SEISMIC: A Self-Exciting Point Process Model for Predicting Tweet Popularity

By Qingyuan Zhao, Murat A. Erdogdu, Hera Y. He, Anand Rajaraman, Jure Leskovec. Knowledge Discovery and Data Mining, 2015

704 citations recorded by the source corpus.

Social networking websites allow users to create and share content. Big information cascades of post resharing can form as users of these sites reshare others' posts with their friends and followers. One of the central challenges in understanding such cascading behaviors is in forecasting information outbreaks, where a single post becomes widely popular by being reshared by many users. In this paper, we focus on predicting the final number of reshares of a given post. We build on the theory of self-exciting point processes to develop a statistical model that allows us to make accurate predictions. Our model requires no training or expensive feature engineering. It results in a simple and efficiently computable formula that allows us to answer questions, in real-time, such as: Given a post's resharing history so far, what is our current estimate of its final number of reshares? Is the post resharing cascade past the initial stage of explosive growth? And, which posts will be the most reshared in the future? We validate our model using one month of complete Twitter data and demonstrate a strong improvement in predictive accuracy over existing approaches. Our model gives only 15% relative error in predicting final size of an average information cascade after observing it for just one hour.

Subfields: Statistical and Nonlinear Physics, Transportation

View Paper: https://www.semanticscholar.org/paper/bb10da9fda9781237808b92c71580901660be770

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Statistical and Nonlinear Physics

In Transportation

Citations in the corpus

Recurrent Marked Temporal Point Processes: Embedding Event History to Vector (2016, background): “More recently, the self-excitation point process [20], has become an ongoing hot topic for modeling the latent dynamics of information diffusion [16, 9, 10, 8, 40, 14, 22], online-user engagement [13], news-feed streams [7], and context-aware recommendations [11].”
DeepHawkes: Bridging the Gap between Prediction and Understanding of Information Cascades (2017, methodology): “DH-origin model directly uses the number of fans as the representation of a user like previous works [11, 12], and simply summarizes the in uence of each retweet in Hawkes process, instead of encoding the in uence of the entire retweet path through a GRU structure.”
Examining a hate speech corpus for hate speech detection and popularity prediction (2018, methodology): “We use an large set of features inspired by re-lated work (Waseem and Hovy, 2016; Sutton et al., 2015; Suh et al., 2010; Zaman et al., 2013; Hong et al., 2011; Zhang et al., 2012; Cheng et al., 2014; Ma et al., 2013; Zhao et al., 2015).”
Transformer Hawkes Process (2020, background): “Retweets (Zhao et al., 2015): The Retweets dataset contains sequences of tweets, where each sequence contains an origin tweet (i.e., some user initiates a tweet), and some follow-up tweets.”
Self-attention with Functional Time Representation Learning (2019, neutral): “Classic temporal point process also allows the usage of inter-event time interval as continuous random variable in modelling sequential observations [26].”
Process (2020, background): “Stock Data: [43] Stock data includes the 11k stock trading information.”
DeepCas: An End-to-end Predictor of Information Cascades (2016, background): “Cascades of particular types of information are empirically proved to be predictable to some extent, including Tweets/microblogs [43, 39, 20, 11, 17, 44], photos [10], videos [2] and academic papers [31].”
Dynamics of information diffusion and its applications on complex networks (2016, methodology): “The third type is based on the probabilistic model, for example, using the theory of exciting point processes (Hawkes process) [94,185].”