It Takes a Village: Integrating an Adaptive Chatbot into an Online Gaming Community

要旨

While the majority of research in chatbot design has focused on creating chatbots that engage with users one-on-one, less work has focused on the design of conversational agents for online communities. In this paper we present results from a three week test of a social chatbot in an established online community. During this study, the chatbot "grew up" from "birth" through its teenage years, engaging with community members and "learning" vocabulary from their conversations. We discuss the design of this chatbot, how users' interactions with it evolved over the course of the study, and how it impacted the community as a whole. We discuss how we addressed challenges in developing a chatbot whose vocabulary could be shaped by users, and conclude with implications for the role of machine learning in social interactions in online communities and potential future directions for design of community-based chatbots.

キーワード
chatbot
interaction design
machine learning
AI
BabyBot
Twitch
community interaction
long-term study
著者
Joseph Seering
Carnegie Mellon University, Pittsburgh, PA, USA
Michal Luria
Carnegie Mellon University, Pittsburgh, PA, USA
Connie Ye
Carnegie Mellon University, Pittsburgh, PA, USA
Geoff Kaufman
Carnegie Mellon University, Pittsburgh, PA, USA
Jessica Hammer
Carnegie Mellon University, Pittsburgh, PA, USA
DOI

10.1145/3313831.3376708

論文URL

https://doi.org/10.1145/3313831.3376708

会議: CHI 2020

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2020.acm.org/)

セッション: Chatbots

Paper session
306AB
5 件の発表
2020-04-30 20:00:00
2020-04-30 21:15:00
日本語まとめ
読み込み中…