The latest issue of MIT's Technology Review features a story about the advanced analytics AT&T is using to eavesdrop on disgruntled customers via Twitter. AT&T researchers have developed software that "finds complaints about network problems on the social network (which now has 175 million users) and extracts the approximate time the tweet was sent and the location of its sender," the article states. The telecom giant, which won an exclusive contract with Apple to provide network services for the iPhone in 2007, is using the Twitter analytics data to prioritize where it sends crews to fix problems.
"Wang and colleagues use two levels of filtering to find tweets by frustrated customers, and they do this by tapping into the programming interface tools Twitter makes freely available," the article states. "A general set of queries pulls in every tweet related to AT&T's mobile service before a more rigorous set of rules homes in on those relating to service quality, for example messages containing words like 'call dropped' or '3G.' This automated method was around 90 percent accurate at identifying genuine complaints, the researchers found."
This combination of techniques and tools has picked up on issues that wouldn't otherwise have been reported and has detected issues around 20 minutes earlier, on average, than a customer service call came in, the article reports.
Many banks monitor Twitter for customer complaints and a large proportion use social media analytics software (offered by SAS, IBM, Radian6, Attensity and others). But as far as we know, few add time and location data to pinpoint problems at specific branches or ATMs. This kind of analytics work could potentially help banks' IT departments schedule repair and support work in a customer-friendly way.
P.S. The wags at Read Write Web have invited Twits to get creative and submit AT&T complaints in haiku form. First submission: "The calls sounds like tin / sometimes I hear my own voice/ wait... this costs HOW much?!"