# On the Robustness of Aspect-based Sentiment Analysis: Rethinking Model, Data, and Training

arXiv: https://arxiv.org/abs/2304.09563 · HTML: https://mlsanity.com/paper/2304.09563/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 86 references that are in the map.
- First posted on arXiv 19 Apr 2023.

## Builds on (most cited first, 30 of 38)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Contrastive Multiview Coding](https://mlsanity.com/paper/1906.05849/) (2019)
- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [Deep Graph Infomax](https://mlsanity.com/paper/1809.10341/) (2018)
- [Adversarial Examples for Evaluating Reading Comprehension Systems](https://mlsanity.com/paper/1707.07328/) (2017)
- [Memory Networks](https://mlsanity.com/paper/1410.3916/) (2014)
- [Deep Biaffine Attention for Neural Dependency Parsing](https://mlsanity.com/paper/1611.01734/) (2016)
- [On Mutual Information Maximization for Representation Learning](https://mlsanity.com/paper/1907.13625/) (2019)
- [Synthetic and Natural Noise Both Break Neural Machine Translation](https://mlsanity.com/paper/1711.02173/) (2017)
- [BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis](https://mlsanity.com/paper/1904.02232/) (2019)
- [Relational Graph Attention Network for Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2004.12362/) (2020)
- [The Effect of Natural Distribution Shift on Question Answering Models](https://mlsanity.com/paper/2004.14444/) (2020)
- [OpenAttack: An Open-source Textual Adversarial Attack Toolkit](https://mlsanity.com/paper/2009.09191/) (2020)
- [Effective LSTMs for Target-Dependent Sentiment Classification](https://mlsanity.com/paper/1512.01100/) (2015)
- [Aspect Level Sentiment Classification with Deep Memory Network](https://mlsanity.com/paper/1605.08900/) (2016)
- [Aspect Based Sentiment Analysis with Gated Convolutional Networks](https://mlsanity.com/paper/1805.07043/) (2018)
- [Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks](https://mlsanity.com/paper/1909.03477/) (2019)
- [RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet Extraction](https://mlsanity.com/paper/2203.09101/) (2022)
- [Cross-Lingual Semantic Role Labeling with High-Quality Translated Training Corpus](https://mlsanity.com/paper/2004.06295/) (2020)
- [Transformation Networks for Target-Oriented Sentiment Classification](https://mlsanity.com/paper/1805.01086/) (2018)
- [TextAttack: A Framework for Adversarial Attacks, Data Augmentation, and Adversarial Training in NLP](https://mlsanity.com/paper/2005.05909/) (2020)
- [Syntax-Aware Aspect Level Sentiment Classification with Graph Attention Networks](https://mlsanity.com/paper/1909.02606/) (2019)
- [Learn from Syntax: Improving Pair-wise Aspect and Opinion Terms Extractionwith Rich Syntactic Knowledge](https://mlsanity.com/paper/2105.02520/) (2021)
- [Adversarial Training for Aspect-Based Sentiment Analysis with BERT](https://mlsanity.com/paper/2001.11316/) (2020)
- [Aspect Level Sentiment Classification with Attention-over-Attention Neural Networks](https://mlsanity.com/paper/1804.06536/) (2018)
- [Retrofitting Structure-aware Transformer Language Model for End Tasks](https://mlsanity.com/paper/2009.07408/) (2020)

