D-Tracker: Modeling Interest Diffusion in Social Activity Tensor Data Streams

2025-05-01

Knowledge Discovery and Data Mining

AI Summary

This work addresses the challenge of modeling and forecasting high-dimensional, multi-dynamic (trend, seasonality, and cross-regional interest diffusion) social activity tensor data streams. We propose a hyperparameter-free, interpretable, and real-time temporal modeling and forecasting method. Our core innovation is the first integration of partial differential equations (PDEs) into a dynamic tensor decomposition framework, explicitly characterizing the continuous spatial diffusion of user interest across geography—enabling automatic disentanglement and physics-based interpretability. Leveraging online streaming learning and differentiable tensor optimization, our method achieves constant computational complexity with respect to sequence length. Extensive experiments on Google Trends and COVID-19 infection data demonstrate substantial improvements in forecasting accuracy over state-of-the-art baselines, accurate recovery of inter-regional interest propagation pathways, and an order-of-magnitude speedup in inference latency.

Technology Category

• Machine Learning: Matrix & Tensor Methods
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Content-based information diffusion

Abstract

Large quantities of social activity data, such as weekly web search volumes and the number of new infections with infectious diseases, reflect peoples' interests and activities. It is important to discover temporal patterns from such data and to forecast future activities accurately. However, modeling and forecasting social activity data streams is difficult because they are high-dimensional and composed of multiple time-varying dynamics such as trends, seasonality, and interest diffusion. In this paper, we propose D-Tracker, a method for continuously capturing time-varying temporal patterns within social activity tensor data streams and forecasting future activities. Our proposed method has the following properties: (a) Interpretable: it incorporates the partial differential equation into a tensor decomposition framework and captures time-varying temporal patterns such as trends, seasonality, and interest diffusion between locations in an interpretable manner; (b) Automatic: it has no hyperparameters and continuously models tensor data streams fully automatically; (c) Scalable: the computation time of D-Tracker is independent of the time series length. Experiments using web search volume data obtained from GoogleTrends, and COVID-19 infection data obtained from COVID-19 Open Data Repository show that our method can achieve higher forecasting accuracy in less computation time than existing methods while extracting the interest diffusion between locations. Our source code and datasets are available at {https://github.com/Higashiguchi-Shingo/D-Tracker.

Problem

• Modeling high-dimensional social activity data streams
• Forecasting trends, seasonality, and interest diffusion
• Capturing interpretable time-varying temporal patterns

Innovation

• Incorporates PDE into tensor decomposition framework
• Fully automatic with no hyperparameters
• Scalable with constant computation time