Browse

BlahBlahBot: Facilitating Conversation between Strangers using a Chatbot with ML-infused Personalized Topic Suggestion

Cited 0 time in Web of Science Cited 3 time in Scopus
Issue Date
2021-05-08
Publisher
Association for Computing Machinery
Citation
Donghoon Shin, Sangwon Yoon, Soomin Kim, and Joonhwan Lee. 2021. BlahBlahBot: Facilitating Conversation between Strangers using a Chatbot with ML-infused Personalized Topic Suggestion. Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery, New York, NY, USA, Article 409, 1–6. DOI:https://doi.org/10.1145/3411763.3451771
Keywords
chatbottopic suggestioncomputer-mediated communicationchat moderation
Abstract
It is a prevalent behavior of having a chat with strangers in online settings where people can easily gather. Yet, people often find it difficult to initiate and maintain conversation due to the lack of information about strangers. Hence, we aimed to facilitate conversation between the strangers with the use of machine learning (ML) algorithms and present BlahBlahBot, an ML-infused chatbot that moderates conversation between strangers with personalized topics. Based on social media posts, BlahBlahBot supports the conversation by suggesting topics that are likely to be of mutual interest between users. A user study with three groups (control, random topic chatbot, and BlahBlahBot; N=18) found the feasibility of BlahBlahBot in increasing both conversation quality and closeness to the partner, along with the factors that led to such increases from the user interview. Overall, our preliminary results imply that an ML-infused conversational agent can be effective for augmenting a dyadic conversation.
Language
English
URI
https://hdl.handle.net/10371/174852
DOI
https://doi.org/10.1145/3411763.3451771
Files in This Item:
Appears in Collections:
Student's Archives (학생저작물)Student's WorksUndergraduated (학부생)
  • mendeley

Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse