Value Alignment of Social Media Ranking Algorithms

2025-09-17

AI Summary

Social media ranking algorithms often embed implicit individualistic value biases and lack explicit alignment with users’ fundamental values. To address this, we propose the first quantifiable and adjustable value-aligned ranking framework grounded in Schwartz’s theory of basic human values. Our method employs NLP techniques to infer latent value dimensions from posts, enables users to specify personalized weights across ten core values, and implements a weighted ranking algorithm to generate value-customized feeds. Two user studies (N=141, N=250) demonstrate that participants can significantly shift the value distribution of their feeds, with outcomes statistically distinct from engagement-driven baselines. Results confirm the framework’s value interpretability, controllability, and practical utility. This work establishes both a theoretical foundation and a reproducible technical pipeline for value-sensitive recommender systems.

Technology Category

• Humans and AI: Learning Human Values and Preferences
• Machine Learning: Learning Preferences or Rankings
• Search and Optimization: Algorithm Configuration

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

While social media feed rankings are primarily driven by engagement signals rather than any explicit value system, the resulting algorithmic feeds are not value-neutral: engagement may prioritize specific individualistic values. This paper presents an approach for social media feed value alignment. We adopt Schwartz's theory of Basic Human Values -- a broad set of human values that articulates complementary and opposing values forming the building blocks of many cultures -- and we implement an algorithmic approach that models and then ranks feeds by expressions of Schwartz's values in social media posts. Our approach enables controls where users can express weights on their desired values, combining these weights and post value expressions into a ranking that respects users' articulated trade-offs. Through controlled experiments (N=141 and N=250), we demonstrate that users can use these controls to architect feeds reflecting their desired values. Across users, value-ranked feeds align with personal values, diverging substantially from existing engagement-driven feeds.

Problem

• Aligning social media feed rankings with human values
• Enabling user control over value preferences in algorithmic feeds
• Diverging from engagement-driven feeds to reflect personal values

Innovation

• Algorithmic ranking based on Schwartz's human values
• User-controlled value weighting for personalized feed customization
• Value-aligned feeds diverging from engagement-driven algorithms