Abstract
We draw a parallel between hashtag time series and neuron spike trains. In each case, the process presents complex dynamic patterns including temporal correlations, burstiness, and all other types of nonstationarity. We propose the adoption of the so-called local variation in order to uncover salient dynamical properties, while properly detrending for the time-dependent features of a signal. The methodology is tested on both real and randomized hashtag spike trains, and identifies that popular hashtags present regular and so less bursty behavior, suggesting its potential use for predicting online popularity in social media.
Highlights
In this paper, we focus on the statistical properties of Twitter and, in particular, on the dynamics and popularity of hashtags
The main purpose of this paper is to introduce a statistical measure suitable for the analysis of non-stationary time series, as they often take place in online social media and communications in social systems
We have focused on the dynamics of hashtags in Twitter
Summary
We focus on the statistical properties of Twitter and, in particular, on the dynamics and popularity of hashtags. Besides this smooth periodic behavior, the data exhibit a noisy signal at a finer time scale, as shown in the inset of Fig 1. Statistical indicators based on this distribution, such as its variance or Fano factor, might be affected in a similar way For this reason, we consider here the so-called local variation LV, originally defined to determine intrinsic temporal dynamics of neuron spike trains [23,24,25,26,27]. Unlike quantities such as P(Δτ), LV compares temporal variations with their local rates and is defined for nonstationary processes [27]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
