Why am I seeing this? Towards recognizing social media recommender systems with missing recommendations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Guidotti, Sabrina, Patania, Sabrina, Vizzari, Giuseppe, Ognibene, Dimitri, Donabauer, Gregor, Kruschwitz, Udo, Taibi, Davide
Format:	Preprint
Published:	2025
Subjects:	Information Retrieval Social and Information Networks
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866909580084117504
author	Guidotti, Sabrina Patania, Sabrina Vizzari, Giuseppe Ognibene, Dimitri Donabauer, Gregor Kruschwitz, Udo Taibi, Davide
author_facet	Guidotti, Sabrina Patania, Sabrina Vizzari, Giuseppe Ognibene, Dimitri Donabauer, Gregor Kruschwitz, Udo Taibi, Davide
contents	Social media plays a crucial role in shaping society, often amplifying polarization and spreading misinformation. These effects stem from complex dynamics involving user interactions, individual traits, and recommender algorithms driving content selection. Recommender systems, which significantly shape the content users see and decisions they make, offer an opportunity for intervention and regulation. However, assessing their impact is challenging due to algorithmic opacity and limited data availability. To effectively model user decision-making, it is crucial to recognize the recommender system adopted by the platform. This work introduces a method for Automatic Recommender Recognition using Graph Neural Networks (GNNs), based solely on network structure and observed behavior. To infer the hidden recommender, we first train a Recommender Neutral User model (RNU) using a GNN and an adapted hindsight academic network recommender, aiming to reduce reliance on the actual recommender in the data. We then generate several Recommender Hypothesis-specific Synthetic Datasets (RHSD) by combining the RNU with different known recommenders, producing ground truths for testing. Finally, we train Recommender Hypothesis-specific User models (RHU) under various hypotheses and compare each candidate with the original used to generate the RHSD. Our approach enables accurate detection of hidden recommenders and their influence on user behavior. Unlike audit-based methods, it captures system behavior directly, without ad hoc experiments that often fail to reflect real platforms. This study provides insights into how recommenders shape behavior, aiding efforts to reduce polarization and misinformation.
format	Preprint
id	arxiv_https___arxiv_org_abs_2504_11000
institution	arXiv
publishDate	2025
record_format	arxiv
spellingShingle	Why am I seeing this? Towards recognizing social media recommender systems with missing recommendations Guidotti, Sabrina Patania, Sabrina Vizzari, Giuseppe Ognibene, Dimitri Donabauer, Gregor Kruschwitz, Udo Taibi, Davide Information Retrieval Social and Information Networks Social media plays a crucial role in shaping society, often amplifying polarization and spreading misinformation. These effects stem from complex dynamics involving user interactions, individual traits, and recommender algorithms driving content selection. Recommender systems, which significantly shape the content users see and decisions they make, offer an opportunity for intervention and regulation. However, assessing their impact is challenging due to algorithmic opacity and limited data availability. To effectively model user decision-making, it is crucial to recognize the recommender system adopted by the platform. This work introduces a method for Automatic Recommender Recognition using Graph Neural Networks (GNNs), based solely on network structure and observed behavior. To infer the hidden recommender, we first train a Recommender Neutral User model (RNU) using a GNN and an adapted hindsight academic network recommender, aiming to reduce reliance on the actual recommender in the data. We then generate several Recommender Hypothesis-specific Synthetic Datasets (RHSD) by combining the RNU with different known recommenders, producing ground truths for testing. Finally, we train Recommender Hypothesis-specific User models (RHU) under various hypotheses and compare each candidate with the original used to generate the RHSD. Our approach enables accurate detection of hidden recommenders and their influence on user behavior. Unlike audit-based methods, it captures system behavior directly, without ad hoc experiments that often fail to reflect real platforms. This study provides insights into how recommenders shape behavior, aiding efforts to reduce polarization and misinformation.
title	Why am I seeing this? Towards recognizing social media recommender systems with missing recommendations
topic	Information Retrieval Social and Information Networks
url	https://arxiv.org/abs/2504.11000