analysis has advanced significantly, fine-grained sentiment classification such as aspect-based sentiment analysis (ABSA), continues to present challenges. These difficulties primarily stem from data scarcity and the inherent complexities of identifying sentiments specific to different aspects within a text. The recent emergence of generative artificial intelligence (AI), particularly large language models (LLMs), has fundamentally altered the landscape of data management and integration. To better capture nuanced sentiment differences, this paper proposes a novel approach that leverages LLMs to generate “hard negatives” for ABSA. We introduce the sentiment-aware chain-of-thought (SACoT) framework, which emulates a human-like reasoning process to manipulate the sentiment polarity of aspect terms. This is achieved by integrating chain-of-thought (CoT) reasoning with a few-shot prompting strategy, guiding the LLM to produce sentences with the desired sentiment towards specific aspects. Furthermore, we employ an LLM-as-a-Judge framework to refine these generated hard negatives, thereby enhancing their quality for subsequent use in supervised fine-tuning and contrastive learning. Extensive experiments on benchmark datasets demonstrate that our proposed approach, LLM-SCADA (LLM-guided sentiment-context-aspect data augmentation), significantly improves model performance, especially in transitioning from neutral to positive sentiments (NEU → POS). An in-depth ablation study further underscores the distinct contributions of the generated hard negatives, the contrastive learning approach, and the refinement process. These findings highlight the potential of LLMs to create sentiment-shifted samples based on aspect terms, paving the way for more robust and sophisticated techniques in the field of ABSA.

Bayesian Biaffine Variational Graph Convolutional Network for Aspect-Based Sentiment Analysis

Aspect-based sentiment analysis (ABSA) aims to identify the sentiment polarity expressed toward a specific aspect in a sentence. Existing sequential and Transformer-based methods can effectively capture contextual semantics, but they often lack explicit modeling of aspect–opinion relations. Graph-based approaches partially address this limitation by incorporating syntactic dependency structures; however, most rely on deterministic parser-derived graphs or fixed relation weights, which may introduce noisy edges and unstable message propagation for ambiguous, informal, or domain-shifted text. To address these issues, this paper proposes a Bayesian Biaffine Variational Graph Convolutional Network (BBV-GCN) for ABSA. Specifically, a contextual encoder first generates token-level representations for each sentence–aspect pair. A biaffine relation scorer then estimates aspect-aware pairwise token interactions and constructs a soft latent relation graph. Rather than treating relation weights as deterministic values, BBV-GCN introduces latent relation variables and learns their posterior distributions through variational inference, thereby enabling uncertainty-aware graph construction. Based on the learned graph, a variational graph convolutional network performs multi-hop message passing to aggregate opinion cues, modifiers, negation patterns, and contrastive signals toward the target aspect representation. Experiments on five benchmark datasets, including Twitter, Laptop14, Restaurant14, Restaurant15, and Restaurant16, demonstrate that BBV-GCN achieves competitive and well-balanced performance relative to representative attention-based, Transformer-based, and graph-based baselines. Ablation studies further confirm the contributions of Bayesian relation modeling, KL regularization, and variational graph propagation. Visualization results illustrate how uncertainty-aware weighting can attenuate spurious relations and produce more interpretable aspect-specific latent graphs. Overall, BBV-GCN provides a robust and uncertainty-aware graph reasoning framework for fine-grained sentiment analysis.

HyGST: a graph-integration enhanced generative framework for end-to-end aspect-based sentiment analysis

Mitigating unreliable syntactic dependencies in aspect-based sentiment analysis via sentiment-aware graph anomaly detection and mix convolution.

A sentiment-aware graph anomaly detection framework that integrates graph anomaly detection with a sentiment consistency evaluation mechanism to eliminate misleading dependencies and preserve key sentiment information from the original graph and can be seamlessly incorporated into other graph-based ABSA models to enhance performance and robustness.

A Lightweight DistilBERT-Attention Model for Aspect-Based Sentiment Analysis

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.