Learning user-specific latent influence and susceptibility from information cascades

Abstract

Predicting cascade dynamics has important implications for understanding information propagation and launching viral marketing. Previous works mainly adopt a pair-wise manner, modeling the propagation probability between pairs of users using n^2 independent parameters for n users. Consequently, these models suffer from severe overfitting problem, specially for pairs of users without direct interactions, limiting their prediction accuracy. Here we propose to model the cascade dynamics by learning two low-dimensional user-specific vectors from observed cascades, capturing their influence and susceptibility respectively. This model requires much less parameters and thus could combat overfitting problem. Moreover, this model could naturally model context-dependent factors like cumulative effect in information propagation. Extensive experiments on synthetic dataset and a large-scale microblogging dataset demonstrate that this model outperforms the existing pair-wise models at predicting cascade dynamics, cascade size, and "who will be retweeted".

from The 29th AAAI Conference on Artificial Intelligence (AAAI-2015)

References in corpus (5)

• Robust dynamic classes revealed by measuring the response function of a social system
• Modeling Information Propagation with Survival Theory
• Cascading Behavior in Large Blog Graphs
• Cumulative Effect in Information Diffusion: A Comprehensive Empirical Study on Microblogging Network
• Popularity Prediction in Microblogging Network: A Case Study on Sina Weibo

Cited by in corpus (1)

• Activating the "Breakfast Club": Modeling Influence Spread in Natural-World Social Networks