This study examines the associations between time series, termed “coherency,” using spectral analysis. Coherence squared, analogous to the squared correlation coefficient, serves as a metric to quantify the degree of interdependence and co-evolution of individual nodes.
We utilized spectral analysis to compute coherence squared, unveiling relationships and co-evolution patterns among individual nodes. The resultant matrix of these relationships was subjected to network analysis.
By conducting a case study analyzing tweets associated with the co-hashtags #StopAsianHate and #BlackLivesMatter, we present a novel approach utilizing coherency network analysis to investigate the dynamics of social media text. Frequency domain analysis aided in calculating coherence squared, effectively illustrating the relationships and co-evolution of individual nodes. Furthermore, an analysis of the phase spectrum's slope facilitated the determination of time lag and potential causality direction between highly co-evolved node pairs.
Our findings underline the potential of coherency network analysis in comprehending the intricate dynamics of social media text. This approach offers valuable insights into how topics, sentiments, or movements manifest and evolve within the digital realm. Future research should explore diverse datasets and domains to broaden our understanding of this novel analytical technique.