There’s a lot more you can learn by tapping into conversations.
“This call is being recorded for quality assurance.” It’s an all-too-predictable refrain for anyone who’s ever made a customer-service call. But what happens next?
There’s a lot more you can learn by tapping into conversations.
For years, companies have used software to mine these calls for what they reveal about customer satisfaction. Sentiment analysis tools, for example, scour call transcriptions for telltale keywords, organize the data, and assign an aggregate score. When scores dip below an assigned benchmark, companies can consider hiring more agents or making product upgrades.
These tools remain popular, but their impact is limited. “Companies love traditional sentiment analysis because it works and it’s relatively simple,” says Julie Wall, a professor of data science and artificial intelligence at the University of East London. “But there are many more features of conversations that we can use to make decisions beyond that.”
Enter artificial intelligence—and a more advanced form of customer-call analysis called conversational analytics. The software uses natural language processing (NLP) models to analyze everything expressed in a voice conversation, and has shown that it can significantly improve customer experience, more accurately predict future behavior, and help human agents get better at their jobs.
“The world is learning that there’s a lot more you can learn by tapping into conversations,” says Bruce Temkin, head of the Qualtrics XM Institute, a consultancy that works with large enterprise customers to improve customer and employee experience.