Temporal and Content Coupling Analysis of Social Media User Behavior

2026-04-30

AI Summary

This study uncovers the coupled mechanisms between temporal dynamics and content selection in social media users’ news consumption. By developing a multi-scale temporal-content analysis framework, it characterizes user behavior across macro (circadian rhythms), meso (inter-session intervals), and micro (intra-session actions) levels, integrating content preference modeling to elucidate interaction patterns. Leveraging large-scale real-world datasets from MIND and Adressa, and employing Fourier analysis alongside power-law and exponential distribution fitting, the work systematically reveals—for the first time—that user activity exhibits pronounced circadian rhythms, inter-session intervals follow a power-law distribution, and intra-session clicks conform to an exponential distribution. Furthermore, it identifies distinct user groups with divergent preference orientations and demonstrates how historical interests and content diversity differentially influence click behavior across varying activity periods.

Abstract

News consumption behavior is shaped by the coupling between temporal dynamics and content selection. This study proposes a multi-scale temporal-content framework and validates it on two large real-world news datasets, MIND and Adressa. Results reveal hierarchical temporal patterns. At the macroscale, Fourier modeling identifies clear circadian rhythms; at the mesoscale, session intervals follow a power-law distribution with $α\approx 1$; and at the microscale, within-session action counts and inter-action intervals follow exponential distributions with $λ\approx 0.3$ and $λ\approx 0.02$, respectively. Content analysis shows that clicks are mainly driven by historical interests, while this dependence weakens as content diversity increases. Temporal-content coupling further indicates that users' historical interests dominate active time periods in shaping behavior. Preference groups also differ: timeliness and entertainment-oriented users click more frequently and rely more on historical interests, whereas diversified users click less and are more sensitive to content diversity.

Problem

• temporal dynamics
• content selection
• user behavior
• news consumption
• temporal-content coupling

Innovation

• multi-scale temporal modeling
• temporal-content coupling
• user behavior analysis
• power-law distribution
• content diversity