Our Data Tool Predicted a Donald Trump Win 4 Weeks Ahead of the Election…

We built an engine that measures Engagement Energy by mining Facebook Pages focused on businesses, organizations, communities and causes. Engagement Energy is measured by taking the normal Facebook data and scoring it using our proprietary algorithm. This algorithm is intentionally agnostic to traditional marketing demographics like race, gender, age and location. It is purely a measure of how engaged a community is as a whole as well as how engaged individuals are with a particular account.

In July we hooked up the Facebook Pages for Donald Trump and Hillary Clinton as a data test. The results were fascinating. We instantly knew how many people Liked, Commented and Shared posts from their respective pages. This allowed us to track and score each community throughout the Election Cycle. 

Screenshot from our Data Dashboard reflecting Facebook tallies.


As the weeks went by, our test to verify Active Engagement ended. We would periodically checked back in, out of curiosity. Mostly our data showed both candidates in an Engagement boxing match. We started noticing that the Donald Trump community was growing at a slightly faster rate than the Hillary Clinton community. 

The most important point to understand about what makes our data unique is our Active Engagement Scoring Algorithm. This algorithm is based on Time. Actions are “Rated and Scored” depending on how much time Users spend on any action. Passive views and/or lurking is not counted. In this case the trackable actions are Likes, Comments and Shares. A Time value is generated for each action type and is adjusted according to our internal scoring mechanism to generate the Engagement Energy score.  custom inputs are in development.

4 weeks before the election this pattern was very noticeable and it was reflected in their energy scores. This was when it became apparent that our analysis might be predicting the next President of the United States of America. Initially our response was simply that our tech and scoring system were too early in development. We would wait and see the outcome. In the meantime, communities that we had close contact with would provide conceptualized data for comparison.

On November 9th we realized we were ignoring a key indicator and indeed our engine accurately reflected the grass roots phenomenon that was happening across the country. We immediately starting organizing our data so that we could show some our story.

Engagement Energy from July 1 to November 9 for Donald Trump.

djt_6month

Engagement Energy from July 1 to November 9 for Hillary Clinton.

hrc_6month
Engagement Energy from July 1 to November 9 Combined and adjusted to track important timeline events.

djt_hrc_overlay

In the above line graphs, you can see the story emerging. Donald Trump took the lead significantly around the debates. The first giant spike happens the day after Presidential Debate #2. Hillary Clinton’s energy after this point ceased to be competitive. 3 times, the Donald Trump Community doubled the Hillary Clinton Community’s best score.

Nov 9 Community Final Scores with Facebook Post Feed

djt_hrc_final
Right after the election the Donald Trump Community achieved a Total Energy of 1 Billion which more than doubles the Hillary Clinton Community Energy of 438 Million Energy. These are all time measurements including the whole history of each account. Understanding these numbers in relation to the election we need to understand the relative Energy output from days connected to significant events during the Election Race.

Nov 9 Community Final Scores with Facebook Post Feed

djt_hrc_timeline 

This Energy Timeline was used to create the combined line graph above. Clearly the post Presidential Debate #3 social media outreach combined with the James Comey announcement created a significant Engagement Energy lead for the Donald Trump Community while depressing the Hillary Clinton Community.

This overview of the Engagement Energy comparisons for these communities reveals some interesting insights and inspires furthers questions. More blog posts to follow as we dig into how our tool predicted Donald Trump as the winner of this election agnostic to skin color, age, gender and location.

Upcoming Article Topics

What was the difference in their Facebook strategies? – DJT HRC Quantitative and Qualitative Post Content Comparison
What differences are there to be learned about their respective communities? – DJT HRC Member Cross Comparison

What do we know about these members? – DJT HRC Brand Comparisons

How does the Data Engine work? – Engagement Scoring Overview and Verification

How to apply these learnings to other communities? – Community Engagement Guidelines

Advertisements

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s