# Eliminating Sentiment Bias for Aspect-Level Sentiment Classification with Unsupervised Opinion Extraction

arXiv: https://arxiv.org/abs/2109.02403 · HTML: https://mlsanity.com/paper/2109.02403/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 34 references that are in the map.
- First posted on arXiv 6 Sep 2021.

## Builds on (most cited first, 19 of 19)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [A Structured Self-attentive Sentence Embedding](https://mlsanity.com/paper/1703.03130/) (2017)
- [End-to-end Neural Coreference Resolution](https://mlsanity.com/paper/1707.07045/) (2017)
- [Reducing Sentiment Bias in Language Models via Counterfactual Evaluation](https://mlsanity.com/paper/1911.03064/) (2019)
- [Knowing What, How and Why: A Near Complete Solution for Aspect-based Sentiment Analysis](https://mlsanity.com/paper/1911.01616/) (2019)
- [Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence](https://mlsanity.com/paper/1903.09588/) (2019)
- [Perturbed Masking: Parameter-free Probing for Analyzing and Interpreting BERT](https://mlsanity.com/paper/2004.14786/) (2020)
- [Relational Graph Attention Network for Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2004.12362/) (2020)
- [Position-Aware Tagging for Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2010.02609/) (2020)
- [Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks](https://mlsanity.com/paper/1909.03477/) (2019)
- [A Joint Training Dual-MRC Framework for Aspect Based Sentiment Analysis](https://mlsanity.com/paper/2101.00816/) (2021)
- [Open-Domain Targeted Sentiment Analysis via Span-Based Extraction and Classification](https://mlsanity.com/paper/1906.03820/) (2019)
- [Does syntax matter? A strong baseline for Aspect-based Sentiment Analysis with RoBERTa](https://mlsanity.com/paper/2104.04986/) (2021)
- [Learning Natural Language Inference using Bidirectional LSTM model and Inner-Attention](https://mlsanity.com/paper/1605.09090/) (2016)
- [Syntax-Aware Aspect-Level Sentiment Classification with Proximity-Weighted Convolution Network](https://mlsanity.com/paper/1909.10171/) (2019)
- [Graph Ensemble Learning over Multiple Dependency Trees for Aspect-level Sentiment Classification](https://mlsanity.com/paper/2103.11794/) (2021)

## Built on by (most cited first, 11 of 11)

- [A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challenges](https://mlsanity.com/paper/2203.01054/) (2022)
- [Sociodemographic Bias in Language Models: A Survey and Forward Path](https://mlsanity.com/paper/2306.08158/) (2023)
- [LSA: Modeling Aspect Sentiment Coherency via Local Sentiment Aggregation](https://mlsanity.com/paper/2110.08604/) (2021)
- [PyABSA: A Modularized Framework for Reproducible Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2208.01368/) (2022)
- [Instruct-DeBERTa: A Hybrid Approach for Aspect-based Sentiment Analysis on Textual Reviews](https://mlsanity.com/paper/2408.13202/) (2024)
- [A Framework of Customer Review Analysis Using the Aspect-Based Opinion Mining Approach](https://mlsanity.com/paper/2212.10051/) (2022)
- [A Weak Supervision Approach for Few-Shot Aspect Based Sentiment](https://mlsanity.com/paper/2305.11979/) (2023)
- [A Note on Bias to Complete](https://mlsanity.com/paper/2402.11710/) (2024)
- [EmoGRACE: Aspect-based emotion analysis for social media data](https://mlsanity.com/paper/2503.15133/) (2025)
- [Topic Bias in Emotion Classification](https://mlsanity.com/paper/2312.09043/) (2023)
- [GHI: Graphormer over Conditioned Hypergraph Incidence for Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2605.22228/) (2026)

## Abstract (arXiv)

Aspect-level sentiment classification (ALSC) aims at identifying the sentiment polarity of a specified aspect in a sentence. ALSC is a practical setting in aspect-based sentiment analysis due to no opinion term labeling needed, but it fails to interpret why a sentiment polarity is derived for the aspect. To address this problem, recent works fine-tune pre-trained Transformer encoders for ALSC to extract an aspect-centric dependency tree that can locate the opinion words. However, the induced opinion words only provide an intuitive cue far below human-level interpretability. Besides, the pre-trained encoder tends to internalize an aspect's intrinsic sentiment, causing sentiment bias and thus affecting model performance. In this paper, we propose a span-based anti-bias aspect representation learning framework. It first eliminates the sentiment bias in the aspect embedding by adversarial learning against aspects' prior sentiment. Then, it aligns the distilled opinion candidates with the aspect by span-based dependency modeling to highlight the interpretable opinion terms. Our method achieves new state-of-the-art performance on five benchmarks, with the capability of unsupervised opinion extraction.