Text Mining Firms’ Golden Opportunity

NEW YORK In April, when Domino’s suddenly had to deal with a YouTube video featuring employees doing disgusting things to its food, it was bad for the pizza chain’s business.

But Domino’s problem turned out to be good for business for a fast-growing segment: companies that track Web chatter. In particular, text mining firms like Lexalytics, Clarabridge and Visible Technologies say they have seen a spike in interest for their automated software programs.

Text mining, which is already used by some Wall Street traders to track issues that could affect stock prices, is now employed by marketers including Cisco, Hormel, Microsoft and Intuit as a sort of blunt instrument to gauge online sentiment about a brand.

While none of the companies claim their software can get a precise read 100 percent of the time, they do claim an accuracy rate of between 60 and 80 percent. Jeff Catlin, CEO of Lexalytics, which developed a proprietary text-mining system for Cisco, said such a solution is needed because there’s just too much information — whether on blogs, in news stories, on Twitter or elsewhere — for people to digest in real time. “If you look at reading a single story, a human will be better than a machine,” he said, but if it comes to reading 100 stories, “if a machine gets it right seven out of 10 times, you’ll be able to predict the overall sentiment.”

Not everyone, however, believes text mining is a silver bullet. Adam Nash, vp, search and platform products at LinkedIn, said his company has received a lot of requests to add an interpretation feature to its popular Company Buzz tool, which tracks conversations on Twitter. But, he added, “it’s something easy to do badly.”

Steve Rappaport, knowledge solutions director at the Advertising Research Foundation, cautioned that text mining needs to be used with care. “It requires understanding what measures and indicators are truly measuring and indicating,” he said.

Despite their perceived limitations, automated tools for listening to branding messages is a growth industry right now. Suresh Vittal, principal analyst with Forrester Research, said the market for such solutions is around $150 million and “it’s growing at a very healthy rate right now.” Last week, the industry got another shot in the arm with the entry of Microsoft, a client of Visible Technologies, which announced a program called Looking Glass, which tracks such messages for marketers and advertisers.

While it’s unclear what Microsoft’s entry into the category will mean for Visible, Vittal said it’s a net positive for the industry: “Anytime Microsoft enters a space, it’s validation.”

As Microsoft’s early interest in text mining shows, tech companies were early adopters of the technology. Intuit, for instance, has been using a text-mining solution from Clarabridge for about three years, according to Chris Jones, Intuit’s analytics infrastructure manager. However, it has mostly used text analytics to monitor inbound calls from customers.

But adoption is spreading beyond tech. Sarah Hofstetter, svp, emerging media and client strategy at the digital marketing agency 360i, said there’s been an uptick of interest since the Domino’s incident. “Fear has been the core of the motivation for daily active listening,” she said. “The challenge is information overload. You can set up alerts to the point of crashing your inbox. … It depends on the frequency of conversations about your brand and your threshold for pain.”