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 challe...

Scholarly peer review is a complex collaborative activity that is increasingly supported by web-based systems. Yet little is known about how reviewers and authors interact in such environments, how criticisms are conveyed, or how the systems may affect the interactions and use of language of reviewers and authors. We looked at one aspect of the interactions between reviewers and authors, the us...

Automatic assessment of subjective characteristics of customers like politeness, satisfaction or competence could provide services companies with information needful for improving service quality. In this work, we construct a regression model for politeness estimation of customers, which uses a) set of linguistic indicators and b) manual estimations of expert(s). We apply the suggested methodol...

In our study „Polite responses to polite requests‟, 1 we reported four experiments. In Experiment 1, people rated the politeness of 18 types of indirect requests, such as Could you tell me where Jordan Hall is? In Experiments 2, 3, and 4, other people rated the politeness of various responses to these requests, such as Yes, I can—it's down the street and Down the street. From the findings, we a...

Sociolinguistic research suggests that women are more likely than men to use politeness strategies in their speech. Researchers have reported that women pay more compliments than men, that women in talk with same-sex peers use a large number of positive-politeness strategies while men in analogous situations do not, and that women are more likely to apologize, soften criticism or express thanks...

This study examines variation in evaluations of im/politeness of a recording of a naturally occurring intercultural apology, focusing in particular on potential cultural differences in these evaluations across speakers of (Australian) English and (Mandarin) Chinese. We first closely analyse the apology itself as a form of social action, and suggest in the course of this analysis that evaluation...

It has been found that Korean speakers lower their average voice pitch when speaking politely [16, 17], contradicting the idea that high pitch is polite across all cultures, as proposed by Ohala’s Frequency Code hypothesis [e.g., 12]. This study looks at pitch as a perceptual cue to politeness in Korean. Ten Korean listeners heard short utterances from eight different speakers and judged whethe...

Analysis of sociointerpersonal communication patterns among discourse participants is essential to understand the manifestation of and the interpersonalcommunication features realized in online social interaction. The linguistic politeness theory provides an effective framework for such an analysis of sociointerpersonal communication features employed by online language users tomaintain and enh...

Politeness is an integral part of human language variation, e.g. consider the difference in the pragmatic effect of realizing the same communicative goal with either “Get me a glass of water mate!” or “I wonder if I could possibly have some water please?” This paper presents POLLy (Politeness for Language Learning), a system which combines a natural language generator with an AI Planner to mode...