Out-of-Network Attention Dynamics on Bluesky

Andrea Failla; Veronica Mesina; Giulio Rossetti

Home/Archive/arXiv

arXiv · 2610.01971

Out-of-Network Attention Dynamics on Bluesky

Andrea Failla·Veronica Mesina·Giulio Rossetti

View original source ↗Read source document ↗Export metadata ↓

Abstract

Personalized social media commonly relies on explicit follow graphs to shape what content users encounter; yet how much attention crosses ties they have not formed remains largely undocumented at scale. We study this question on Bluesky, a large decentralized microblogging platform whose default feed relies on a simple, reverse-chronological content recommender. We analyze 173 million user-author interactions (likes, reposts, replies, and quotes) collected from a near-complete platform dump between February and September 2023. We decompose each interaction by attention-path length (already followed, relayed by a followed account, reachable within two follow-hops, or beyond) and find that 74.5% of interactions reach the user through an account they already follow. Measured by distance in the follow graph rather than by route, 80.6% of interaction lands within two follow hops, far beyond the 22.4% an expected-degree null predicts. We then characterize how exploration varies across users and over tenure. A broad-reaching minority generates three quarters of all exploratory activity, while aggregate declines in exploration with tenure mask three distinct individual trajectories. Finally, attention reaching beyond two hops converts into new follow ties at less than one third the rate of two-hop-local exploratory attention. Together, these results depict a platform where out-of-network exploration is substantial in volume but strongly constrained by network proximity and unlikely to translate into new social ties.

Explore related subjects

cs.SI cs.CY

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Andrea Failla, Veronica Mesina, Giulio Rossetti. 2026-10-01. Out-of-Network Attention Dynamics on Bluesky. https://arxiv.org/abs/2610.01971

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Beyond the Clique: Comparing Clique and Dowker Complexes for Co-occurrence Data in Learning Analytics

Learning analytics increasingly represents the relations in co-occurrence data---codes in a window of discourse, participants in a thread, tags on a post---as simplicial complexes and analyses them with persistent homology. The standard approach uses the clique complex. Because its simplices are determined by the pairwise network alone, it cannot distinguish "three elements co-occurred together" from "each of the three pairs co-occurred separately". The Dowker complex, in contrast, takes as simplices the sets of entities actually observed to co-occur. We compare analyses based on these two complexes. First, we show that, on the same 1-skeleton, the Dowker complex is a subcomplex of the clique complex, the map on first homology induced by the inclusion is surjective, and its kernel is generated by phantom triangles that never co-occurred; that is, the clique construction can only erase holes. We then test this on real data. On four Stack Exchange data sets, 46--91% of clique triangles are phantom and 522--1,970 holes are erased. On the example data of the learning analytics R packages tna/Nestimate, the first Betti number $β_1$ of the clique complex is 0 at every threshold, whereas the Dowker complex detects holes. Against a degree-preserving null model, the Dowker complex departs strongly in five of the six data sets. Moreover, this difference does not appear in the fixed-threshold analyses used in practice. We conclude that the construction should follow the data type and that, for observed groups, the Dowker complex is the appropriate choice; it fills a gap in current tooling. Code is available at https://github.com/igu-lab/beyond-the-clique.

cs.SI↗

arXiv2026

Degree-Corrected Joint Matrix Factorization for Multilayer Community Detection

Multilayer networks allow the modeling of interactions between the same entities across different contexts, such as temporal observations, varying settings, or interactions of different types. The goal of community detection in multilayer networks is to identify groups of nodes exhibiting similar connectivity patterns, which may vary across layers. We propose a method based on a joint nonnegative symmetric matrix trifactorization for community detection in multilayer networks, where each graph is approximated by a nonnegative symmetric matrix trifactorization. Our approach enforces constraints on the factor matrices so that communities are disjoint and shared across layers, while allowing each layer to have its own connectivity patterns and node degrees. This flexibility enables the model to capture both local and global structural variations across layers. We also develop an algorithm to efficiently solve this problem. We evaluate multilayer community detection methods using the multilayer degree-corrected stochastic block model (MDCBM), a flexible framework for generating realistic multilayer graphs with heterogeneous degrees and varying connectivity patterns. Experiments show that our method reliably detects communities across diverse regimes, whereas existing state-of-the-art approaches are often limited by restrictive structural assumptions.

cs.SI↗

arXiv2026

Mapping the Winds of Stance Dynamics using Potential Landscape Models

From changing fashion trends to views on world leaders and economic policies, large-scale shifts in group positions happen regularly and unexpectedly. How can we track these in the wild? How can we characterize them? Existing work has primarily leveraged stance detection to track shifts of specific groups on a single issue. However, such methods will only find shifts when they accurately pick exactly the right group and right issue. They do not capture the multi-dimensional, multi-resolution stance landscape in which these shifts actually happen. To better model drift and shift in public opinion, we require a framework that can track change at the population level, across a diverse range of issues. We propose a method to infer the potential landscape of stance dynamics, the gradient of which shows large-scale stance shifts, and apply it to show en masse stance shifts by prominent Canadian political elites across multiple platforms and years. We do this using large-scale stance detection to find stance expressions, latent-GP factor analysis, and potential landscape neural networks to find the potential landscape of that space. This allows us to find descriptive potential landscapes in a coherent, linear, low-dimensional space, where we can explain the specific characteristics of each dimension. As confirmation of the descriptive power of the model, it also has predictive power: it is significantly better than a simple baseline, and beats an auto-regressive forecasting method at short horizons, and a damped-Theta forecasting method at long horizons.

cs.SI↗