Bob Moore is a Research Staff Member at IBM Research-Almaden, where he examines the intersection of human conversation and technology. Currently, he is developing a methodology for Conversational UX Design that applies the formal, qualitative models of natural human conversation, from the field of Conversation Analysis, to the design of conversational interfaces. He has developed a general Natural Conversation Framework, also implemented on the IBM Watson Conversation service, which defines a set of conversational UX patterns.

In addition to conversational systems, Bob explores the use of automated transcription technologies in the practice of Conversation Analysis research. With automated transcription, conversation analysts may be able to scale their methods to better exploit today’s big conversational data. However, current transcription technologies still lack robustness under many conditions and lack capabilities for capturing many aspects for naturally occurring talk, which conversation analysts require. Hence, automated transcription technologies offer only a partial solution for the conversation analyst.

In the past Bob has worked as a research scientist at Yahoo! Labs and at the Xerox Palo Alto Research Center (PARC) and as a game designer at The Multiverse Network. Bob’s past research includes studies of user interaction with search engines using eye-tracking, avatar-mediated interaction in virtual worlds, face-to-face interaction in print shops, work practices in automobile assembly plants and telephone-mediated interaction in survey call centers. Bob holds Ph.D., M.S. and B.A. degrees in sociology with concentrations in ethnomethodology, Conversation Analysis and ethnography.

With recent advances in natural language understanding techniques and far-field microphone arrays, natural language interfaces, such as chatbots and voice assistants, are emerging as a popular new way to interact with computers. They have made their way out of the research labs and into the pockets, desktops, cars and living rooms of the general public. But although such interfaces recognize bits of natural language, and even voice input, they generally lack conversational competence, or the ability to engage in natural conversation.

Today’s platforms provide sophisticated tools for analyzing language and retrieving knowledge, but they fail to provide adequate support for modeling social activity. This job is left to the user experience (UX) designer or software developer to figure out. Fortunately, instead of relying solely on commonsense knowledge of how conversation works, UX designers can rely, in part, on conversation science.

The Natural Conversation Framework (NCF), developed at IBM Research, provides concepts, principles and interaction patterns adapted from the Conversation Analysis (CA) literature for designers. Its pattern language in particular offers 100 generic conversational UX patterns fashioned after patterns of how humans naturally talk.