Measuring online attention over time by persistence recency and re-emergence
Measuring Time-Horizon Engagement Effectiveness: Persistence, Recency, and Re-Emergence
Social and Information NetworksComputers and Society
Summary
People usually look at online attention by counting how much activity happens overall or at the peak, but this misses important details about timing. This paper introduces a way to track attention by focusing on how long it lasts (persistence), how recent it is (recency), and whether it comes back after a break (re-emergence). The authors tested their approach on YouTube videos and Wikipedia page views to show it reveals different patterns of attention that typical measures hide. They also found that false claims online don't have a unique attention pattern, showing these time-based aspects matter separately.
What this means in practice
- •For social media analysts: Analyze engagement patterns of online videos or posts by separating long-lasting, recent, and returning attention to better understand audience behavior.
- •For online content moderators: Use distinct temporal patterns of attention to support investigations into how misinformation spreads or resurfaces over time.
Authors
Bonnie Rushing, Ethan Anderson, William Hersch, Shouhuai Xu
Abstract
Online attention is commonly summarized using cumulative volume, peak activity, or arithmetic averages, but such measures can obscure differences between activity that is sustained over time, concentrated near the present, or renewed after dormancy. This paper introduces the Time-Horizon Engagement Effectiveness (TH-EE) framework, which constructs interpretable temporal profiles of online attention by distinguishing three related but non-equivalent properties: persistence, recency, and re-emergence. We evaluate the framework through controlled engagement traces, a proof-of-concept application to 1,850 YouTube videos across 37 topics (18 cohorts selected a priori as exemplars of persistent, acute, cyclical, and recently originating attention, and 19 cohorts corresponding to authoritatively debunked claims), and an event-level validation on eleven years of daily Wikipedia pageview series for the same topics. The controlled analyses show that the framework distinguishes distributed activity from concentrated bursts, introduces temporal-order sensitivity through recency weighting, and identifies renewed activity after a defined dormant interval. On the event-level series, the framework's reactivations co-locate with Kleinberg burst onsets, and PELT change points far more often than chance. The YouTube application shows that debunked-claim cohorts do not occupy a unique region of temporal-profile space; they exhibit heterogeneous patterns that overlap substantially with benign topics. These results support treating persistence, recency, and re-emergence as separate dimensions of online attention. TH-EE is a descriptive and comparative measurement framework, not a classifier of misinformation, coordination, intent, or content veracity.