Cross-correlograms reveal timing patterns in social media behaviors
Inferring Temporal Dependencies from Social Time Series with the Cross-Correlogram
Social and Information Networks
Summary
Measuring how people influence each other over time can be tricky because social actions happen in bursts and change a lot. The researchers adapted a method from brain science called the cross-correlogram to better detect these time-based connections in social behavior. Their new approach adjusts for regular cycles in activity, like daily rhythms, which can hide real influence patterns. They showed their method works better than some common techniques and used it to find real delayed responses on Twitter linked to TV broadcast times.
What this means in practice
- •For social media analysts: Detect delayed influence patterns between topics across social platforms, even when regular daily activity cycles interfere.
- •For online marketing teams: Link social media activity peaks to scheduled broadcasts to optimize timing of promotional campaigns for maximum engagement.
Authors
Bridget Smart, Renaud Lambiotte, Takaaki Aoki, Ryota Kobayashi
Abstract
Characterizing temporal interactions in social systems is challenging because social behavior can be bursty and non-stationary, violating the stationarity assumptions of many methods used to measure temporal dependence. The cross-correlogram, an existing technique used to profile neural excitations and inhibitions, offers an interpretable alternative to methods such as Granger causality or co-occurrence, as it produces a full profile of lagged dependence directly from event times rather than a single summary statistic. We adapt the cross-correlogram by integrating functional models of behavior with data-driven temporal response profiling. By characterizing how periodic structure biases traditional cross-correlograms, we propose a correction based on smooth intensity functions, specified from a known functional form or estimated empirically. This approach provides a robust, interpretable estimator of temporal dependency profiles even when collective rhythms operate on timescales that overlap those of the interactions of interest. We demonstrate theoretically and through simulation that the proposed method recovers temporal dependencies in periodic regimes, outperforming interval-jitter and Granger causality methods. Finally, we apply the method to 3.1 million event times from X (formerly Twitter) collected between 2019 and 2020, demonstrating how cross-correlograms reveal delayed temporal relationships in collective online behavior that are missed by co-occurrence measures. For a subset of television-related hashtags, recovered delays align with known broadcast schedules, providing evidence that the proposed method captures genuine temporal structure rather than artifacts of shared attention cycles.