You are here:  Home  >  Data Education  >  Current Article

PolyVista Technology Digs Deep Into Sentiment

By   /  October 28, 2013  /  No Comments

rsz_polyvSamsung Galaxy S4 or Apple iPhone 5? Many users are contemplating which smartphone upgrade is the right one for them. PolyVista, a BI text analytics tool that specializes in finding insights and sentiment in text-based data like online reviews, social media, blogs and surveys, wants to help out. It just published the results it gleaned from its PolyVista Zoom review analysis technology, which looked at online review text and analyzed each topic for positive and negative sentiment.

While both garnered more positive than negative commentary on social media, it concludes that the Galaxy S4 got a slight — 8 percent — edge over the iPhone 5.

That’s something both Apple and Samsung would like to know, too. And providing insights like that “from either structured or unstructured data to a business-person with a minimal amount of work by them” is what the company is aiming for, says Shahbaz Anwar, PolyVista CEO. Its value proposition, he says, is bringing text analytics via the cloud to companies that can’t afford to make the investments in expertise, talent software and infrastructure to do it in-house, particularly in verticals such as high-tech and services.

But Apple and Samsung probably would like to go deeper into understanding why things added up the way they added up. While other text analytics solutions that seek to unveil sentiment tend to focus on the monitoring alone, says Anwar, PolyVista tries to deliver a more comprehensive answer.

“If you ask them why is it positive or negative, they may not be able to tell you that, or if the trend is going in the wrong direction, what corrections do you need to make,” he says. “We’re trying to make it so we give them all the information they need that they don’t even have to ask any more additional questions.”

There is value in monitoring, but even more so in telling precisely the reason why someone’s commentary is negative, he says. The recent iPhone vs. Galaxy comparison, for instance, honed in on the latter’s battery life and phone quality as advantages for users who need those capabilities, while noting that topics like performance, where Apple scored high, weren’t even mentioned in the context of Samsung’s offering, helping lead to a conclusion that the iPhone might be better for power users who need a high performance smartphone.

Getting to that comprehensiveness, he says, involves improving on some tried-and-true algorithms, in natural language processing, data mining, and pattern recognition for example. But PolyVista, he says, also has focused hard on the data harvesting problem, and believes it has a strong advantage over competitors there. “The biggest problem in all this is data cleaning, the pre-processing,” he says. “That’s the heart of the system. If that’s not done right everything that happens downstream is affected.”

Among the solution’s capabilities, he notes, is ensuring the cleanliness of data when structured and unstructured information is integrated together, as they might be in pulling insights together from a survey. “Most customers want to integrate their own CRM data with survey data for a particular product,” and PolyVista has developed its own fuzzy matching algorithms to ensure that what something is called in an internal CRM or other database and what a customer calls it in a survey in freeform text are aligned.

PolyVista’s technology can be implemented in either a public or private cloud configuration.

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...

Is Data Governance Solely About Controls on Data?

Read More →