To maximize your performance on any digital platform, you need to create your content in line with its search system, ensuring that your posts show up when people go looking for the products and/or services you offer.

There's no exception there, either. In 2016, Pinterest reported that it was facilitating more than two billion searches every month. Then, in 2016, Pinterest only had around 100 million users, and while Pinterest hasn't provided any official update on this stat, we can assume, as the platform now closes in on 300 million active users, that it's significantly increased on that.

And if you want to maximise the performance of your Pins, you will want to make sure that your Pins are being surfaced around your key terms.

We published a high-level view some time ago of how Pinterest's search system works, but this week, we have a technical rundown direct from Pinterest of how it is using the text elements of Pins in order to give more relevant experiences.
Pinterest claims its algorithm can capture the following annotations (remember: EN = English, Pinterest captures annotations in 28 languages):

(EN, sloth sanctuary, 0.99)
(EN, sloths, 0.95)
(EN, costa rica, 0.90)
(EN, carribean, 0.85)
(EN, animals, 0.80)
(EN, travel, 0.80)
The important point here is that some of these words are not actually used within the Pin – 'Carribean' isn't mentioned explicitly in the user-created caption, neither are 'animal' or 'travel'. These terms are derivations based on the probability of them possibly being relevant search matches for the extracted words – so 'visiting' might have a relation with 'travel', 'sloths' with 'animals', etc.

With this comes the need to ensure your Pin descriptions are accurate and in line with keywords and terms specific to the image of the Pin. The system at Pinterest is advanced enough to make some relevant connections, but it needs the key terms that will accurately allow the Pin to be displayed.

Pinterest gathers its text information from a variety of sources from within each Pin:

Pin title, description, URL
Board name and description
Page title and description of the link
Search queries that frequently lead to clicks on the Pin
Names of objects detected in the image using a visual classifier
You can’t control the visual recognition element, which Pinterest uses to match products via its Lens-based tools, but the others are all reliant on your input when posting.

Using data it discovers in each Pin, its software then extracts the most probable information points to match-and filters out those that are not relevant.

For instance, using the description of the Pin above:

"The Sloth Sanctuary in Costa Rica is the only sloth sanctuary in the world. Click to read more about my journey there + sees pics of baby sloths!
From that description, Pinterest will eliminate annotations such as "world", "journey" and "read" which do not make good keywords and are not relevant to the Pin. That does not mean you shouldn't use such descriptors, but that's a reminder of how important using relevant, unique keywords is in order to help classify your content.