You are here:  Home  >  Data Blogs | Information From Enterprise Leaders  >  Current Article

Text and Sentiment Analytics Team In Servicing The Customer Experience

By   /  November 5, 2012  /  No Comments

Did you ever take a survey and wonder if anyone actually was paying attention to your input? Here’s a tip: If it’s more than 20 questions, ignore it, advises Sam Keninger, director of product marketing at customer experience vendor Medallia.

“That’s the old market research way of doing things, and [the resulting big report compiled by market researchers] ends up in a binder on someone’s desk and no one will read it,” he says. A shorter survey – about a page long, and generally with a question about whether you’d recommend the product or service – signifies that attention will be paid.

Why? “The survey is an extension of the customer experience itself, so the shorter it can be the better,” Keninger says. And surveys can be shorter – and more effective at telling the company what it needs to know in real-time – when they can depend more on free-form text responses. They can do that when they can leverage both text and sentiment analytic engines to understand which topics are trending and to identify emerging issues, and ideally route those in real time to the front-lines where workers understand and can take action to fix the underlying problems.

Medallia takes two routes to those ends, whether for dealing with surveys, social media, inbound customer requests or the like. Its initial approach was rules-based text analytics – deep linguistic processing that continues to be a part of its solution. “It does a great job of identifying the what to focus on, particularly because we do key driver analysis and it really highlights which topics drive loyalty and which force people to be detractors,” says Keninger.

There are quantitative measures with the majority of data it works with (think of a survey that asks someone to rate their overall satisfaction, for instance), so it can do reporting based on a combination of score and topic. That is, it can understand whether, when a topic is talked about, it brings a loyalty score up or down, and by how much.

With the addition last week of the sentiment analytics feature, Medallia now  brings in a simultaneous analytics engine that takes a machine- learning based approach geared to doing a better job of understanding the whys behind the whats. Facebook, Twitter and other social media data, or inbound emails, for example, won’t have scores associated with that information, so a sentiment tool comes in handy for social media, as well as for more formal surveys.

“If you give a bad Google Plus or Yelp review, chances are the Medallia platform will uncover it in real-time, so don’t be surprised if general managers start giving you [as a dis-satisfied consumer] phone calls,” he says.

Medallia also has concentrated on making its solution usable to workers across the enterprise, not just corporate analysts, Keninger says – adding that that isn’t always the case with pure-play text analytics providers that other customer experience solutions providers may partner with.

Another area of focus for the company has been on mobile platforms, for the convenience both of those filling out the surveys and those charged with responding to those results. “A lot of people on the front lines are mobile – a general manager at a hotel doesn’t spend a lot of time in front of a computer,” he says. At the same time, giving its customers a mobile way to communicate with their own customers is generating a lot more feedback, he notes.

Ultimately, what Medallia wants to do with customers, he says, is drive so much comfort in the results and methodology from its analytics “that they can begin to rely more and more on it.” And stop asking so many survey questions.

About the author

Jennifer Zaino is a New York-based freelance writer specializing in business and technology journalism. She has been an executive editor at leading technology publications, including InformationWeek, where she spearheaded an award-winning news section, and Network Computing, where she helped develop online content strategies including review exclusives and analyst reports. Her freelance credentials include being a regular contributor of original content to The Semantic Web Blog; acting as a contributing writer to RFID Journal; and serving as executive editor at the Smart Architect Smart Enterprise Exchange group. Her work also has appeared in publications and on web sites including EdTech (K-12 and Higher Ed), Ingram Micro Channel Advisor, The CMO Site, and Federal Computer Week.

You might also like...

Property Graphs: The Swiss Army Knife of Data Modeling

Read More →