Recommender system in X inadvertently profiles ideological positions of users

• URL: http://arxiv.org/abs/2602.02624v1
• Date: Mon, 02 Feb 2026 16:22:56 GMT
• Title: Recommender system in X inadvertently profiles ideological positions of users
• Authors: Paul Bouchaud, Pedro Ramaciotti,
• Abstract summary: We use a data donation program, collecting more than 2.5 million friend recommendations made to 682 volunteers on X over a year.<n>Using publicly available knowledge on the architecture of the recommender, we inferred the positions of recommended users in its embedding space.<n>Our results show that the platform's recommender system produces a spatial ordering of users that is highly correlated with their Left-Right positions.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Studies on recommendations in social media have mainly analyzed the quality of recommended items (e.g., their diversity or biases) and the impact of recommendation policies (e.g., in comparison with purely chronological policies). We use a data donation program, collecting more than 2.5 million friend recommendations made to 682 volunteers on X over a year, to study instead how real-world recommenders learn, represent and process political and social attributes of users inside the so-called black boxes of AI systems. Using publicly available knowledge on the architecture of the recommender, we inferred the positions of recommended users in its embedding space. Leveraging ideology scaling calibrated with political survey data, we analyzed the political position of users in our study (N=26,509 among volunteers and recommended contacts) among several attributes, including age and gender. Our results show that the platform's recommender system produces a spatial ordering of users that is highly correlated with their Left-Right positions (Pearson rho=0.887, p-value < 0.0001), and that cannot be explained by socio-demographic attributes. These results open new possibilities for studying the interaction between human and AI systems. They also raise important questions linked to the legal definition of algorithmic profiling in data privacy regulation by blurring the line between active and passive profiling. We explore new constrained recommendation methods enabled by our results, limiting the political information in the recommender as a potential tool for privacy compliance capable of preserving recommendation relevance.

Related papers

• Let's Measure the Elephant in the Room: Facilitating Personalized Automated Analysis of Privacy Policies at Scale [14.986181740022106]
  PoliAnalyzer is a neuro-symbolic system that assists users with personalized privacy policy analysis.<n>It uses Natural Language Processing to extract formal representations of data usage practices from policy texts.<n>It can support automated personalized privacy policy analysis at scale using off-the-shelf NLP tools.
  arXiv  Detail & Related papers  (2025-07-15T20:19:33Z)
• Why am I seeing this? Towards recognizing social media recommender systems with missing recommendations [4.242821809663174]
  We introduce a method for Automatic Recommender Recognition using Graph Neural Networks (GNNs)<n>Our approach enables accurate detection of hidden recommenders and their influence on user behavior.<n>This study provides insights into how recommenders shape behavior, aiding efforts to reduce polarization and misinformation.
  arXiv  Detail & Related papers  (2025-04-15T09:16:17Z)
• Quantifying User Coherence: A Unified Framework for Cross-Domain Recommendation Analysis [69.37718774071793]
  This paper introduces novel information-theoretic measures for understanding recommender systems. We evaluate 7 recommendation algorithms across 9 datasets, revealing the relationships between our measures and standard performance metrics.
  arXiv  Detail & Related papers  (2024-10-03T13:02:07Z)
• CURE4Rec: A Benchmark for Recommendation Unlearning with Deeper Influence [55.21518669075263]
  CURE4Rec is the first comprehensive benchmark for recommendation unlearning evaluation.<n>We consider the deeper influence of unlearning on recommendation fairness and robustness towards data with varying impact levels.
  arXiv  Detail & Related papers  (2024-08-26T16:21:50Z)
• Transparency, Privacy, and Fairness in Recommender Systems [0.19036571490366497]
  This habilitation elaborates on aspects related to (i) transparency and cognitive models, (ii) privacy and limited preference information, and (iii) fairness and popularity bias in recommender systems.
  arXiv  Detail & Related papers  (2024-06-17T08:37:14Z)
• Measuring Strategization in Recommendation: Users Adapt Their Behavior to Shape Future Content [66.71102704873185]
  We test for user strategization by conducting a lab experiment and survey. We find strong evidence of strategization across outcome metrics, including participants' dwell time and use of "likes" Our findings suggest that platforms cannot ignore the effect of their algorithms on user behavior.
  arXiv  Detail & Related papers  (2024-05-09T07:36:08Z)
• How to Diversify any Personalized Recommender? [0.0]
  We introduce a novel approach to improve the diversity of Top-N recommendations while maintaining accuracy.<n>Our approach employs a user-centric pre-processing strategy aimed at exposing users to a wide array of content categories and topics.<n>Using pre-processed data for training leads to recommender systems achieving performance levels comparable to, and in some cases, better than those trained on original, unmodified data.
  arXiv  Detail & Related papers  (2024-05-03T15:02:55Z)
• Improving Recommendation System Serendipity Through Lexicase Selection [53.57498970940369]
  We propose a new serendipity metric to measure the presence of echo chambers and homophily in recommendation systems. We then attempt to improve the diversity-preservation qualities of well known recommendation techniques by adopting a parent selection algorithm known as lexicase selection. Our results show that lexicase selection, or a mixture of lexicase selection and ranking, outperforms its purely ranked counterparts in terms of personalization, coverage and our specifically designed serendipity benchmark.
  arXiv  Detail & Related papers  (2023-05-18T15:37:38Z)
• Two-Stage Neural Contextual Bandits for Personalised News Recommendation [50.3750507789989]
  Existing personalised news recommendation methods focus on exploiting user interests and ignores exploration in recommendation. We build on contextual bandits recommendation strategies which naturally address the exploitation-exploration trade-off. We use deep learning representations for users and news, and generalise the neural upper confidence bound (UCB) policies to generalised additive UCB and bilinear UCB.
  arXiv  Detail & Related papers  (2022-06-26T12:07:56Z)
• Random Walks with Erasure: Diversifying Personalized Recommendations on Social and Information Networks [4.007832851105161]
  We develop a novel recommendation framework with a goal of improving information diversity using a modified random walk exploration of the user-item graph. For recommending political content on social networks, we first propose a new model to estimate the ideological positions for both users and the content they share. Based on these estimated positions, we generate diversified personalized recommendations using our new random-walk based recommendation algorithm.
  arXiv  Detail & Related papers  (2021-02-18T21:53:32Z)
• A Survey on Knowledge Graph-Based Recommender Systems [65.50486149662564]
  We conduct a systematical survey of knowledge graph-based recommender systems. We focus on how the papers utilize the knowledge graph for accurate and explainable recommendation. We introduce datasets used in these works.
  arXiv  Detail & Related papers  (2020-02-28T02:26:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.