Detecting Relational States in Online Social Networks (original) (raw)

2018 5th International Conference on Behavioral, Economic, and Socio-Cultural Computing (BESC), 2018

Abstract

The state of relationships between actors ion the internet is constantly changing and fluctuating to a social system of constant shocks. Link prediction, community detection, recommendation systems were built from around this fundamentally unstable system. Stable relational states - which hold important and latent deterministic knowledge have often been overlooked in this regard. In this paper, we propose a novel method of quantifying and detecting stability in the relationship between a given pair of actors. Our main algorithm (MVVA) establishes relational stability from a multivariate, autoregressive link feature dynamics perspective. Under our experimental design, we provide another built-in module based on the Hamiltonian Monte Carlo technique to provide a comprehensive cross-validation on the performance and accuracy of our proposed MVVA model.

Thuan Pham hasn't uploaded this paper.

Let Thuan know you want this paper to be uploaded.

Ask for this paper to be uploaded.