IBM's Watson artificial intelligence platform is getting a new enhancement that will help the system detect human emotion in customer service situations.
According to a blog post published Thursday, IBM Watson distinguished engineer and master inventor Rama Akkiraju said the new Tone Analyzer for Customer Engagement tool is designed to help customer service agents and chatbots craft appropriate responses to frustrated, sad, or satisfied customers.
Through linguistic analysis, the tool can pick up on seven different types of tone via conversations with customer service agents and chatbots: frustration, satisfaction, excitement, politeness, impoliteness, sadness and sympathy. The system also claims to be able to detect these sentiments in emojis, emoticons, and slang.
The Tone Analyzer was developed with a machine learning algorithm that trained on customer support conversations on Twitter. It also detects how tones progress throughout conversations, and offers suggestions on when agents should be more sympathetic, polite, or excited during an interaction.
"The new feature makes a chatbot tone-aware, enabling it to provide unique responses to frustrated, sad, or satisfied customers," Akkiraju said in the blog post. "For example, it can respond to sadness with, 'I'm sorry you are upset about this problem," but to satisfaction with, 'I'm glad you are satisfied with our service.'"
IBM has made a concerted effort this week to defend its Watson business after Jefferies analyst James Kisner published a stinging critique of the cognitive platform and IBM's ability to boost adoption and maintain AI talent internally.
IBM CFO Martin Schroeter said Wednesday that Watson is finding use cases in government as well as financial services. And the IBM Services Platform with Watson will also bolster adoption.
"We saw Watson deployments continue to expand globally. The cognitive opportunity is a global one. It's not centered in New York or Boston or Silicon Valley. We can't just look and listen in those places," said Schroeter.