Beyond Leakage and Complexity: Towards Realistic and Efficient Information Cascade Prediction

TL;DR

This paper introduces a realistic evaluation framework, a new large-scale dataset, and an efficient model for predicting information cascade popularity in social networks, addressing key limitations of prior work.

Contribution

It proposes a time-ordered data splitting strategy, introduces the Taoke dataset with rich conversion signals, and develops CasTemp, a fast, effective cascade modeling framework.

Findings

CasTemp achieves state-of-the-art performance on four datasets.

CasTemp significantly speeds up training compared to complex graph-based methods.

The new dataset Taoke captures complete cascade lifecycle including conversions.

Abstract

Information cascade popularity prediction is a key problem in analyzing content diffusion in social networks. However, current related works suffer from three critical limitations: (1) temporal leakage in current evaluation--random cascade-based splits allow models to access future information, yielding unrealistic results; (2) feature-poor datasets that lack downstream conversion signals (e.g., likes, comments, or purchases), which limits more practical applications; (3) computational inefficiency of complex graph-based methods that require days of training for marginal gains. We systematically address these challenges from three perspectives: task setup, dataset construction, and model design. First, we propose a time-ordered splitting strategy that chronologically partitions data into consecutive windows, ensuring models are evaluated on genuine forecasting tasks without future information leakage. Second, we introduce Taoke, a large-scale e-commerce cascade dataset featuring rich promoter/product attributes and ground-truth purchase conversions--capturing the complete diffusion lifecycle from promotion to monetization. Third, we develop CasTemp, a lightweight framework that efficiently models cascade dynamics through temporal walks, Jaccard-based neighbor selection for inter-cascade dependencies, and GRU-based encoding with time-aware attention. Under leak-free evaluation, CasTemp achieves state-of-the-art performance across four datasets with orders-of-magnitude speedup. Notably, it excels at predicting second-stage popularity conversions--a practical task critical for real-world applications.