Pinterest has published a new overview of how a recent update to its algorithm has enabled it to better balance the types of content it shows in user home feeds, which will enable it to display a broader range of content, as opposed to simply relying on engagement data to drive its Pin recommendations.
The update is a new approach to Pinterest’s algorithm distribution, which will enable it to put more focus on, say, video content, or content from a more culturally diverse set of creators, without having to compromise user experience.
And if you’re looking to use Pinterest within your digital marketing efforts, it’s worth noting how the update could impact what your target audience is shown in the app.
As explained by Pinterest engineer Yaron Greif:
“Every day millions of Pinners visit the home feed to find inspiration on Pinterest. As a member of the home feed ranking team, it’s my job to not only figure out what relevant pins to show Pinners but also to make sure that those Pins will help maintain the health of the overall Pinterest ecosystem.”
So, Pinterest doesn’t only display content based on what you’ve engaged within the past, and the boards that you follow – it also seeks to highlight other content, relative to different goals.
So what are those other goals?
Sharing more video content is one:
“For instance, relative to ranking just for relevance, we might display more newly-created Pins to ensure our corpus doesn’t become stale, or more video Pins to surface actionable ideas from creators.”
As with all platforms, video content generates more engagement, and in Pinterest’s case, that likely also means that it gets an extra boost within the algorithm, beyond what each user has shared and engaged with in the past.
That’s an important consideration – if you want to maximize your reach on Pinterest, it’s worth both keeping your content flowing, with new, fresh Pins for the system to rank, but also to consider different content types, particularly video, and also new post options and tools that Pinterest may be looking to give more exposure to via algorithm ranking.
In order to achieve these expanded content exposure goals, Pinterest has implemented a new ‘controllable distribution’ system which is:
“…applied after the traditional ranking layer to control the tradeoff between areas like relevance, freshness, and creator goals by boosting and demoting the ranking scores of content types.”
How much influence that process has is not entirely clear, but as with video, Pinterest will seek to amplify certain types of content and creators at different times in order to meet variable goals, in addition to basic ranking based on each users’ engagement.
“Controllable distribution replaces hard-coded constants with a system where business owners can specify a global target for the percentage of impressions by content type. For example, if 4% of the feed is set to video, controllable distribution can then automatically determine how to achieve that distribution while still respecting Pinner content preferences. Importantly, controllable distribution adjusts the system continuously in realtime, so it does not grow stale.”
One of the key use cases for this will likely be to increase creator representation on the platform.
As Pinterest recently noted in its response to the #BlackLivesMatter protests:
“We are working to make sure the content people see on Pinterest represents people from diverse backgrounds. We are investing more resources into growing the diversity of content on our platform.”
Having the capacity implement more specific influence on algorithm-defined results will facilitate this, helping to ensure that Pinterest users are exposed to more content from different sources.
Though it also interesting to note a recent flaw uncovered in Pinterest’s algorithm recommendations, which has seen Pinterest hosting a range of offensive posts. As reported by OneZero, Pinterest’s process for addressing concerning content and trends is to block them from showing up in main feeds and in relevant searches.
“[While] Facebook and Twitter have opted to combat disinformation by removing millions of harmful posts and accounts, Pinterest chose another route, launching a search ban on “polluted content” in 2018 that started with anti-vaccination terms, cancer cures, and other health misinformation. Instead of completely eliminating this type of content, Pinterest’s search engine blocks results for keywords likely to produce misinformation.”
That process reduces the enforcement load on Pinterest, while also limiting the distribution of such content – but it also means that such material still exists on the platform, and can still be accessed via other search options, like, for example, Google search.
That means that Pinterest, while it’s addressing this content on front, is still facilitating the distribution of the same material in other, less obvious ways. OneZero‘s investigation found various Pins depicting underage girls, anti-vax content and more, which have largely gone unchecked, and may present another content challenge for Pinterest to address.
That’s a separate concern from algorithm distribution, but related in terms of how Pinterest surfaces and recommends (or doesn’t) certain types of content.
All up, this new algorithm update will enable Pinterest to put more focus on specific elements of its choosing within its Pin recommendations, without impacting user experience.
The full extent of this influence is impossible to quantify, but it is worth noting the changes to how Pinterest’s algorithm works, and considering what that might mean for your own approach.