Aumann–Shapley path-integral attribution at million-agent scale shows small visibility-biased panels structurally misattribute nonlinear social emergence, and no global rescaling can reconcile them.
A.et al.Exposure to opposing views on social media can increase political polarization.Proceedings of the National Academy of Sciences115, 9216–9221 (2018)
10 Pith papers cite this work, alongside 1,784 external citations. Polarity classification is still indexing.
10
Pith papers citing it
1,784
external citations · OpenAlex
citation-role summary
background 2
citation-polarity summary
years
2026 10roles
background 2polarities
background 2representative citing papers
Tenant comments on Dutch housing association Facebook posts cluster into six discourse types, and organizational context—not post style—predicts which type appears.
U.S. economic news sentiment has shifted from a reactive to a persistent process over 45 years, with longer residence times in optimistic or pessimistic regimes.
Inequality in online user engagement, quantified via KL-divergence, inverse coefficient of variation, and log-Gini on bipartite networks, remains stable over time across multiple platforms and interaction types.
Republican posts are more toxic than Democratic ones, but Democratic content draws more toxic replies due to higher volume of Republican cross-partisan engagement.
An AI system that elicits personal experiences and visualizes policy support increased perceived legitimacy and perspective-taking in collective decisions despite unfavorable outcomes.
LLMs fail to emulate human belief dynamics: they mismatch initial distributions and show higher conformity than humans in network interactions.
A heterogeneous ensemble of XLM-RoBERTa-large and mDeBERTa-v3-base with independent task modeling and class weighting is reported as effective for multilingual, multicultural, and multievent online polarization detection.
citing papers explorer
-
Attributing Emergence in Million-Agent Systems
Aumann–Shapley path-integral attribution at million-agent scale shows small visibility-biased panels structurally misattribute nonlinear social emergence, and no global rescaling can reconcile them.
-
Does online sustainability communication shape public discourse? Insights from six years of tenant-housing provider interactions
Tenant comments on Dutch housing association Facebook posts cluster into six discourse types, and organizational context—not post style—predicts which type appears.
-
Stable Sentiment and Persistent Dynamics in U.S. Economic News over 45 Years
U.S. economic news sentiment has shifted from a reactive to a persistent process over 45 years, with longer residence times in optimistic or pessimistic regimes.
-
Persistent Structural Inequality of Online Interactions Across Platforms
Inequality in online user engagement, quantified via KL-divergence, inverse coefficient of variation, and log-Gini on bipartite networks, remains stable over time across multiple platforms and interaction types.
-
"F*** You Biden": Cross-Partisan Electoral Toxicity on X
Republican posts are more toxic than Democratic ones, but Democratic content draws more toxic replies due to higher volume of Republican cross-partisan engagement.
-
AI and Collective Decisions: Strengthening Legitimacy and Losers' Consent
An AI system that elicits personal experiences and visualizes policy support increased perceived legitimacy and perspective-taking in collective decisions despite unfavorable outcomes.
-
Can LLMs Emulate Human Belief Dynamics?
LLMs fail to emulate human belief dynamics: they mismatch initial distributions and show higher conformity than humans in network interactions.
-
YEZE at SemEval-2026 Task 9: Detecting Multilingual, Multicultural and Multievent Online Polarization via Heterogeneous Ensembling
A heterogeneous ensemble of XLM-RoBERTa-large and mDeBERTa-v3-base with independent task modeling and class weighting is reported as effective for multilingual, multicultural, and multievent online polarization detection.
- Divergent Paths to Depolarization: Dialogue Design Shapes the Intergroup Attitudinal Effects of AI-Assisted Political Argumentation
- BiAxisBias: Evaluating LLM Bias Beyond a Single Prompt and a Single Explanation