# Chatbots language design: the influence of language variation on user experience

**Authors:** Ana Paula Chaves, Jesse Egbert, Toby Hocking, Eck Doerry, Marco Aurelio Gerosa  
**arXiv:** [2101.11089](https://arxiv.org/abs/2101.11089)  
**Date:** 2021-01-26  
**Summary page:** https://www.summarizepaper.com/en/paper/2101.11089v1/

## Key points

- The paper explores the impact of chatbot language choices on user perceptions and experiences
- The authors draw on sociolinguistic theory to investigate how a chatbot's language can adhere to the expected social role it performs within a given context
- Register differences play a role in shaping the user's perception of the human-chatbot interaction
- The study produced parallel corpora of conversations in the tourism domain with similar content but varying register characteristics and evaluated users' preferences for chatbot linguistic choices in terms of appropriateness, credibility, and user experience
- Register characteristics are strong predictors of user preferences, highlighting the need for designing chatbots with register-appropriate language to improve acceptance and users' perceptions of chatbot interactions
- This research provides valuable insights into the importance of considering linguistic register in chatbot design to enhance user experience and acceptance by taking into account users' preferences for appropriate language use.

## Summary

The paper titled "Chatbots language design: the influence of language variation on user experience" explores the impact of chatbot language choices on user perceptions and experiences. The authors, Ana Paula Chaves, Jesse Egbert, Toby Hocking, Eck Doerry, and Marco Aurelio Gerosa draw on sociolinguistic theory to investigate how a chatbot's language can adhere to the expected social role it performs within a given context. Specifically, they analyze how register differences play a role in shaping the user's perception of the human-chatbot interaction. The study produced parallel corpora of conversations in the tourism domain with similar content but varying register characteristics and evaluated users' preferences for chatbot linguistic choices in terms of appropriateness, credibility, and user experience. The results show that register characteristics are strong predictors of user preferences, highlighting the need for designing chatbots with register-appropriate language to improve acceptance and users' perceptions of chatbot interactions. This research provides valuable insights into the importance of considering linguistic register in chatbot design to enhance user experience and acceptance by taking into account users' preferences for appropriate language use. Additionally, this research emphasizes that careful consideration should be given to designing chatbots with register-appropriate language as it can significantly influence users' perceptions and experiences when interacting with them.