Detecting Coordinated Activities Through Temporal, Multiplex, and Collaborative Analysis

2025-12-22

AI Summary

Existing single-account analysis methods fail to detect coordinated behavior in information manipulation due to their inability to capture cross-account, multi-modal temporal dependencies. Method: We propose a multimodal temporal collaborative analysis framework that constructs a multilayer network to model cross-modal interactions among accounts. It decouples interaction layers and incorporates an exponential decay temporal kernel to dynamically capture recurrent coordination patterns. A node-normalized collaboration model and a cross-layer evidence aggregation mechanism are designed to precisely characterize anomalous group-level temporal patterns that exceed chance-level synchronization. Contribution/Results: Unlike prior static or single-layer approaches, our framework is the first to enable time-aware multilayer collaborative modeling. Evaluated on multiple real-world coordinated activity datasets, it achieves significant improvements in detection accuracy and robustness. The framework provides an interpretable and scalable paradigm for identifying influence operations.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Data Mining & Knowledge Management: Mining of Visual, Multimedia & Multimodal Data

Application Category

• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Social Networks and Social Media: Social media analysis through the lenses of networks

Abstract

In the era of widespread online content consumption, effective detection of coordinated efforts is crucial for mitigating potential threats arising from information manipulation. Despite advances in isolating inauthentic and automated actors, the actions of individual accounts involved in influence campaigns may not stand out as anomalous if analyzed independently of the coordinated group. Given the collaborative nature of information operations, coordinated campaigns are better characterized by evidence of similar temporal behavioral patterns that extend beyond coincidental synchronicity across a group of accounts. We propose a framework to model complex coordination patterns across multiple online modalities. This framework utilizes multiplex networks to first decompose online activities into different interaction layers, and subsequently aggregate evidence of online coordination across the layers. In addition, we propose a time-aware collaboration model to capture patterns of online coordination for each modality. The proposed time-aware model builds upon the node-normalized collaboration model and accounts for repetitions of coordinated actions over different time intervals by employing an exponential decay temporal kernel. We validate our approach on multiple datasets featuring different coordinated activities. Our results demonstrate that a multiplex time-aware model excels in the identification of coordinating groups, outperforming previously proposed methods in coordinated activity detection.

Problem

• Detects coordinated online activities across multiple modalities
• Models temporal behavioral patterns using multiplex networks
• Identifies influence campaigns through collaborative analysis

Innovation

• Multiplex networks decompose activities into interaction layers
• Time-aware collaboration model employs exponential decay temporal kernel
• Aggregates coordination evidence across multiple online modalities