ABSTRACT
Despite a growing body of research about the design and use of conversational agents, existing work has almost exclusively focused on interactions between an agent and a human. Less is known about how an agent is perceived and used during human-human conversation. We compared conversations between dyads using AI-assisted and standard messaging apps and elicited qualitative feedback from users of the AI-assisted messaging app through interviews. We find discrepancies between the AI assistant's suggestions and the conversational content, which is also reflected in participant interviews. Our results are used to suggest some areas for improvement and future work in AI-assisted communication.
- Petter Bae Brandtzæg and Asbjørn Følstad. 2017. "Why People Use Chatbots." In International Conference on Internet Science, 377--392.Google Scholar
- David Coniam. 2014. "The linguistic accuracy of chatbots: usability from an ESL perspective." Text & Talk 34(5), 545--567.Google ScholarCross Ref
- Asbjørn Følstad and Petter Bae Brandtzæg. 2017. "Chatbots and the new world of HCI." interactions 24(4), 38--42. Google ScholarDigital Library
- Katherine Ibister, Hideyuki Nakanishi, Toru Ishida, and Cliff Nass. 2000. "Helper Agent: Designing an Assistant for Human-Human Interaction in a Virtual Meeting Space". CHI Letters 2(1), 57--64. Google ScholarDigital Library
- Nathan Ingraham. 2016. "Google stores 'transient' Allo messages until you delete them". Engadget. https://www.engadget.com/2016/09/21/googleallo-messages-privacy/Google Scholar
- Joseph Kim and Julie A. Shah. 2016. "Improving Team's Consistency of Understanding in Meetings". IEEE Transactions on Human-Machine Systems 46(5), 625--637.Google ScholarCross Ref
- Lorenz Cuno Klopfenstein, Saverio Delpriori, Silvia Malatini, and Alessandro Bogliolo. 2017. "The Rise of Bots: A Survey of Conversational Interfaces, Patterns, and Paradigms." In Proceedings of the 2017 Conference on Designing Interactive Systems, 555--565. Google ScholarDigital Library
- Daniel T. L. Shek. 2002. "Chinese adolescents' explanations of poverty: The perceived causes of poverty scale". Adolescence 37(148), 789--803.Google Scholar
- Aaron Smith. 2011. "Americans and Text Messaging". Pew Research Center. http://www.pewinternet.org/2011/09/19/americans-and-text-messaging/Google Scholar
- Tom Simonite. 2017. "Facebook's Perfect, Impossible Chatbot". MIT Technology Review. https://www.technologyreview.com/s/604117/facebooks-perfect-impossible-chatbot.Google Scholar
Index Terms
- AI-Supported Messaging: An Investigation of Human-Human Text Conversation with AI Support
Recommendations
Verbal cues of involvement in dyadic same-culture and cross-culture instant messaging conversations
CABS '14: Proceedings of the 5th ACM international conference on Collaboration across boundaries: culture, distance & technologyThis paper explores how people in same-culture and cross- culture pairs use verbal cues to express involvement in dyadic text-based Instant Messaging (IM) conversations. We report an experimental study with same-culture and cross-culture pairs of ...
Messaging design and beyond: learning from a user study on holiday greeting messages
Mobility '07: Proceedings of the 4th international conference on mobile technology, applications, and systems and the 1st international symposium on Computer human interaction in mobile technologyThe design of text messaging keeps the same ever since invented. However, the relevant user practice has already diverted from its intended use. The latest example is that through it people send holiday greetings to friends or acquaintances. In this ...
Punctuation in text messages may convey abruptness. Period
In contrast with face-to-face conversations, text messages lack extra-linguistic cues such as tone of voice and gestures. We explore the hypothesis that textisms, such as irregular punctuation, are used to fill this role. We extend the work of Gunraj, ...
Comments