Stanford just published a report called “Computer calls can talk couch potatoes into walking” which is a great valuation of the automated call technology. The study compared calls by real people to automated calls encouraging sedentary adults to exercise.
It is interesting since it is conceptually similar to the technology which we provide at Silverlink Communications. They used Text to Speech (TTS) which can sound a little “computer-like” while we record our calls with voice talent. In their study, participants had to respond using the dial pad (e.g., press “1” if you have exercised today) while our calls respond to voice (e.g., say “one” if you have exercised today). We have studied the improvements in success rates on calls simply from using all recorded voice versus some TTS and seen a very positive lift. [It is obviously hard to record variable fields such as first and last name, but we have done some of that to improve results.] Additionally, given all the variables you can play with in a more sophisticated system – different voices, different speed of the message, dynamic paths, etc., it would be interesting to do that head to head comparison.
A couple of key takeaways from the article:
- Many of the participants in the program were over 55. [Which are your primary users of healthcare services.]
- Initially 80-85% of those in the program said that they preferred or needed a human after listening to the computer program. [What you hear from lots of people until they use it a few times.]
- Participants who lacked confidence in their abilities to be successful and who were less comfortable interacting with people did better with the computer voice. [A client of ours in the specialty pharmacy space was emphasizing this for certain therapy classes recently.]
- The computer voice was just as helpful for men and women.
“The goal was to get participants out walking at a brisk pace for 30 minutes most days of the week, or some other form of medium-intensity physical activity, for about 150 minutes a week, as recommended by the U.S. Surgeon General. They were divided into three groups: a control group that didn’t get calls, a group called by trained health educators and a group called by a computer delivering an interactive, individualized program similar to that being delivered by the health educators. Exercise levels were measured with the use of an accelerometer, which provides an estimate of physical activity amount as well as intensity.”