# Interpreting Neural Networks to Improve Politeness Comprehension

arXiv: https://arxiv.org/abs/1610.02683 · HTML: https://mlsanity.com/paper/1610.02683/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Oct 2016.

## Built on by (most cited first, 12 of 12)

- [TyDiP: A Dataset for Politeness Classification in Nine Typologically Diverse Languages](https://mlsanity.com/paper/2211.16496/) (2022)
- [Computational Politeness in Natural Language Processing: A Survey](https://mlsanity.com/paper/2407.12814/) (2024)
- [Explaining the Road Not Taken](https://mlsanity.com/paper/2103.14973/) (2021)
- [Towards Explaining Subjective Ground of Individuals on Social Media](https://mlsanity.com/paper/2211.09953/) (2022)
- [Tell Model Where to Attend: Improving Interpretability of Aspect-Based Sentiment Classification via Small Explanation Annotations](https://mlsanity.com/paper/2302.10479/) (2023)
- [Comparing Styles across Languages: A Cross-Cultural Exploration of Politeness](https://mlsanity.com/paper/2310.07135/) (2023)
- [Conversational Analysis of Daily Dialog Data using Polite Emotional Dialogue Acts](https://mlsanity.com/paper/2205.02921/) (2022)
- [Politeness Stereotypes and Attack Vectors: Gender Stereotypes in Japanese and Korean Language Models](https://mlsanity.com/paper/2306.09752/) (2023)
- [Learning Intrinsic Dimension via Information Bottleneck for Explainable Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2402.18145/) (2024)
- [Polite Emotional Dialogue Acts for Conversational Analysis in Daily Dialog Data](https://mlsanity.com/paper/2112.13572/) (2021)
- [Improving Prediction Performance and Model Interpretability through Attention Mechanisms from Basic and Applied Research Perspectives](https://mlsanity.com/paper/2303.14116/) (2023)
- [No Universal Courtesy: A Cross-Linguistic, Multi-Model Study of Politeness Effects on LLMs Using the PLUM Corpus](https://mlsanity.com/paper/2604.16275/) (2026)

## Abstract (arXiv)

We present an interpretable neural network approach to predicting and understanding politeness in natural language requests. Our models are based on simple convolutional neural networks directly on raw text, avoiding any manual identification of complex sentiment or syntactic features, while performing better than such feature-based models from previous work. More importantly, we use the challenging task of politeness prediction as a testbed to next present a much-needed understanding of what these successful networks are actually learning. For this, we present several network visualizations based on activation clusters, first derivative saliency, and embedding space transformations, helping us automatically identify several subtle linguistics markers of politeness theories. Further, this analysis reveals multiple novel, high-scoring politeness strategies which, when added back as new features, reduce the accuracy gap between the original featurized system and the neural model, thus providing a clear quantitative interpretation of the success of these neural networks.