The Science Behind TopicPulse FAQs

This article will answer several frequently asked questions about the science behind TopicPulse. If you have additional questions or curiosity, feel free to reach out to Futuri VIP Support.

How does TopicPulse decide when a topic should be categorized as Hot, Trending, Flat or Stop?

Our development team worked with the brightest minds at Edison Research to define when a topic should be categorized as Hot, Trending, Flat, or Stop. Edison Research is the firm that manages exit poll research for all of the major networks at every election season. That means they are specialists in managing large amounts of data in real-time.

We've put together an entire article (with charts, because we love charts) to answer this question. Click here for more information.

How does TopicPulse merge sources into a common "topic"?

TopicPulse uses latent semantic analysis to determine which posts and articles belong to a particular topic. Semantic analysis programmatically looks at words for patterns and common context. In addition, we have human moderators constantly reviewing TopicPulse for quality assurance.

How does TopicPulse get demographic information?

We use data from Facebook sharing and profiles, as well as Twitter data (when available). Plus, we look at the profile of people who are reading any news sources via Quantcast, which is like Scarborough for digital publishers, and Alexa, a qualitative research company owned by Amazon. We combine all of that available data into one easy-to-read graph.

The "core" demo in TopicPulse is determined by who is MOST engaged in a topic vs. the general audience. As an example, if 25-49 year olds are engaged, but the most active and engaged members of the social chatter are specifically 30-35 years old, we highlight the 30-35 part of the cell as the "core."

How does TopicPulse determine what appears in local market pulses?

Your local pulse is populated with geo-targeted content based on your specific area, content shared from media sources within that target area, and engagement generated from the area.

Did you find it helpful? Yes No

Send feedback
Sorry we couldn't be helpful. Help us improve this article with your feedback.