Social Media Feed Elicitation

2026-02-20

AI Summary

Users often struggle to fully articulate their preferences for customized social media feeds, leading to blind spots in generated content. This work proposes a novel approach that integrates large language models with structured interactive interviews, introducing a needs-elicitation interview mechanism into this domain for the first time. Through a closed-loop dialogue process, the method helps users clarify ambiguous or missing preferences. Online experiments on BlueSky demonstrate that feeds generated using this approach significantly outperform those based on users’ manual descriptions, yielding higher user satisfaction and enhanced perceived control over their digital experience.

Technology Category

• Natural Language Processing: Generation
• Machine Learning: Learning Preferences or Rankings
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Web Mining and Content Analysis: Content-based information diffusion

Abstract

Social media users have repeatedly advocated for control over the currently opaque operations of feed algorithms. Large language models (LLMs) now offer the promise of custom-defined feeds--but users often fail to foresee the gaps and edge cases in how they define their custom feed. We introduce feed elicitation interviews, an interactive method that guides users through identifying these gaps and articulating their preferences to better author custom social media feeds. We deploy this approach in an online study to create custom BlueSky feeds and find that participants significantly prefer the feeds produced from their elicited preferences to those produced by users manually describing their feeds. Through feed elicitation interviews, we advance users' ability to control their social media experience, empowering them to describe and implement their desired feeds.

Problem

• social media feed
• user control
• algorithmic transparency
• preference elicitation
• custom feeds

Innovation

• feed elicitation
• custom social media feeds
• large language models
• user preference elicitation
• algorithmic transparency