What Should Social Media Packages Include?
The Facebook algorithm, similarly to search engine algorithms, ranks all the posts that have the possibility of being shown on a user’s news feed based on how likely a user will have a positive reaction to that content. Facebook prioritises posts from friends over brands, to emphasise “meaningful interactions.”
Facebook’s news feed algorithm is a machine learning ranking system. However, it’s not just one algorithm, instead it’s a combination of multiple algorithms that work together in different phases.
Different parts of the algorithm are useful for a variety of things, such as, selecting “candidate” posts to show in a person’s news feed, eliminating posts with misinformation or clickbait, creating lists of friends that a person interacts with, topics that the person tends to engage with and then using all of these factors to rank (or not rank) posts in a user’s news feed. All of these different layers are applied in order to predict what a Facebook member is going to find most relevant.
The goal of the algorithms is to rank which posts show up in the news feed, the order they are in and to select the posts that a Facebook member is likely to be interested in, interact and engage with. To do this Facebook uses thousands of specifically designed ‘signals.’
One of these ranking signals that Facebook uses is the “characteristics” of a post. To do this, Facebook uses a feature or the quality of a post to determine whether this is the kind of thing that a user tends to interact with more or less.
For example, if a post is accompanied by an eye-catching and colourful image, and a member has a history of interacting with posts with colourful images, then the post will be ranked higher. The same will apply if the user prefers to interact with videos – in these cases video content will be ranked higher.
Whether the post has an image, a video, if friends of a user are tagged in the post, those and other characteristics of a post are used as a ranking factor for determining whether a post is going to be shown to a user and where it will be ranked on the main news feed.
Time is also a ranking factor which coincides with a relatively recent Facebook patent that states that how recently something was posted is allowed to be used as a ranking factor. The Facebook news feed patent this refers to is called, Selection and Presentation of News Stories Identifying External Content to Social Networking System Users.
The patent states that news stories may be ranked based on chronological data associated with interactions with the news stories. To ensure the most recently shared news stories have a higher ranking.
Furthermore, this patent confirms the value in posting the same post more than once during the course of a day. It may reach different people across different time periods and those who engage with the post can help it gain greater visibility.
Another ranking factor involves predicting whether a user will be likely to be interested in or engage with a post. Facebook uses a number of signals to make that prediction. This draws on information from past posts and people that the user has historically interacted with. Facebook uses these past interactions to enable additional predictions about future interactions.
Facebook also uses machine learning models to predict each of these different things. There’s a model that predicts what content a user will like, another model that predicts which post the user will comment on. Each of these forms of engagement will then receive a ranking score and are subsequently ranked. Any action a person rarely engages in (for instance, a ‘like’ prediction that’s very close to zero) automatically gets a minimal role in ranking, as the predicted value is very low. The last step in the ranking process is to ensure the diversity of the type of content that is shown in the news feed. This is essential to combat repetition.
Whether you’re starting from scratch, or you want help and advice with your social media feeds, our Social Media Marketing Agency can provide you with a targeted approach to ensure higher rankings. Call us today on 020 7100 0726.