Embedded Topics in the Stochastic Block Model

TL;DR

This paper introduces ETSBM, a deep latent variable model that combines network clustering with topic modeling on textual data, enabling analysis of communication networks with textual edges.

Contribution

The paper presents ETSBM, a novel model that integrates stochastic block modeling and embedded topic modeling for networks with textual edge data.

Findings

Effective on synthetic data

Successfully applied to real-world dataset

Improves network and topic analysis

Abstract

Communication networks such as emails or social networks are now ubiquitous and their analysis has become a strategic field. In many applications, the goal is to automatically extract relevant information by looking at the nodes and their connections. Unfortunately, most of the existing methods focus on analysing the presence or absence of edges and textual data is often discarded. However, all communication networks actually come with textual data on the edges. In order to take into account this specificity, we consider in this paper networks for which two nodes are linked if and only if they share textual data. We introduce a deep latent variable model allowing embedded topics to be handled called ETSBM to simultaneously perform clustering on the nodes while modelling the topics used between the different clusters. ETSBM extends both the stochastic block model (SBM) and the embedded topic model (ETM) which are core models for studying networks and corpora, respectively. The inference is done using a variational-Bayes expectation-maximisation algorithm combined with a stochastic gradient descent. The methodology is evaluated on synthetic data and on a real world dataset.