There are quite a few reasons why an IVR solution is better than a traditional manpowered call center: an IVR system can accept calls 24/7, it always knows the right answer, it doesn’t get easily agitated or grumpy with callers and it can save companies a ton of time and money.

Now, we can add gathering customer feedback to the list of benefits.

Researchers Shuchih Ernet Chang and Yu-Teng Jang of the National Chung Hsing University in Taiwan have developed a program to determine customer satisfaction over the phone, named the Satisfaction Level Assessment System, or SLAS.

In their study, entitled “Assessing Customer Satisfaction in a V-Commerce Environment,” the team explains how the SLAS measures tone of voice, determines the caller’s emotion and associates that emotion with a level of overall satisfaction.

By measuring a variety of variables in sound wave patterns, the computer is able to match the overall tone of voice with a database of vocal tones that are each associated with a level of happiness and satisfaction.

From that, the system can store the data and determine overall trends within the IVR system, enabling developers to work out bugs and change structure to better suit callers’ needs.

The proposed method and system can detect customer satisfaction on the spot; i.e. it detects customer satisfaction in real time. Once we obtain the customer satisfaction level in a real-time v-commerce environment, timely feedback can be given to those relatively unhappy or unsatisfied customers for achieving the goal of timely service recovery.

What’s even more interesting about the system, though, is that despite the complexity of human emotion, the SLAS can better determine customer satisfaction during a call than a live person.

In the study, 20 people listening to the same 12 calls, attempting to match customer satisfaction level with reported results from the callers, only achieved an accuracy rate of 62.5%, whereas the machine was able to determine satisfaction with 83% accuracy.

Most research evaluates customer satisfaction level by asking customers to fill out satisfaction questionnaires, but fewer and fewer people would like to truly answer questionnaires. Hence, the proposed SLAS may indeed become a feasible alternative for evaluating customer satisfaction.

It seems that this new system tackles the biggest challenge facing IVR systems today: gathering real input and making sure the system is not only a good fit for the company, but callers are receiving the best experience the company can offer.