## Built on by (most cited first, 20 of 20)

- [Reasoning Implicit Sentiment with Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.11255/) (2023)
- [Information Screening whilst Exploiting! Multimodal Relation Extraction with Feature Denoising and Multimodal Topic Modeling](https://mlsanity.com/paper/2305.11719/) (2023)
- [Generating Visual Spatial Description via Holistic 3D Scene Understanding](https://mlsanity.com/paper/2305.11768/) (2023)
- [Cross2StrA: Unpaired Cross-lingual Image Captioning with Cross-lingual Cross-modal Structure-pivoted Alignment](https://mlsanity.com/paper/2305.12260/) (2023)
- [Constructing Holistic Spatio-Temporal Scene Graph for Video Semantic Role Labeling](https://mlsanity.com/paper/2308.05081/) (2023)
- [Revisiting Disentanglement and Fusion on Modality and Context in Conversational Multimodal Emotion Recognition](https://mlsanity.com/paper/2308.04502/) (2023)
- [A Systematic Review of Aspect-based Sentiment Analysis: Domains, Methods, and Trends](https://mlsanity.com/paper/2311.10777/) (2023)
- [Constructing Code-mixed Universal Dependency Forest for Unbiased Cross-lingual Relation Extraction](https://mlsanity.com/paper/2305.12258/) (2023)
- [EduRABSA: An Education Review Dataset for Aspect-based Sentiment Analysis Tasks](https://mlsanity.com/paper/2508.17008/) (2025)
- [Adversarial Evasion Attack Efficiency against Large Language Models](https://mlsanity.com/paper/2406.08050/) (2024)
- [ECQED: Emotion-Cause Quadruple Extraction in Dialogs](https://mlsanity.com/paper/2306.03969/) (2023)
- [TKDP: Threefold Knowledge-enriched Deep Prompt Tuning for Few-shot Named Entity Recognition](https://mlsanity.com/paper/2306.03974/) (2023)
- [Revisiting Conversation Discourse for Dialogue Disentanglement](https://mlsanity.com/paper/2306.03975/) (2023)
- [A Bi-directional Multi-hop Inference Model for Joint Dialog Sentiment Classification and Act Recognition](https://mlsanity.com/paper/2308.04424/) (2023)
- [DialogRE^C+: An Extension of DialogRE to Investigate How Much Coreference Helps Relation Extraction in Dialogs](https://mlsanity.com/paper/2308.04498/) (2023)
- [DPR: An Algorithm Mitigate Bias Accumulation in Recommendation feedback loops](https://mlsanity.com/paper/2311.05864/) (2023)
- [Syntactic Fusion: Enhancing Aspect-Level Sentiment Analysis Through Multi-Tree Graph Integration](https://mlsanity.com/paper/2312.03738/) (2023)
- [KPC-cF: Aspect-Based Sentiment Analysis via Implicit-Feature Alignment with Corpus Filtering](https://mlsanity.com/paper/2407.00342/) (2024)
- [Data-Efficient Adaptation and a Novel Evaluation Method for Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2511.03034/) (2025)
- [The challenge of generating and evolving real-life like synthetic test data without accessing real-world raw data -- a Systematic Review](https://mlsanity.com/paper/2602.06609/) (2026)

## Abstract (arXiv)

Aspect-based sentiment analysis (ABSA) aims at automatically inferring the specific sentiment polarities toward certain aspects of products or services behind the social media texts or reviews, which has been a fundamental application to the real-world society. Since the early 2010s, ABSA has achieved extraordinarily high accuracy with various deep neural models. However, existing ABSA models with strong in-house performances may fail to generalize to some challenging cases where the contexts are variable, i.e., low robustness to real-world environments. In this study, we propose to enhance the ABSA robustness by systematically rethinking the bottlenecks from all possible angles, including model, data, and training. First, we strengthen the current best-robust syntax-aware models by further incorporating the rich external syntactic dependencies and the labels with aspect simultaneously with a universal-syntax graph convolutional network. In the corpus perspective, we propose to automatically induce high-quality synthetic training data with various types, allowing models to learn sufficient inductive bias for better robustness. Last, we based on the rich pseudo data perform adversarial training to enhance the resistance to the context perturbation and meanwhile employ contrastive learning to reinforce the representations of instances with contrastive sentiments. Extensive robustness evaluations are conducted. The results demonstrate that our enhanced syntax-aware model achieves better robustness performances than all the state-of-the-art baselines. By additionally incorporating our synthetic corpus, the robust testing results are pushed with around 10% accuracy, which are then further improved by installing the advanced training strategies. In-depth analyses are presented for revealing the factors influencing the ABSA robustness.