Feature Driven and Point Process Approaches for Popularity Prediction

Abstract

Predicting popularity, or the total volume of information outbreaks, is an important subproblem for understanding collective behavior in networks. Each of the two main types of recent approaches to the problem, feature-driven and generative models, have desired qualities and clear limitations. This paper bridges the gap between these solutions with a new hybrid approach and a new performance benchmark. We model each social cascade with a marked Hawkes self-exciting point process, and estimate the content virality, memory decay, and user influence. We then learn a predictive layer for popularity prediction using a collection of cascade history. To our surprise, Hawkes process with a predictive overlay outperform recent feature-driven and generative approaches on existing tweet data [43] and a new public benchmark on news tweets. We also found that a basic set of user features and event time summary statistics performs competitively in both classification and regression tasks, and that adding point process information to the feature set further improves predictions. From these observations, we argue that future work on popularity prediction should compare across feature-driven and generative modeling approaches in both classification and regression tasks.

References in corpus (6)

• Power-law distributions in empirical data
• Robust dynamic classes revealed by measuring the response function of a social system
• Can Cascades be Predicted?
• SEISMIC: A Self-Exciting Point Process Model for Predicting Tweet Popularity
• Exploring limits to prediction in complex social systems
• Download relaxation dynamics on the WWW following newspaper publication of URL

Cited by in corpus (17)

• A Survey of Information Cascade Analysis: Models, Predictions, and Recent Advances
• Expecting to be HIP: Hawkes Intensity Processes for Social Media Popularity
• SIR-Hawkes: Linking Epidemic Models and Hawkes Processes to Model Diffusions in Finite Populations
• Predicting the Popularity of Micro-videos with Multimodal Variational Encoder-Decoder Framework
• Explicit Time Embedding Based Cascade Attention Network for Information Popularity Prediction
• The Virality of Hate Speech on Social Media
• Capturing Dynamics of Information Diffusion in SNS: A Survey of Methodology and Techniques
• Will This Video Go Viral? Explaining and Predicting the Popularity of Youtube Videos
• Detecting False Rumors from Retweet Dynamics on Social Media
• Inference of multivariate exponential Hawkes processes with inhibition and application to neuronal activity
• Interval-censored Transformer Hawkes: Detecting Information Operations using the Reaction of Social Systems
• Radflow: A Recurrent, Aggregated, and Decomposable Model for Networks of Time Series
• Evently: Modeling and Analyzing Reshare Cascades with Hawkes Processes
• Evolution of diversity and dominance of companies in online activity
• Predicting Relationship Labels and Individual Personality Traits from Telecommunication History in Social Networks using Hawkes Processes
• Popularity Prediction for Social Media over Arbitrary Time Horizons
• Revisiting Information Cascades in Online Social Networks