# Causal Intervention Improves Implicit Sentiment Analysis

arXiv: https://arxiv.org/abs/2208.09329 · HTML: https://mlsanity.com/paper/2208.09329/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 64 references that are in the map.
- First posted on arXiv 19 Aug 2022.

## Builds on (most cited first, 24 of 24)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [A Structured Self-attentive Sentence Embedding](https://mlsanity.com/paper/1703.03130/) (2017)
- [Counterfactual VQA: A Cause-Effect Look at Language Bias](https://mlsanity.com/paper/2006.04315/) (2020)
- [Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond](https://mlsanity.com/paper/2109.00725/) (2021)
- [BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis](https://mlsanity.com/paper/1904.02232/) (2019)
- [Invariance, Causality and Robustness](https://mlsanity.com/paper/1812.08233/) (2018)
- [Relational Graph Attention Network for Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2004.12362/) (2020)
- [Interactive Attention Networks for Aspect-Level Sentiment Classification](https://mlsanity.com/paper/1709.00893/) (2017)
- [Counterfactual Invariance to Spurious Correlations: Why and How to Pass Stress Tests](https://mlsanity.com/paper/2106.00545/) (2021)
- [Adapt or Get Left Behind: Domain Adaptation through BERT Language Model Finetuning for Aspect-Target Sentiment Classification](https://mlsanity.com/paper/1908.11860/) (2019)
- [Identifying Spurious Correlations for Robust Text Classification](https://mlsanity.com/paper/2010.02458/) (2020)
- [Does syntax matter? A strong baseline for Aspect-based Sentiment Analysis with RoBERTa](https://mlsanity.com/paper/2104.04986/) (2021)
- [Learning Implicit Sentiment in Aspect-based Sentiment Analysis with Supervised Contrastive Pre-Training](https://mlsanity.com/paper/2111.02194/) (2021)
- [Unsupervised Discovery of Implicit Gender Bias](https://mlsanity.com/paper/2004.08361/) (2020)
- [Challenges of Using Text Classifiers for Causal Inference](https://mlsanity.com/paper/1810.00956/) (2018)
- [Feature-Wise Bias Amplification](https://mlsanity.com/paper/1812.08999/) (2018)
- [Tasty Burgers, Soggy Fries: Probing Aspect Robustness in Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2009.07964/) (2020)
- [Empowering Language Understanding with Counterfactual Reasoning](https://mlsanity.com/paper/2106.03046/) (2021)
- [Adversarial Visual Robustness by Causal Intervention](https://mlsanity.com/paper/2106.09534/) (2021)
- [Same Representation, Different Attentions: Shareable Sentence Representation Learning from Multiple Tasks](https://mlsanity.com/paper/1804.08139/) (2018)

## Built on by (most cited first, 16 of 16)

- [Reasoning Implicit Sentiment with Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.11255/) (2023)
- [Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives](https://mlsanity.com/paper/2307.16851/) (2023)
- [Causal Walk: Debiasing Multi-Hop Fact Verification with Front-Door Adjustment](https://mlsanity.com/paper/2403.02698/) (2024)
- [RVISA: Reasoning and Verification for Implicit Sentiment Analysis](https://mlsanity.com/paper/2407.02340/) (2024)
- [Aspect-Based Sentiment Analysis with Explicit Sentiment Augmentations](https://mlsanity.com/paper/2312.10961/) (2023)
- [EmPO: Emotion Grounding for Empathetic Response Generation through Preference Optimization](https://mlsanity.com/paper/2406.19071/) (2024)
- [My Words Imply Your Opinion: Reader Agent-based Propagation Enhancement for Personalized Implicit Emotion Analysis](https://mlsanity.com/paper/2412.07367/) (2024)
- [Causal Prompting for Implicit Sentiment Analysis with Large Language Models](https://mlsanity.com/paper/2507.00389/) (2025)
- [Domain Generalization via Causal Adjustment for Cross-Domain Sentiment Analysis](https://mlsanity.com/paper/2402.14536/) (2024)
- [DINER: Debiasing Aspect-based Sentiment Analysis with Multi-variable Causal Inference](https://mlsanity.com/paper/2403.01166/) (2024)
- [Learning Local Causal World Models with State Space Models and Attention](https://mlsanity.com/paper/2505.02074/) (2025)
- [When to Trust: A Causality-Aware Calibration Framework for Accurate Knowledge Graph Retrieval-Augmented Generation](https://mlsanity.com/paper/2601.09241/) (2026)
- [Topic-aware Causal Intervention for Counterfactual Detection](https://mlsanity.com/paper/2409.16668/) (2024)
- [Application of Multiple Chain-of-Thought in Contrastive Reasoning for Implicit Sentiment Analysis](https://mlsanity.com/paper/2503.07140/) (2025)
- [CURE: Controlled Unlearning for Robust Embeddings -- Mitigating Conceptual Shortcuts in Pre-Trained Language Models](https://mlsanity.com/paper/2509.05230/) (2025)
- [Task-Routed Mixture-of-Experts with Cognitive Appraisal for Implicit Sentiment Analysis](https://mlsanity.com/paper/2605.20916/) (2026)

## Abstract (arXiv)

Despite having achieved great success for sentiment analysis, existing neural models struggle with implicit sentiment analysis. This may be due to the fact that they may latch onto spurious correlations ("shortcuts", e.g., focusing only on explicit sentiment words), resulting in undermining the effectiveness and robustness of the learned model. In this work, we propose a causal intervention model for Implicit Sentiment Analysis using Instrumental Variable (ISAIV). We first review sentiment analysis from a causal perspective and analyze the confounders existing in this task. Then, we introduce an instrumental variable to eliminate the confounding causal effects, thus extracting the pure causal effect between sentence and sentiment. We compare the proposed ISAIV model with several strong baselines on both the general implicit sentiment analysis and aspect-based implicit sentiment analysis tasks. The results indicate the great advantages of our model and the efficacy of implicit sentiment reasoning.