Overview

1 Recommender systems in action

Recommender systems are presented as a powerful but often invisible force shaping modern digital life, from shopping and travel to news, social media, and even dating. The chapter opens with a cautionary example of how a user can be gradually drawn toward extreme content through a cycle of clicking, engagement, and algorithmic suggestion, raising the question of whether the harm comes from the system, the user, or both.

At a high level, the chapter explains that recommender systems are algorithms that rank and curate content based on inferred relevance, usually learned from past behavior rather than explicit user instructions. It contrasts a world without recommendations—where people would have to manually sift through overwhelming amounts of irrelevant content—with one where platforms use personalization to save time, increase engagement, and direct attention. The chapter also shows how social media evolved from simple subscription-based feeds to networked sharing and then to fully algorithmic timelines that can insert content from outside a user’s immediate connections.

The larger concern is that recommendation is not neutral sorting but a form of amplification that can reshape attention, culture, and politics. Because platforms optimize for engagement, they can reinforce popularity, intensify emotions, and push users toward increasingly extreme or harmful material, creating feedback loops that are difficult to observe and even harder to measure. The chapter argues that understanding recommender systems requires examining both how content is selected and how it is ranked, since those choices determine which voices are boosted, which are ignored, and how platforms can influence society at scale.

The feedback loop between user and recommender systems. Users and recommender systems are in a mutual feedback loop, with the output of one serving as the input to the other. The output of the algorithm, the recommendations, is the input for the users. The users’ output, what they engage with, is a signal for the recommender. On top of that, both the user and the recommender system update their internal state. Users change their minds and evolve their preferences over time, while algorithms learn users’ preferences and try to align more with them.
The feedback loop between user and recommender systems. Users and recommender systems are in a mutual feedback loop, with the output of one serving as the input to the other. The output of the algorithm, the recommendations, is the input for the users. The users’ output, what they engage with, is a signal for the recommender. On top of that, both the user and the recommender system update their internal state. Users change their minds and evolve their preferences over time, while algorithms learn users’ preferences and try to align more with them.
Given a list of items, this recommender system reranks them according to a predefined metric, such as value to the user.
Given a list of items, this recommender system reranks them according to a predefined metric, such as value to the user.
Various social media models. In the Subscription model, the content is seen only by users who explicitly follow the content producer, with no options or resharing. In the Network model, users can also reshare content from users they follow, enabling the distribution of content outside of the immediate network. Finally, in the Algorithmic model, an algorithm can add content to users’ feeds, even with no direct connection to the content itself or its author.
Various social media models. In the Subscription model, the content is seen only by users who explicitly follow the content producer, with no options or resharing. In the Network model, users can also reshare content from users they follow, enabling the distribution of content outside of the immediate network. Finally, in the Algorithmic model, an algorithm can add content to users’ feeds, even with no direct connection to the content itself or its author.

Summary

  • Recommender systems are a powerful tool—and often underappreciated as a tool to order vast amounts of information for us. As a technology that pervades every application we interact with, RecSys have the power to influence our preferences in numerous domains, including highly consequential ones such as news consumption, dating choices, and financial decisions.
  • Social media was created as a tool to connect people on the internet—at first free of commercial interest—and to build location-free communities around shared interests.
  • The evolution of the internet has brought about more online platforms that have been able to connect an unprecedented number of people. Given the high running costs and the investors’ demands, platforms were nudged into finding ways of monetizing such efforts.
  • Social media platforms began experimenting with recommender systems as a means to align business and customer interests. By explicitly indicating business goals and taking into account users’ behavior, platforms were able to serve more relevant content to users—which made the users be more active and spend more time on the platforms.
  • The use of such algorithms raises important questions about algorithmic amplification, such as understanding which content is amplified more and why. Different types of platform designs enable various approaches to thinking about amplification.

FAQ

What are recommender systems, in simple terms?Recommender systems are algorithms that rank or order items so that the most relevant ones appear first. They are used to show you content, products, videos, posts, or other options that a platform predicts you will find useful or interesting.
Why are recommender systems so important in everyday life?They are embedded in many websites and apps we use, from streaming services and e-commerce sites to news platforms, social media, and dating apps. They shape what we buy, read, watch, travel to, and even who we may date.
What would life be like without recommender systems?Without recommender systems, users would have to sift through huge catalogs or endless feeds manually, which would be inefficient and overwhelming. RecSys help surface hidden gems and reduce the time spent on irrelevant content.
How do recommender systems and users influence each other?They form a feedback loop: the system recommends content, users interact with it, and those interactions become signals that the algorithm uses to make future recommendations. Over time, this mutual influence can change both the feed and the user’s preferences.
What is algorithmic amplification?Algorithmic amplification is the extra exposure a piece of content receives because of a recommendation algorithm. If a post is ranked highly or shown repeatedly, it becomes more amplified than content that is shown less often.
How do social media platforms use recommender systems differently from older media?Unlike traditional media, social media often lets users create, share, and reshuffle content at massive scale. Recommender systems then help decide what appears in feeds, including content from people or topics users do not explicitly follow.
What are the main social media models described in the chapter?The chapter describes three models: subscription, network, and algorithmic. In subscription, users only see content from accounts they follow; in network, reshared content can spread beyond the immediate audience; in algorithmic, the platform can add content to feeds through algorithmic curation even without a direct connection.
Why do recommender systems sometimes contribute to radicalization or harmful content spirals?Because they tend to learn from what users engage with, they can keep showing more of the same kind of content. If someone clicks on extreme or harmful material, the system may interpret that as interest and recommend increasingly similar content, creating a rabbit hole effect.
Why is measuring recommender systems so difficult?Because there is no universally agreed definition of “value,” and because algorithms and users constantly influence each other over time. Also, platforms typically optimize for measurable signals like engagement, which do not always reflect true quality or societal benefit.
What is the societal impact of recommender systems?They can concentrate attention, shape culture, influence public opinion, and affect democratic processes. They may also amplify misinformation, hate, or extreme views, while at the same time helping people discover communities, news, and content that matter to them.

pro $24.99 per month

  • access to all Manning books, MEAPs, liveVideos, liveProjects, and audiobooks!
  • choose one free eBook per month to keep
  • exclusive 50% discount on all purchases
  • renews monthly, pause or cancel renewal anytime

lite $19.99 per month

  • access to all Manning books, including MEAPs!

team

5, 10 or 20 seats+ for your team - learn more


Close
choose your plan

team

monthly
annual
$49.99
$499.99
only $41.67 per month
  • five seats for your team
  • access to all Manning books, MEAPs, liveVideos, liveProjects, and audiobooks!
  • choose another free product every time you renew
  • choose twelve free products per year
  • exclusive 50% discount on all purchases
  • renews monthly, pause or cancel renewal anytime
  • renews annually, pause or cancel renewal anytime
  • Hidden Influences Hidden Influences ebook for free
Close
choose your plan

team

monthly
annual
$49.99
$499.99
only $41.67 per month
  • five seats for your team
  • access to all Manning books, MEAPs, liveVideos, liveProjects, and audiobooks!
  • choose another free product every time you renew
  • choose twelve free products per year
  • exclusive 50% discount on all purchases
  • renews monthly, pause or cancel renewal anytime
  • renews annually, pause or cancel renewal anytime
  • Hidden Influences Hidden Influences ebook for free