Saved in:
Bibliographic Details
Main Authors: Baihaqi, Muhammad Yeza, Contreras, Angel García, Kawano, Seiya, Yoshino, Koichiro
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.09839
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916287090786304
author Baihaqi, Muhammad Yeza
Contreras, Angel García
Kawano, Seiya
Yoshino, Koichiro
author_facet Baihaqi, Muhammad Yeza
Contreras, Angel García
Kawano, Seiya
Yoshino, Koichiro
contents Rapport is known as a conversational aspect focusing on relationship building, which influences outcomes in collaborative tasks. This study aims to establish human-agent rapport through small talk by using a rapport-building strategy. We implemented this strategy for the virtual agents based on dialogue strategies by prompting a large language model (LLM). In particular, we utilized two dialogue strategies-predefined sequence and free-form-to guide the dialogue generation framework. We conducted analyses based on human evaluations, examining correlations between total turn, utterance characters, rapport score, and user experience variables: naturalness, satisfaction, interest, engagement, and usability. We investigated correlations between rapport score and naturalness, satisfaction, engagement, and conversation flow. Our experimental results also indicated that using free-form to prompt the rapport-building strategy performed the best in subjective scores.
format Preprint
id arxiv_https___arxiv_org_abs_2406_09839
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Rapport-Driven Virtual Agent: Rapport Building Dialogue Strategy for Improving User Experience at First Meeting
Baihaqi, Muhammad Yeza
Contreras, Angel García
Kawano, Seiya
Yoshino, Koichiro
Computation and Language
Human-Computer Interaction
Rapport is known as a conversational aspect focusing on relationship building, which influences outcomes in collaborative tasks. This study aims to establish human-agent rapport through small talk by using a rapport-building strategy. We implemented this strategy for the virtual agents based on dialogue strategies by prompting a large language model (LLM). In particular, we utilized two dialogue strategies-predefined sequence and free-form-to guide the dialogue generation framework. We conducted analyses based on human evaluations, examining correlations between total turn, utterance characters, rapport score, and user experience variables: naturalness, satisfaction, interest, engagement, and usability. We investigated correlations between rapport score and naturalness, satisfaction, engagement, and conversation flow. Our experimental results also indicated that using free-form to prompt the rapport-building strategy performed the best in subjective scores.
title Rapport-Driven Virtual Agent: Rapport Building Dialogue Strategy for Improving User Experience at First Meeting
topic Computation and Language
Human-Computer Interaction
url https://arxiv.org/abs/2406.09839