Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Computational Politeness in Natural Language Processing: A Survey

Priyanshu Priya, Mauajama Firdaus, Asif Ekbal

TL;DR

This survey analyzes computational politeness in NLP, framing it around identification and generation tasks across non-conversational and conversational data and highlighting linguistic foundations, datasets, and methods. It surveys statistically driven and deep learning approaches, including recent LLM-enabled studies, and catalogs performance across diverse corpora with attention to context and social factors. The work identifies data scarcity and annotation quality as major bottlenecks while pointing to growing trends in context-aware modeling, cross-cultural politeness, and socio-linguistic cue integration. The findings underscore politeness as a crucial driver of user experience, trust, and effectiveness in human-computer interaction, and suggest directions toward multilingual, socially aware, and ethically aligned polite NLP systems.

Abstract

Computational approach to politeness is the task of automatically predicting and generating politeness in text. This is a pivotal task for conversational analysis, given the ubiquity and challenges of politeness in interactions. The computational approach to politeness has witnessed great interest from the conversational analysis community. This article is a compilation of past works in computational politeness in natural language processing. We view four milestones in the research so far, viz. supervised and weakly-supervised feature extraction to identify and induce politeness in a given text, incorporation of context beyond the target text, study of politeness across different social factors, and study the relationship between politeness and various sociolinguistic cues. In this article, we describe the datasets, approaches, trends, and issues in computational politeness research. We also discuss representative performance values and provide pointers to future works, as given in the prior works. In terms of resources to understand the state-of-the-art, this survey presents several valuable illustrations, most prominently, a table summarizing the past papers along different dimensions, such as the types of features, annotation techniques, and datasets used.

Computational Politeness in Natural Language Processing: A Survey

TL;DR

This survey analyzes computational politeness in NLP, framing it around identification and generation tasks across non-conversational and conversational data and highlighting linguistic foundations, datasets, and methods. It surveys statistically driven and deep learning approaches, including recent LLM-enabled studies, and catalogs performance across diverse corpora with attention to context and social factors. The work identifies data scarcity and annotation quality as major bottlenecks while pointing to growing trends in context-aware modeling, cross-cultural politeness, and socio-linguistic cue integration. The findings underscore politeness as a crucial driver of user experience, trust, and effectiveness in human-computer interaction, and suggest directions toward multilingual, socially aware, and ethically aligned polite NLP systems.

Abstract

Computational approach to politeness is the task of automatically predicting and generating politeness in text. This is a pivotal task for conversational analysis, given the ubiquity and challenges of politeness in interactions. The computational approach to politeness has witnessed great interest from the conversational analysis community. This article is a compilation of past works in computational politeness in natural language processing. We view four milestones in the research so far, viz. supervised and weakly-supervised feature extraction to identify and induce politeness in a given text, incorporation of context beyond the target text, study of politeness across different social factors, and study the relationship between politeness and various sociolinguistic cues. In this article, we describe the datasets, approaches, trends, and issues in computational politeness research. We also discuss representative performance values and provide pointers to future works, as given in the prior works. In terms of resources to understand the state-of-the-art, this survey presents several valuable illustrations, most prominently, a table summarizing the past papers along different dimensions, such as the types of features, annotation techniques, and datasets used.
Paper Structure (21 sections, 3 figures, 8 tables)

This paper contains 21 sections, 3 figures, 8 tables.

Table of Contents

  1. Introduction
  2. Politeness studies in Linguistics
  3. Approaches to Politeness
  4. Politeness Variations in Linguistic Studies
  5. Relationship with Etiquette, Formality, Emotion and Offensiveness
  6. Problem Definition
  7. Politeness as Natural Language Understanding Task
  8. Politeness as Natural Language Generation Task
  9. A note on languages
  10. Datasets
  11. Non-conversational Dataset
  12. Conversational Dataset
  13. Approaches
  14. Statistical Approaches
  15. Deep Learning-based Approaches
  16. ...and 6 more sections

Figures (3)

  • Figure 1: Organization of the present survey
  • Figure 2: Overview of various approaches to politeness in linguistic studies
  • Figure 3: Trends in computational politeness research