Download this Paper Open PDF in Browser

Understanding the Predictive Power of Computational Mechanics and Echo State Networks in Social Media

12 Pages Posted: 28 Jun 2013 Last revised: 6 Sep 2015

David Darmon

University of Maryland

Jared Sylvester

University of Maryland

Michelle Girvan

University of Maryland, College Park

William Rand

North Carolina State University

Date Written: June 26, 2013

Abstract

There is a large amount of interest in understanding users of social media in order to predict their behavior in this space. Despite this interest, user predictability in social media is not well-understood. To examine this question, we consider a network of fifteen thousand users on Twitter over a seven week period. We apply two contrasting modeling paradigms: computational mechanics and echo state networks. Both methods attempt to model the behavior of users on the basis of their past behavior. We demonstrate that the behavior of users on Twitter can be well-modeled as processes with self-feedback. We find that the two modeling approaches perform very similarly for most users, but that they differ in performance on a small subset of the users. By exploring the properties of these performance-differentiated users, we highlight the challenges faced in applying predictive models to dynamic social data.

Keywords: prediction, social behavior modeling, social dynamics

Suggested Citation

Darmon, David and Sylvester, Jared and Girvan, Michelle and Rand, William, Understanding the Predictive Power of Computational Mechanics and Echo State Networks in Social Media (June 26, 2013). Available at SSRN: https://ssrn.com/abstract=2285537 or http://dx.doi.org/10.2139/ssrn.2285537

David Darmon (Contact Author)

University of Maryland ( email )

College Park
College Park, MD 20742
United States

Jared Sylvester

University of Maryland ( email )

College Park
College Park, MD 20742
United States

Michelle Girvan

University of Maryland, College Park ( email )

College Park, MD 20742
United States
301.405.1610 (Phone)

William Rand

North Carolina State University ( email )

Poole College of Management
Box 7229, North Carolina State University
Raleigh, NC North Carolina 27695-7229
United States
7347177965 (Phone)

HOME PAGE: http://billrand.org

Paper statistics

Downloads
61
Rank
300,888
Abstract Views
476