# Fine-grained Sentiment Analysis with Faithful Attention

arXiv: https://arxiv.org/abs/1908.06870 · HTML: https://mlsanity.com/paper/1908.06870/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Aug 2019.

## Built on by (most cited first, 23 of 23)

- [Interpreting Language Models with Contrastive Explanations](https://mlsanity.com/paper/2202.10419/) (2022)
- [The Out-of-Distribution Problem in Explainability and Search Methods for Feature Importance Explanations](https://mlsanity.com/paper/2106.00786/) (2021)
- [Quantifying Context Mixing in Transformers](https://mlsanity.com/paper/2301.12971/) (2023)
- [Approximating How Single Head Attention Learns](https://mlsanity.com/paper/2103.07601/) (2021)
- [Order in the Court: Explainable AI Methods Prone to Disagreement](https://mlsanity.com/paper/2105.03287/) (2021)
- [Going Beyond XAI: A Systematic Survey for Explanation-Guided Learning](https://mlsanity.com/paper/2212.03954/) (2022)
- [ORCA: Interpreting Prompted Language Models via Locating Supporting Data Evidence in the Ocean of Pretraining Data](https://mlsanity.com/paper/2205.12600/) (2022)
- [Explain and Predict, and then Predict Again](https://mlsanity.com/paper/2101.04109/) (2021)
- [Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updates](https://mlsanity.com/paper/2110.03212/) (2021)
- [Do Context-Aware Translation Models Pay the Right Attention?](https://mlsanity.com/paper/2105.06977/) (2021)
- [MDACE: MIMIC Documents Annotated with Code Evidence](https://mlsanity.com/paper/2307.03859/) (2023)
- [Explainable Deep Learning in Healthcare: A Methodological Survey from an Attribution View](https://mlsanity.com/paper/2112.02625/) (2021)
- [A survey on improving NLP models with human explanations](https://mlsanity.com/paper/2204.08892/) (2022)
- [VisFIS: Visual Feature Importance Supervision with Right-for-the-Right-Reason Objectives](https://mlsanity.com/paper/2206.11212/) (2022)
- [ExDDV: A New Dataset for Explainable Deepfake Detection in Video](https://mlsanity.com/paper/2503.14421/) (2025)
- [StyLEx: Explaining Style Using Human Lexical Annotations](https://mlsanity.com/paper/2210.07469/) (2022)
- [Faithful and Plausible Explanations of Medical Code Predictions](https://mlsanity.com/paper/2104.07894/) (2021)
- [Main Predicate and Their Arguments as Explanation Signals For Intent Classification](https://mlsanity.com/paper/2502.01270/) (2025)
- [Large Language Models as Attribution Regularizers for Efficient Model Training](https://mlsanity.com/paper/2502.20268/) (2025)
- [Interpreting Sentiment Composition with Latent Semantic Tree](https://mlsanity.com/paper/2308.16588/) (2023)
- [Efficient Text-Attributed Graph Learning through Selective Annotation and Graph Alignment](https://mlsanity.com/paper/2506.07168/) (2025)
- [Can human clinical rationales improve the performance and explainability of clinical text classification models?](https://mlsanity.com/paper/2507.21302/) (2025)
- [Human-Centered Supervision for Sentiment Analysis in Telugu: A Systematic Inquiry Beyond Accuracy](https://mlsanity.com/paper/2508.01486/) (2025)

## Abstract (arXiv)

While the general task of textual sentiment classification has been widely studied, much less research looks specifically at sentiment between a specified source and target. To tackle this problem, we experimented with a state-of-the-art relation extraction model. Surprisingly, we found that despite reasonable performance, the model's attention was often systematically misaligned with the words that contribute to sentiment. Thus, we directly trained the model's attention with human rationales and improved our model performance by a robust 4~8 points on all tasks we defined on our data sets. We also present a rigorous analysis of the model's attention, both trained and untrained, using novel and intuitive metrics. Our results show that untrained attention does not provide faithful explanations; however, trained attention with concisely annotated human rationales not only increases performance, but also brings faithful explanations. Encouragingly, a small amount of annotated human rationales suffice to correct the attention in our task.