The IBM natural conversation framework: a new paradigm for conversational UX design

Click to increase image sizeClick to decrease image size

Disclosure statement

No potential conflict of interest was reported by the author(s).

Correction Statement

This article has been republished with minor changes. These changes do not impact the academic content of the article.

Notes

¹ Also, known as the Alma Design System (Moore et al., 2020).

² “Recipient design” is a feature of human conversation by which speakers tailor their utterances specifically to individual recipients in multiple ways (Sacks et al., 1974).

³ Current speech recognition and natural language understanding technology lack the ability to detect the full range of trouble sources necessary for all major repair types.

⁴ For reviews of conversational platforms, see this Gartner Peer Insights page: https://www.gartner.com/reviews/market/conversational-platforms

⁵ An alternative study design for the socializing scenario would be one in which the reduced features buddy leads the conversation by latching the initiation of next topics onto its responses to prior topics, as is also commonly done with chatbots. This would enable users to discover more content but would entirely prevent them from leading the conversation.

⁶ Chatbots reviewed included Boostai, https://www.boost.ai/;IBM’s AskHR, USCIS Emma, HP chatbot.

⁷ The Sequence Abort pattern has a slot for Abort Acknowledgment, which in this case contains the response, “Suit yourself!” Other randomly selected responses include, “Whatever you say” and “If you say so.” If designers consider these responses inappropriate for their use cases, they can change the Abort Acknowledgment to something more innocuous like “Okay” or to an empty response.

Additional information

Notes on contributors

Robert J. Moore

Robert J. Moore works as a senior research scientist at IBM Research-Almaden, in San Jose, California, and previously worked at Yahoo! Labs and Xerox PARC. His research examines the intersections of social interaction and technology. Currently, he adapts conversation science to the design of natural conversation interfaces. Robert holds Ph.D., M.S. and B.A. degrees in sociology with concentrations in ethnomethodology, Conversation Analysis and ethnography.

Sungeun An

Sungeun An is a Ph.D. candidate in Human-Centered Computing at the Georgia Institute of Technology. Her research interests lie at the intersection of Cognitive Science, AI, and Learning Science & Technology. Her work focuses on understanding user behavior through log data and analysis in exploratory learning environments.

Guang-Jie Ren

Guang-Jie Ren leads the re*THINK Enterprise team in IBM Research with a passion in creating user-centered, research-driven, evidence-based innovations to address industry challenges. His work leverages a wide range of disciplines from business and management to design and engineering to social science and machine learning. Trained as an industrial engineer, he received his PhD degree in Engineering & Management from the University of Cambridge before joining IBM in 2009.