Did you notice a change in your LinkedIn engagement lately? Maybe you see the same post for the fifth or sixth time by the same person, or maybe you get fewer notifications?

There is a reason for that. According to LinkedIn expert Richard van der Blom, LinkedIn has been changing its algorithm and notifications of late, which has significantly changed a few aspects on how it distributes posts and shows people what they are most likely to engage with.

According to van der Blom's latest analysis:
LinkedIn is indeed showing you more content from the people and Pages you engage most with
LinkedIn will now and more spot focus in hashtag engagement to bring valuable topics to the attention of the user
What LinkedIn no longer needs to notify you for:
Posts now gaining more ground overtime rather than the most seen on the first day. According to van der Blom, posts are now gaining much traction on the second and third day since they were posted
So why is that?

A new overview by LinkedIn reveals that it recently revamped the algorithm to base it on more engagement signals, including how users interact with hashtags, who they engage with in the app, and even what they interact with, namely individual posts.

According to LinkedIn:

Our Homepage Feed generates billion-record datasets over millions of sparse IDs on a daily basis. For improving the performance and personalization of the feed, we have incorporated the representation of sparse IDs as features into the recommendation algorithms that power these products.

Which is a technical way of saying that it added more signals into the mix, with "sparse IDs," in this case, referring to hashtags, users and posts, among other interactions that include Likes and shares. Indeed, LinkedIn claims it's increased the parameters for its feed recommendation architecture 500x.

"Our method is to change the large corpus sparse id features into a more compact embedding space, in which hundreds of millions of parameters in embedding lookup tables are trained by multi-billions of records. An embedding represents high-dimensional categorical data in a continuous low-dimensional space, capturing huge relations and patterns while reducing computational complexity.". The following example shows that members who share similar preferences or often interact with the same type of content or a similar group of other members will tend to have similar embeddings and, therefore, a smaller distance in the embedding space. This allows the system to discern and recommend content that is contextually relevant or aligns with member preferences.
That's a lot of words, yes, and technical papers aren't the best for trying to determine the practical meaning of what you and I should care about. But basically, you're probably seeing fewer posts from really small groups of people, and on more focused topics, because that is probably what you are likely going to engage with most, and LinkedIn's algorithm now has far more factors it has to factor into account in order to predict likely engagement.
Which ought to make your LinkedIn feed more interesting and actually aligned with your personal areas of interest. Which may or may not be perfect for discovery, since a lot of activity is generated with relations to colleagues, former and current, not the current topics of interest, but weighing hashtag engagement, for instance will be critical in this regard, ideally balancing people you know directly with the topics of most relevance to you at a given time.

But sure, it may mean you see more of the same sorts of people in your feed as a result.

The solution? Interact more using hashtags, and append your input to relevant conversations you add your thoughts to, and take part in the app. The more you do so, the more signals you are sending the algorithm in terms of what interests you, and it is now perhaps better attuned than ever to your specific focus topics.

And apparently it's paying off because LinkedIn saw a 41% year-over-year increase in original content shares last year, in addition to "record levels" of engagement according to the platform, that parent company Microsoft continues to report within its quarterly performance updates.

As more people seek an alternative to Twitter and the changes that Elon Musk is making it seems, LinkedIn has been a primary beneficiary while its constant algorithm updates are also keeping everyone sticking, coming back more often.

Sharpening up focus on key topics of interest could well be the secret to making your LinkedIn experience shine, while, in terms of posting, it is also useful to play up the value of community engagement- and you can build on that wherever possible, responding to comments, using relevant hashtags, sharing topical updates, etc.

No secret code, if you will, to cracking the algorithm, but LinkedIn now knows more about who is interested in your content and is increasingly likely to show it to them in-stream.