Presented By O’Reilly and Intel AI
Put AI to Work
April 29-30, 2018: Training
April 30-May 2, 2018: Tutorials & Conference
New York, NY

From here to "Her": Evolving chatbot interactions to meet the relational needs of humans

Ian Beaver (Verint), Cynthia Freeman (Next IT)
4:50pm–5:30pm Wednesday, May 2, 2018
Average rating: ****.
(4.60, 5 ratings)

Who is this presentation for?

  • Virtual assistant designers, human-computer interface designers, and customer service strategists

Prerequisite knowledge

  • A basic understanding of virtual assistants

What you'll learn

  • Understand how users attempt to relate to modern virtual assistants and the issues that must be addressed to create a truly conversational agent


Conversation is emerging as the next great human-machine interface. A study published in 2017 investigated the presence and effect of relational language on intelligent virtual agents (IVAs). Using data from large-scale, real-world enterprise IVA implementations, the study shows that people are increasingly attempting to relate to chatbots as they would to human agents.

Ian Beaver and Cynthia Freeman outline the challenges faced by the AI industry to relate to humans in the way they relate to each other. Ian and Cynthia discuss the raw data and findings of the study, which measured the usage of relational strategies such as emotional expressions, backstory, and justification in conversations between humans and AI-powered customer service agents. Highlighting findings from the study, they demonstrate relational strategies used by humans in conversation and explain how virtual assistants must evolve to communicate effectively. They also cover the implications of these findings for anyone who is deploying or thinking of deploying an IVA—especially those who are deploying to support their business. Ian and Cynthia also discuss the challenges facing developers of chatbots and IVAs as people increasingly speak to machines in the same manner they speak to human agents and address the research questions these findings raise and how the data can be used by the AI community.

Photo of Ian Beaver

Ian Beaver


Ian Beaver is a chief scientist at Verint, a provider of conversational AI systems for enterprise businesses. Ian has been publishing discoveries in the field of AI since 2005 on topics surrounding human–computer interactions such as gesture recognition, user preference learning, and communication with multimodal automated assistants. Ian has presented his work at various academic and industry conferences and authored over 30 patents within the field of human language technology. His extensive experience and access to large volumes of real-world, human–machine conversation data for his research has made him a leading voice in conversational analysis of dialog systems. Ian currently leads a team in finding ways to optimize human productivity by way of automation and augmentation, using symbiotic relationships with machines.

Photo of Cynthia  Freeman

Cynthia Freeman

Next IT

Cynthia Freeman is a research and software engineer at Next IT corporation, a developer of conversational AI systems. She is currently a graduate student in computer science at the University of New Mexico. She holds an MS in applied mathematics from the University of Washington and a BS in mathematics from Gonzaga University.