# Semantic-preserved Augmentation with Confidence-weighted Fine-tuning for Aspect Category Sentiment Analysis

arXiv: https://arxiv.org/abs/2506.07148 · HTML: https://mlsanity.com/paper/2506.07148/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 34 references that are in the map.
- First posted on arXiv 8 Jun 2025.

## Builds on (most cited first, 20 of 20)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [MvP: Multi-view Prompting Improves Aspect Sentiment Tuple Prediction](https://mlsanity.com/paper/2305.12627/) (2023)
- [Text Data Augmentation for Large Language Models: A Comprehensive Survey of Methods, Challenges, and Opportunities](https://mlsanity.com/paper/2501.18845/) (2025)
- [Solving Aspect Category Sentiment Analysis as a Text Generation Task](https://mlsanity.com/paper/2110.07310/) (2021)
- [Joint Aspect and Polarity Classification for Aspect-based Sentiment Analysis with End-to-End Neural Networks](https://mlsanity.com/paper/1808.09238/) (2018)
- [Multi-Instance Multi-Label Learning Networks for Aspect-Category Sentiment Analysis](https://mlsanity.com/paper/2010.02656/) (2020)
- [MER 2025: When Affective Computing Meets Large Language Models](https://mlsanity.com/paper/2504.19423/) (2025)
- [RVISA: Reasoning and Verification for Implicit Sentiment Analysis](https://mlsanity.com/paper/2407.02340/) (2024)
- [Context-aware Embedding for Targeted Aspect-based Sentiment Analysis](https://mlsanity.com/paper/1906.06945/) (2019)
- [Sentence Constituent-Aware Aspect-Category Sentiment Analysis with Graph Attention Networks](https://mlsanity.com/paper/2010.01461/) (2020)
- [Exploring Cognitive and Aesthetic Causality for Multimodal Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2504.15848/) (2025)
- [Enhanced Coherence-Aware Network with Hierarchical Disentanglement for Aspect-Category Sentiment Analysis](https://mlsanity.com/paper/2403.10214/) (2024)
- [Semantically Consistent Data Augmentation for Neural Machine Translation via Conditional Masked Language Model](https://mlsanity.com/paper/2209.10875/) (2022)
- [DS2-ABSA: Dual-Stream Data Synthesis with Label Refinement for Few-Shot Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2412.14849/) (2024)

## Abstract (arXiv)

Large language model (LLM) is an effective approach to addressing data scarcity in low-resource scenarios. Recent existing research designs hand-crafted prompts to guide LLM for data augmentation. We introduce a data augmentation strategy for the aspect category sentiment analysis (ACSA) task that preserves the original sentence semantics and has linguistic diversity, specifically by providing a structured prompt template for an LLM to generate predefined content. In addition, we employ a post-processing technique to further ensure semantic consistency between the generated sentence and the original sentence. The augmented data increases the semantic coverage of the training distribution, enabling the model better to understand the relationship between aspect categories and sentiment polarities, enhancing its inference capabilities. Furthermore, we propose a confidence-weighted fine-tuning strategy to encourage the model to generate more confident and accurate sentiment polarity predictions. Compared with powerful and recent works, our method consistently achieves the best performance on four benchmark datasets over all baselines.