mlsanityData to 14 Oct 2026

Aspect-Based Sentiment Analysis with Explicit Sentiment Augmentations

arXiv 2312.10961 ↗First posted 18 Dec 2023cs.CL cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

Aspect-based sentiment analysis (ABSA), a fine-grained sentiment classification task, has received much attention recently. Many works investigate sentiment information through opinion words, such as ''good'' and ''bad''. However, implicit sentiment widely exists in the ABSA dataset, which refers to the sentence containing no distinct opinion words but still expresses sentiment to the aspect term. To deal with implicit sentiment, this paper proposes an ABSA method that integrates explicit sentiment augmentations. And we propose an ABSA-specific augmentation method to create such augmentations. Specifically, we post-trains T5 by rule-based data. We employ Syntax Distance Weighting and Unlikelihood Contrastive Regularization in the training procedure to guide the model to generate an explicit sentiment. Meanwhile, we utilize the Constrained Beam Search to ensure the augmentation sentence contains the aspect terms. We test ABSA-ESA on two of the most popular benchmarks of ABSA. The results show that ABSA-ESA outperforms the SOTA baselines on implicit and explicit sentiment accuracy.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 18 of its 36 references that are in the map. First posted on arXiv 18 Dec 2023.

Builds on

18 of 36 references.

References · 18

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  2. 2019EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Taskscited by 807
  3. 2020Beyond English-Centric Multilingual Machine Translationcited by 561
  4. 2019BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysiscited by 176
  5. 2020Relational Graph Attention Network for Aspect-based Sentiment Analysiscited by 104
  6. 2015Effective LSTMs for Target-Dependent Sentiment Classificationcited by 82
  7. 2023Reasoning Implicit Sentiment with Chain-of-Thought Promptingcited by 80
  8. 2019Adapt or Get Left Behind: Domain Adaptation through BERT Language Model Finetuning for Aspect-Target Sentiment Classificationcited by 63
  9. 2019An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysiscited by 52
  10. 2019Soft Contextual Data Augmentation for Neural Machine Translationcited by 49
  11. 2021Does syntax matter? A strong baseline for Aspect-based Sentiment Analysis with RoBERTacited by 41
  12. 2021Learning Implicit Sentiment in Aspect-based Sentiment Analysis with Supervised Contrastive Pre-Trainingcited by 37
6 more
  1. 2022Sample, Translate, Recombine: Leveraging Audio Alignments for Data Augmentation in End-to-end Speech Translationcited by 27
  2. 2021AUGNLG: Few-shot Natural Language Generation using Self-trained Data Augmentationcited by 17
  3. 2022Causal Intervention Improves Implicit Sentiment Analysiscited by 16
  4. 2021Graph Ensemble Learning over Multiple Dependency Trees for Aspect-level Sentiment Classificationcited by 13
  5. 2020Understanding Pre-trained BERT for Aspect-based Sentiment Analysiscited by 9
  6. 2021To be Closer: Learning to Link up Aspects with Opinionscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 2; 2026: 3.

7 papers.

  1. 2024Why Misinformation is Created? Detecting them by Integrating Intent Featurescited by 11
  2. 2024RVISA: Reasoning and Verification for Implicit Sentiment Analysiscited by 9
  3. 2025Causal Prompting for Implicit Sentiment Analysis with Large Language Modelscited by 4
  4. 2025Weakly Supervised Fine-grained Span-Level Framework for Chinese Radiology Report Quality Assurancecited by 0
  5. 2026Large-Scale Aspect-Based Sentiment Analysis with Reasoning-Infused LLMscited by 0
  6. 2026Task-Routed Mixture-of-Experts with Cognitive Appraisal for Implicit Sentiment Analysiscited by 0
  7. 2026GHI: Graphormer over Conditioned Hypergraph Incidence for Aspect-Based Sentiment Analysiscited by 0