Customer experience and sentiment analysis
Levy agrees, saying Jodange customers understand that listening to social media is important but now need help in filtering. “There is no longer the notion that trusted information only comes from The New York Times,” he says. “Once you get a handle on who is influencing your brand, that becomes actionable.” Influence analysis, analyzing digital breadcrumbs to see which individuals have the highest credibility and widest reach, should be a part of the overall text analytics strategy. By knowing in advance who the influencers are for your brand, you’ll be better prepared to manage crisis and opportunity effectively, reaching out to 20 key contacts instead of 10,000 questionable ones.
Taking sentiment out of the silo
There’s widespread agreement among vendors and analysts that text analysis is only as valuable as the actions it prompts. In a Forrester report from February 2009, called “Obstacles To Customer Experience Success,” a survey of 90 customer experience decision-makers from large North American firms found that 89 percent said that customer experience would be either very important or critical to their 2009 efforts, but a lack of cooperation across organizations remains a major obstacle.
When it comes to sentiment analysis, different functions are listening for different answers. A customer service manager needs insight into customer experience, a product manager wants to hear complaints or praise for features as well as product design ideas, and brand managers may be looking for competitive intelligence.
“It’s easy to turn on an application and get a feed of data,” says Sid Banerjee, CEO of Clarabridge, a provider of text mining software. “For our customers, acting on it is the hardest part of the equation. You must have an environment where people are culturally attuned to action.” Banerjee points out that where business intelligence solutions have traditionally been sold to the IT function, Clarabridge has had success selling its customer experience management solutions directly to the primary consumers of the data.
The challenge to the enterprise is to combine analysis of what is being said, by whom, with more structured customer intelligence data in order to develop a robust customer engagement strategy. Forrester’s Vittal says that to break sentiment analysis out of the silo, “The platforms must be open and integratable. Customer intelligence data is still siloed, and there is a complexity gap that must be overcome.”
Clarabridge’s December 2009 announcement of a partnership with pollster Harris Interactive is an illustration of how it can be done. The companies plan to combine unstructured data from opinions about President Obama’s healthcare reform initiative, posted on social media and other online sites, with public opinion as measured through structured survey research, to paint a truer picture of citizens’ emotions and decision factors on that volatile issue.
For companies that are just getting started with sentiment analysis, Radian6’s LeBrun suggests what he terms “the Yellow Brick Road” approach. “You have to pick up the social phone and listen to what’s being said, analyze and identify who the influencers are,” he says. “Step two is to start responding, not just by data mining but by building community.”
The third step is participation. By moving from metrics to diagnostics—understanding not just what is being said, but the root causes behind it—a company can truly begin to capitalize on the promise of text analytics. It’s another arrow in the quiver that can help companies understand and respond to the messages their customers are sending, loud though not always clear.
Partial list of text analytics/sentiment analytics vendors
Teragram (a division of SAS)
To download the Alta Plana Text Analytics 2009 chart which shows the breadth of usage for text analytics tools go here: http://www.kmworld.com/downloads/60764/2085_chart-2.pdf