CommunityBots: Creating and Evaluating A Multi-Agent Chatbot Platform for Public Input Elicitation

CommunityBots: Creating and Evaluating A Multi-Agent Chatbot Platform for Public Input Elicitation
复制标题

CommunityBots:创建和评估用于征求公众意见的多代理聊天机器人平台

DOI:
10.1145/3579469
复制
发表时间:
2023
影响因子:
--
通讯作者:
Mahyar, Narges
Mahyar, Narges
中科院分区:
--
文献类型:
--
作者:
Jiang, Zhiqiu;Rashik, Mashrur;Panchal, Kunjal;Jasim, Mahmood;Sarvghad, Ali;Riahi, Pari;DeWitt, Erica;Thurber, Fey;Mahyar, Narges

文献摘要

参考文献

被引文献

相似文献

近年来,人工智能对话代理或聊天机器人的普及已经成为传统在线调查的替代方案,可以从人们那里获取信息。然而,在使用单代理聊天机器人进行对话和收集各种主题的多方面信息方面存在差距。先前的研究表明,在多方面的对话中,单代理聊天机器人很难理解用户的意图和解释人类的语言。在这项工作中,我们研究了如何利用多代理聊天机器人系统进行跨多个领域的多方面对话。为此,我们进行了一项绿野仙踪研究,以调查多代理聊天机器人的设计,用于收集跨多个高级域及其相关主题的公共输入。接下来,我们设计、开发并评估了CommunityBots——一个多代理聊天机器人平台,每个聊天机器人单独处理不同的领域。为了管理多个话题和聊天机器人之间的对话,我们提出了一种新的对话和话题管理(CTM)机制,该机制基于用户的响应和意图来处理话题切换和聊天机器人切换。我们进行了一项主题间研究,将CommunityBots与96名人群工作者的单代理聊天机器人基线进行了比较。我们的评估结果表明,CommunityBots的参与者在同一会话中与多个不同的聊天机器人交谈时,明显更投入,提供了更高质量的回应,并且经历了更少的谈话中断。我们还发现,与界面相结合的视觉线索有助于参与者更好地理解CTM机制的功能,这使他们能够感知文本会话的变化,从而提高用户满意度。在此基础上,我们讨论了未来多智能体聊天机器人设计的研究方向及其在丰富信息提取中的应用。
In recent years, the popularity of AI-enabled conversational agents or chatbots has risen as an alternative to traditional online surveys to elicit information from people. However, there is a gap in using single-agent chatbots to converse and gather multi-faceted information across a wide variety of topics. Prior works suggest that single-agent chatbots struggle to understand user intentions and interpret human language during a multi-faceted conversation. In this work, we investigated how multi-agent chatbot systems can be utilized to conduct a multi-faceted conversation across multiple domains. To that end, we conducted a Wizard of Oz study to investigate the design of a multi-agent chatbot for gathering public input across multiple high-level domains and their associated topics. Next, we designed, developed, and evaluated CommunityBots - a multi-agent chatbot platform where each chatbot handles a different domain individually. To manage conversation across multiple topics and chatbots, we proposed a novel Conversation and Topic Management (CTM) mechanism that handles topic-switching and chatbot-switching based on user responses and intentions. We conducted a between-subject study comparing CommunityBots to a single-agent chatbot baseline with 96 crowd workers. The results from our evaluation demonstrate that CommunityBots participants were significantly more engaged, provided higher quality responses, and experienced fewer conversation interruptions while conversing with multiple different chatbots in the same session. We also found that the visual cues integrated with the interface helped the participants better understand the functionalities of the CTM mechanism, which enabled them to perceive changes in textual conversation, leading to better user satisfaction. Based on the empirical insights from our study, we discuss future research avenues for multi-agent chatbot design and its application for rich information elicitation.
对话风格:分析朋友之间的谈话
DOI: 10.1177/0261927x8500400208
发表时间: 1985
影响因子: 2.1
作者:
M. Stubbs
通讯作者: M. Stubbs
触发学生富有成效的对话的可配置对话代理:CALL 领域的试点研究
DOI: 10.1007/s40593-013-0007-3
发表时间: 2013
影响因子: 4.9
作者:
Stergios Tegos;S. Demetriadis;T. Tsiatsos
通讯作者: T. Tsiatsos
一种新颖的基于多代理的聊天机器人方法来协调对话助理
DOI: 10.1007/978-3-030-53337-3_8
发表时间: 2020
期刊: Information Technology & Systems eJournal
影响因子: --
作者:
J. Zolitschka
通讯作者: J. Zolitschka
创建人性化的聊天机器人:聊天机器人开发人员可以向 Webcare 员工学习如何采用人声对话
DOI: 10.1007/978-3-030-39540-7_4
发表时间: 2020
期刊: 2018 First International Conference on Artificial Intelligence for Industries (AI4I)
影响因子: --
作者:
Christine Liebrecht;C. V. Hooijdonk
通讯作者: C. V. Hooijdonk
在财富管理建议中使用多个代理从对话失败中恢复
DOI: 10.1007/978-3-319-95579-7_7
发表时间: 2018
期刊: 2018 First International Conference on Artificial Intelligence for Industries (AI4I)
影响因子: --
作者:
Heloisa Candello;Claudio S. Pinhanez
通讯作者: Claudio S. Pinhanez