Compass: Continuously Aligning Social Media Feeds via In-Situ Reflections

2026-08-04

AI Summary

This work addresses the tendency of social media recommendation systems to prioritize users’ impulsive reactions over their reflective, authentic preferences, a gap exacerbated by the temporal misalignment between explicit preferences and behavioral signals. To bridge this divide, the authors propose a lightweight, in-situ reflection mechanism that operates without requiring explicit user initiation. By embedding subtle prompts directly within the content feed, the system encourages real-time preference articulation and reflection. Concurrently, it periodically simulates behavioral signals to dynamically recalibrate recommendations, establishing a closed-loop alignment between user-reflected preferences and system outputs. A 10-day field study on YouTube Shorts (N=15) demonstrates that this approach significantly enhances reflective consumption, enables iterative preference refinement, and improves recommendation alignment—all while preserving a seamless and natural browsing experience.

Abstract

Social media recommendation feeds often optimize for users' immediate impulses rather than preferences they would hold after deeper reflection. Some systems address this misalignment by incorporating users' explicit preferences via a configuration page or in-feed controls instead of just behavioral signals. However, users typically have evolving preferences, and their stated preferences and behavior naturally diverge, necessitating continuous reflection and feed realignment. But existing strategies require the user to take initiative and are often effortful; as a result, in practice they are rarely invoked. We present Compass, a system that aligns a user's feed with their reflective preferences by helping users reflect on and articulate their preferences given their behavior. To enable continuous reflection during everyday browsing, Compass surfaces in-situ reflections via lightweight notifications, while feed alignment is achieved by periodically simulating behavioral signals and directly manipulating feed content. We embedded Compass within YouTube Shorts and compared it against a baseline without continuous support through a 10-day field study (N=15). We found that Compass promoted more reflective and purposeful feed consumption, iterative preference adjustment, and stronger feed alignment, without sacrificing the casual nature of feed browsing.

Problem

• social media feeds
• reflective preferences
• preference alignment
• user behavior
• continuous reflection

Innovation

• in-situ reflection
• feed alignment
• reflective preferences
• continuous preference adjustment
• lightweight notifications