Data Stories: Stefan Papp of Blab on Predictive Social Intelligence

Data Stories is about telling cool stories about the amazing ways that social data is used. This week we’re interviewing Stefan Papp of Blab, a Gnip customer, about their predictive social analytics that are able to help customers understand the directions conversations online are headed in 24, 48, and 72 hour time frames. I absolutely loved this concept and wanted to understand more about how it worked.
Stefan Papp of Blab
1. Why did Blab decided to take a different approach instead of doing social media monitoring?

Typical social media monitoring tools use keyword-based searches – you put in your keyword and the tools return all historical results matching that keyword.  The catch is that you will only find the insights you are looking for. Our approach is to listen to the entire conversation as it organically evolves, allowing you to discover much more of what your users are discussing — including the unexpected insights you probably would not have thought to search for. Finding those non-obvious but vibrant discussions gives companies whole new opportunities to engage with their target audiences.

2. What makes social data a good source in predicting behavior?

When you monitor social data you have a unique opportunity to listen to the unfiltered personal voices of millions of users. This offers insight into not just what is trending in social but what people are really thinking and feeling; their beliefs and true opinions. Standard behavioral prediction methods use things like focus groups and polls. But these approaches have long been known to produce skewed data – both consciously and subconsciously, users tend to tailor their responses to what they think the “best” response should be. Social data has none of this user bias and as a result is an excellent source of raw unfiltered intelligence.

3. How do you think Blab fits into the trend of real-time marketing?

The challenge that real-time marketing presents is creating on-topic content and getting that content out the door before the conversation is old news. Blab not only monitors current conversations in real time but predicts which of those conversations are going to be hot 72 hours from now. This takes the reaction out of real-time marketing and for the first time gives control to the brand. Blabenables you to put relevant content in front of an engaged audience at the right time – before a conversation has grown so big that your voice can’t be heard. You can also strike a chord by engaging your audience in those non-obvious conversations happening right now that you would not have thought to join.

4. What’s some surprising findings companies have found when using Blab?

One of the major insights that companies have gained from using our Predictive Social Intelligence engine is how conversations evolve online. So many companies only think about Facebook and Twitter when they think social, but social is so much more than that. Blab enables you to watch a conversation evolve across the entire spectrum of social networks. You can follow a conversation that begins with a YouTube post, which then drives a larger conversation on Twitter, and ends up being predicted to explode on Tumblr 72 hours from now.  Without a holistic view like this companies can be led to believe that a conversation has ended when in fact it continues vibrantly on another untracked social platform.

Another interesting finding is that our clients get an unadulterated view of their standing in social discourse. One client, a global technology concern, was surprised and chagrined to find that while there was lively discussion around their competitors, there was no discussion at all about them in their area of expertise. As humbling as that was, it became a call to action and fueled enthusiasm for engaging more effectively. Blab helped that company discover a negative and use that knowledge to improve their position.

5. Clearly, Blab has huge implications when it comes to crisis communications. One of the things that has amazed me about social media is that you don’t need a huge following to start a fuss about a brand. How does Blab separate the wheat from the chaff when it comes to determining conversations that might spike?

We use two unique methods to identify truly relevant conversations and to make accurate predictions on when a conversation will spike.  First, we throw NLP out the window and use a proprietary contextual classification approach to find the conversations that are related to a given topic. Rather than filtering out words like “got” we let our engine tell us if a term or phrase should be included. And guess what? There is a thriving “got” conversation among people who are passionate about “Game of Thrones.” We embrace acronyms, slang, abbreviations and sarcasm in a language agnostic manner (from Klingon to emoticon). The result is that we give you a picture of the whole conversation, unfiltered yet relevant. The second unique method is our proprietary approach to determining which conversations will spike or cool down. As conversations ebb and flow on the social canvas they establish patterns of historical facts. We’ve discovered that regardless of the topic, these patterns tend to repeat themselves. So while there are a huge number of them, the universe of conversation patterns is not infinite. When we see a familiar pattern we can predict, and often with high confidence, how a conversation will progress up to 72 hours into the future.

Taken together, Blab gives brands the ability to find potentially troubling conversations as they emerge; to determine if action is important by predicting which conversation is likely to take off; to engage that conversation or take other remedial action; and to know if the engagement is having an impact by watching to see if the prediction of growth turns into a prediction of decline for the troubling conversation.

If you’re interested in more data stories, please check out some of our other interviews.

  1. Hilary Mason of bitly on how data science adds value
  2. Blake Shaw of Foursquare on how Foursquare is a microscope for cities
  3. Liv Buli of Next Big Sound on being the world’s first data music journalist
  4. Christian Rudder of OKCupid on data science and dating
  5. Harper Reed of Obama for America on data and politics