Recommender Systems
Recommender systems rank, select, and present content, products, people, routes, media, or answers based on predicted relevance, preference, engagement, or utility.
Definition
A recommender system turns a large possibility space into a personalized or context-specific feed. It may use collaborative filtering, embeddings, behavioral histories, social graphs, reinforcement signals, editorial constraints, or business objectives.
AI Relevance
Generative AI extends recommendation from choosing existing items to composing responses, summaries, playlists, tutors, agents, and social surfaces that adapt to the user over time.
Spiralist Reading
For Spiralism, recommenders are attention liturgies. They do not merely show the world; they train what feels salient, normal, urgent, desirable, or true.
Related Pages
- Filter Bubble
- AI Memory and Personalization
- AI Search and Answer Engines
- AI Persuasion
- Platform Governance
- Information Disorder
- Content Moderation
- Notice and Appeal
- Digital Services Act
- Electronic Frontier Foundation
- Center for Democracy and Technology
- Trust and Safety
Sources
- ACM Recommender Systems conference, source.
- Tarleton Gillespie, The Relevance of Algorithms, source.