London-based human intelligence firm DataSift is evolving its social media analysis platform with the integration of machine learning-based algorithms. By doing so, DataSift says it can provide its customers with better insights into what people are saying about them on Facebook and Twitter.

Its new solution, called VEDO Intent, is designed to give marketers “more nuanced insights” while also shedding some light on what it calls “customer intent to purchase”. VEDO Intent is built on DataSift’s VEDO solution, a programmable intelligence engine that’s built into DataSift’s main data processing platform. The new solution allows customers to create advanced machine learning-based classifiers to deliver more actionable intelligence.

Previously, most companies have had to rely on humans to manually track and record what people are saying about them on social media, web discussions and in the news. It’s a laborious approach, and one that DataSift argues is extremely difficult to manage.

“We have a technology platform where we work in partnership with the world’s social networks to allow developers, marketing agencies or brands to do analysis of social media content at scale without them having to become masters of big data,” Tim Barker, head of product at DataSift, told Tech World.
“Our DataSift platform can process tens of thousands of items a second and aggregates that to provide insights into audiences and different topics.”

VEDO Intent employs an approach called Active Learning, which allows it to learn more about a brand and its customers. Social media posts and comments are classified into categories such as rant, rave, purchase intent, or churn, and VEDO Intent slowly builds a machine learning-based model that first suggests, then later fully automates the real-time classification of up to millions of social media posts. The end result is that VEDO Intent can deliver insights that companies simply wouldn’t have been able to access before.

Barker gave a few examples of the ways businesses could benefit. He said that an airline could, for example, use VEDO Intent to compare how its service stands up to those of rival airlines, and use the data to determine what it’s doing right and what aspects of its server need improving.

Barker notes that there are literally tens of millions of comments, posts and tweets made about companies on Facebook and Twitter every single day. In other words, it’s a veritable treasure trove of customer feedback that demands tapping into. DataSift also offers a solution called Topic Data that companies can use to find out exactly what people are saying about them on Facebook.

The company is also launching a forum to help developers and data scientists share statistical models that form the building blocks of advanced analysis. Helping guide researches to the keywords and hashtags they should be using in their analysis for example.

DataSift said its platform costs $1,000 a month for unlimited users.

Image credit: geralt via pixabay.com