Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2610.10173

When Exposure Is Not Attention: Auditing the Preference-Exposure-Consumption Gap in Personalized News Recommenders

Woojin Park
View original source ↗Read source document ↗Export metadata ↓

Abstract

Personalized news platforms are often evaluated as if stated preferences, logged recommendation exposure, and click consumption form a single coherent pipeline. Collapsing these layers can distort audit conclusions: a platform may appear more aligned or diverse than observed click consumption supports, which can misdirect diversity governance or algorithmic intervention. We introduce a reusable Preference-Exposure-Consumption (PEC) audit framework that separates stated preference, observed weighted profile state, logged recommendation exposure, app-surface pathways, and click consumption under explicit observability boundaries. Using six months of logs from a deployed mobile news application, we audit 1,583 user profiles, 95,143 logged recommendation items, and 17,512 click events. Each trace type contributes distinct information; none directly substitutes for another. Preference-consumption alignment exceeds chance-based null baselines but captures only part of users' top-consumed category set. Logged recommendation lists contain clicked articles more often than a date-matched candidate-pool baseline predicts (11.29% vs 9.13%; top-5 lift 1.47x), but many clicks arrive through other app surfaces. Raw exposure-consumption diversity gaps shrink under count matching, yet concentration mismatch persists in the audit-eligible cohort (HHI gap 0.082). Together, the results show that audit conclusions change depending on whether platforms measure stated preference, logged exposure, or click consumption.

Explore related subjects

cs.SI

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Woojin Park. 2026-10-07. When Exposure Is Not Attention: Auditing the Preference-Exposure-Consumption Gap in Personalized News Recommenders. https://arxiv.org/abs/2610.10173

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

KEEP EXPLORING

Related papers

arXiv2026

Link Fraction Mixed Membership Reveals Community Diversity in Aggregated Social Networks

Community detection is a critical tool for understanding the mesoscopic structure of large-scale networks. However, when applied to aggregated or coarse-grained social networks, disjoint community partitions cannot capture the diverse composition of community memberships within aggregated nodes. While existing mixed membership methods alleviate this issue, they may detect communities that are highly sensitive to the aggregation resolution, not reliably reflecting the community structure of the underlying individual-level network. This paper presents the Link Fraction Mixed Membership (LFMM) method, which computes the mixed memberships of nodes in aggregated networks. Unlike existing mixed membership methods, LFMM is consistent under aggregation. Specifically, we show that it conserves community membership sums at different scales. The method is utilized to study a population-scale social network of the Netherlands, aggregated at different resolutions. Experiments reveal variation in community membership across different geographical regions and evolution over the last decade. In particular, we show how our method identifies large urban hubs that act as the melting pots of diverse, spatially remote communities.

cs.SI↗
arXiv2026

Identifying the Group to Intervene on to Maximize Effect Under Cross-Group Interference

In many networked systems, interventions applied to one group of units can induce substantial causal effects on another group through cross-group interference pathways. Despite its practical importance in domains such as public health, digital marketing, and social policy, the problem of identifying which intervention subset in a source group maximizes the benefit on a target group remains largely unaddressed. We formalize this problem as cross-group causal influence estimation and introduce the core-to-group causal effect (Co2G), a formally defined causal estimand that quantifies the contrast in target-group outcomes under intervention versus non-intervention on a candidate source subset. We establish the nonparametric identifiability of Co2G from observational network data using do-calculus under standard causal assumptions, and develop a graph neural network-based estimator that captures cross-group interference patterns. To navigate the combinatorial search space of candidate subsets, we propose CauMax, an uncertainty-aware causal effect maximization framework with two scalable selection algorithms: (i) CauMax-G, an iterative greedy search with Monte Carlo dropout-based lower confidence bounds, and (ii) CauMax-D, a differentiable gradient-based optimization via a concrete Gumbel-Softmax relaxation. Extensive experiments on semi-synthetic data over two real-world social-network topologies, complemented by a real-outcome validation on three additional networks, show that CauMax substantially reduces regret relative to structural and diffusion-based heuristics, by up to an order of magnitude at small budgets and consistently across all budgets, while remaining robust to the uncertainty-penalty weight.

cs.SI↗
arXiv2026

Transmission Neural Networks: Inhibitory and Excitatory Connections

This paper extends the Transmission Neural Network model proposed by Gao and Caines in [1]-[3] to incorporate inhibitory connections and neurotransmitter populations. The extended network model contains binary neuronal states, transmission dynamics, and inhibitory and excitatory connections. Under technical assumptions, we establish the characterization of the firing probabilities of neurons, and show that such a characterization considering inhibitions can be equivalently represented by a neural network where each neuron has a continuous state of dimension 2. Moreover, we incorporated neurotransmitter populations into the modeling and establish the limit network model when the number of neurotransmitters at all synaptic connections go to infinity. Finally, sufficient conditions for stability and contraction properties of the limit network model are established.

cs.SI↗