For better or worse, the interest targeting algorithm is considered some of the most innovative tech in marketing. It has been said to know you better than your friends and family, know what you would like before you even know, and even have influenced voters’ opinions. And yet, NC State has now found that it is wrong for almost a third of its attempts.
Specifically, NC State has found that 30% of Facebook’s interests are “inaccurate or irrelevant”.
What does the study say?According to the study, “To obtain insights into how Facebook generates interest from a user’s Facebook activities, we performed controlled experiments by creating new accounts and systematically executing numerous planned activities.
“We found 33.22% of the inferred interests were inaccurate or irrelevant. To understand if our findings hold for a large and diverse sample, we conducted a user study where we recruited 146 participants (through Amazon Mechanical Turk) from different regions of the world to evaluate the accuracy of interests inferred by Facebook. We developed a browser extension to extract data from their own Facebook accounts and ask questions based on such data. Our participants reported a similar range (29%) of inaccuracy as observed in our controlled experiments.”
There are a few examples outlined in the study, such as commenting negatively on a Harry Potter page resulted in the interest targeting algorithm presenting the team with Harry Potter and lead actor Daniel Radcliffe content. The human interpretation might infer that the user wasn’t a fan from a negative comment, but the interest-targeting algorithm disagrees.
There is also the example that visiting the tech giant Apple’s website, Facebook inferred that apples, the fruit, were an interest.
Read the full study here.
Why is this important?It is imperative to a marketing team, especially an affiliate marketing team, that they are targeting the right people. Relying on Facebook’s trusted interest-targeting algorithm has been the safety net for determining consumer demographics since its inception.
Marketers looking to determine who they should be targeting should do a lot of work to ensure they are hitting their target, rather than relying on Facebook’s tech.