A temporal data mining approach exploiting network science and information theory

What is it about?

This paper is about Transcendental Information Cascades, a novel temporal data mining approach that extends the concept of bursty structures in content sequences. Structural (e.g. network metrics) and informational (e.g. entropy) properties of Transcendental Information Cascades are discussed and a case study of the online citizen science platform Zooniverse demonstrates the application of the approach on real-world data.

Featured Image

Why is it important?

The method is a useful tool for exploratory data analysis and hypothesis generation when the raw underlying data has some sequential order.