Learning Speed: What Jeff Bezos, Elon Musk, And Bill Gates Know That Most People Don’t

Learning Speed: What Jeff Bezos, Elon Musk, And Bill Gates Know That Most People Don’t

Twitter Algorithm is now public. Here’s what I learned. The algorithm consists of mind-boggling 48 million parameters which has evolved over 2 decades of marvelous engineering serving 150 billion tweets to devices. The system is made up of three main stages: candidate sourcing, ranking, and filtering. These models aim to answer important questions about the Twitter network, such as, “What is the probability you will interact with another user in the future?”

Twitter runs a request 5 billion times a day and completes in under 1.5 seconds on average. For You timeline consists of 50% In-Network Tweets and 50% Out-of-Network Tweets on average, though this may vary from user to user. Twitter also uses a model called Real Graph to predict how likely you are to engage with a particular tweet based on your interactions with the author of the tweet. The first is to analyze the engagement of the people you follow and look for tweets similar to those they engage with. The second is to use a method called Embedding Spaces, where they generate numerical representations of users’ interests and tweet content to find similarities between users, tweets, and user-tweet pairs.

Twitter also has a tool called SimClusters, which finds communities of influential users based on custom algorithms. Tweets can be embedded into these communities based on their current popularity within that community. They start by gathering around 1500 Tweets that they think might be good candidates. To rank the Tweets, Twitter uses a big computer program called a neural network. This program has around 48 million parts that work together to make predictions about how people will interact with Tweets.

One interesting aspect of the Twitter algorithm is the focus on author diversity. The platform ensures that your feed doesn’t have too many consecutive tweets from a single author. This helps to provide a more diverse range of content and perspectives, preventing users from being trapped in an echo chamber. By including tweets from a variety of authors, Twitter aims to expose users to a wider range of ideas and opinions.

Another factor that influences the recommendations on Twitter is feedback-based fatigue. If you have provided negative feedback around a certain tweet, Twitter will lower its score to avoid showing it to you again. This helps to improve user experience by reducing the visibility of content that you have shown disinterest in. By taking into account user feedback, Twitter can fine-tune its recommendations and ensure that users are presented with content that aligns with their preferences.

Additionally, the engagement with tweets plays a significant role in the algorithm. Replies to tweets increase the chances of recommendations by 1x. This means that if you actively engage in conversations and discussions on Twitter, the platform is more likely to show you relevant tweets based on those interactions. Furthermore, including images or videos in tweets can boost recommendations by 2x. Visual content tends to capture attention and make tweets more engaging, leading to increased visibility and reach.

Twitter Blue, a paid subscription service, can boost recommendations by 2–4x. This indicates that users who opt for the premium features of Twitter are more likely to receive tailored recommendations that match their interests and preferences. By investing in the paid subscription, users can enhance their Twitter experience and gain access to additional benefits and personalized content.

Being part of a trusted circle, or having a group of users who frequently engage with your tweets, can boost recommendations by 3x. This highlights the importance of building a strong network and fostering connections on Twitter. When you have a group of followers who regularly interact with your content, it signals to the algorithm that your tweets are valuable and relevant, leading to increased visibility and recommendations.

Retweets from other users can boost recommendations by 20x. When your tweets are shared by others, it amplifies their reach and increases the likelihood of them being recommended to a wider audience. This demonstrates the power of social validation and the impact of viral content on the Twitter algorithm.

Likes on tweets can boost recommendations by 30x. The number of likes a tweet receives is a strong indicator of its popularity and quality. When a tweet accumulates a high number of likes, it signals to the algorithm that it is well-received by users, leading to increased recommendations and visibility.

In conclusion, the Twitter algorithm is a complex system that utilizes multiple stages and models to generate tailored recommendations for users. By understanding the key factors that influence the algorithm, such as author diversity, feedback-based fatigue, engagement with tweets, and social validation, users can optimize their Twitter experience and increase the visibility of their content. Here are three actionable advice:

1. Engage actively: Participate in conversations, reply to tweets, and foster connections with other users. By actively engaging on Twitter, you increase the chances of receiving relevant recommendations and building a strong network.

2. Use visual content: Incorporate images or videos in your tweets to make them more engaging and visually appealing. Visual content has a higher chance of being recommended, increasing its reach and visibility.

3. Build a trusted circle: Cultivate relationships with users who frequently engage with your tweets. Having a group of followers who regularly interact with your content can significantly boost recommendations and increase the visibility of your tweets.

By implementing these strategies and understanding the inner workings of the Twitter algorithm, you can enhance your Twitter experience and maximize the impact of your presence on the platform.