Towards User-Centric Guidelines for Chatbot Conversational Design

TL;DR

This paper develops user-centric guidelines for chatbot conversational design based on a systematic review and survey, aiming to improve user satisfaction and engagement.

Contribution

It introduces a set of conversational guidelines derived from literature review and evaluation, aiding designers in creating more effective chatbots.

Findings

Guidelines are perceived as usable, flexible, and clear by respondents.

Applying guidelines increases user satisfaction and engagement.

The study provides a structured approach to chatbot conversational practices.

Abstract

The conversational nature of chatbots poses challenges to designers since their development is different from other software and requires investigating new practices in the context of human-AI interaction and their impact on user experience. Therefore, this work aims to unveil chatbot conversational practices alongside their impacts on users to build a web guide to support designers while conceiving conversations for chatbots. We have carried out a Systematic Literature Review (SLR) to identify linguist, visual, and interactive elements used in chatbot conversational design. The SLR resulted in 40 selected studies that were reviewed and coded into a set of conversational guidelines that were evaluated through a survey. Respondents strongly agreed that applying the proposed guidelines in chatbot development would induce greater user satisfaction and user engagement and the guide is usable, flexible, clear, and understandable, making it a great ally in building chatbots with an improved user experience.