Mar 15–18, 2020

Deploying chatbots and conversational analysis: learn what customers really want to know

Ian Beaver (Verint - Next IT), Aryn Sargent (Verint)
4:30pm5:00pm Monday, March 16, 2020
Location: LL20A

Who is this presentation for?

Non-technical or Business audience

Level

Non-technical

Description

In the customer service domain, virtual assistants and spoken dialog systems are increasingly deployed to cut costs. The conversation logs are typically only used for finding intent matching errors and improving the bot itself. However, by performing deeper analysis of the user turns in a conversation, your customers may be telling you much more about your company and the quality of your self-service offerings.

For example, the U.S. Army learned through deep analysis of its bot conversations that active military personnel were frequently asking it about Post Traumatic Stress Disorder (PTSD) symptoms and support, most likely because they were ashamed to talk with a human where they could be perceived as weak or pulled from duty. This was a surprise to the Army as the chatbot was intended for recruitment topics, but because of this discovery the Defense Health Agency was informed that they needed to provide more anonymous self-service PTSD resources for soldiers.

In this talk, vendor-agnostic trade-offs between build or buy for natural language self-service solutions such as chatbots will be highlighted. Once a bot is in place, motivations and techniques for deep conversational analysis are covered as well as several real world examples. The discoveries possible through these solutions have enabled companies to change their websites or customer service models to conform to what their users were really seeking for, increasing customer satisfaction and retention.

Prerequisite knowledge

None.

What you'll learn

Attendees will learn the real long term costs associated with IVAs, and the trade-offs between building in-house and buying a solution. Attendees will also learn the hidden gold mine of data from natural language interfaces which will help uncover the true voice of the customer and their primary needs.
Photo of Ian Beaver

Ian Beaver

Verint - Next IT

Ian Beaver, PhD is the Chief Scientist at Verint Intelligent Self Service, 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 multi-modal 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 Aryn Sargent

Aryn Sargent

Verint

Aryn Sargent is a data analyst with over 6 years of experience leading the identification and acceleration of successful solutions for enterprise conversational AI and Intelligent Virtual Assistants. Over the past six years, Aryn has held numerous roles within Verint Next IT including key positions within product management, product strategy, and data analysis. Today, Aryn leads strategic accounts and clients in identifying and defining IVA understanding and knowledge areas through the use of proprietary AI-powered tools to analyze unstructured conversational data. She is responsible for client’s automation strategies and evaluating, measuring and growing their success; defining tactical knowledge areas to achieve long-term vision. When she’s not working with data sets, she is well known for her green thumb in the garden and her love of dogs, fostering dogs in need until they find a loving, forever home.

Leave a Comment or Question

Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?

Join the conversation here (requires login)

Contact us

confreg@oreilly.com

For conference registration information and customer service

partners@oreilly.com

For more information on community discounts and trade opportunities with O’Reilly conferences

Become a sponsor

For information on exhibiting or sponsoring a conference

pr@oreilly.com

For media/analyst press inquires