Algorithms will use machine-learning to deliver more authentic and relevant conversations to users’ feeds.
This week, LinkedIn has announced its latest modifications to its news feed algorithms in a bid to improve user experience.
The professional social networking platform confirmed the changes on its blog page, and outlined how its algorithms will now work to deliver more authentic conversations to its users.
At the heart of the feed sits a machine learning algorithm that works to identify the best conversations for our members. In a fraction of a second, the algorithm scores tens of thousands of posts and ranks the most relevant at the top of the feed.
Filtering through for what matters
At its heart, the new algorithm will sort through content published by users, finding a shared common ground to improve the overall experience.
LinkedIn prioritises users by filtering through direct interactions, direct connections, such as co-workers, and information on profiles to gauge interests and common experiences. The ‘talking about’ section rewards conversations which are ‘authentic’ and have ‘constructive back and forth’, while common groups, hashtags, and pages are also considered.
People You Know, Talking About Things You Care About
This is the ethos steering the new changes. And whilst the algorithm has the theory, it will ultimately be down to the users to put it into practice.
In another blog post outlining the algorithm updates, Pete Davies, Consumer Product at LinkedIn, shares his best practices to make the most of them.
- Post things that encourage a response. For example, if you’re posting a link, express an opinion with it.
- Think about using the best type of post for the topic. Despite the rumors, the algorithm doesn’t favor any particular format. We have video, images, multi-images, text and long-form articles. More are on the way.
- Use @mentions to pull other people you know into a conversation when you think they’ll have something valuable to add. Be thoughtful: only mention people that you think are likely to respond, max five is a good rule of thumb.
- Engage in the conversation, respond to commenters and encourage back and forth.
Matthew Berks is a Digital Marketing Assistant at Red Website Design, the UK’s leading low-cost website design company.