A Query-Driven System for Discovering Interesting Subgraphs in Social Media

TL;DR

This paper introduces a query-driven system that automatically discovers interesting, structurally and content-wise distinct subgraphs in social media data modeled as heterogeneous graphs, aiding users in targeted analysis.

Contribution

It presents a novel algorithm combining group-by operations and subjective interestingness to identify distinctive subgraphs based on user interests.

Findings

Effective discovery of interesting subgraphs demonstrated on socio-political data

Algorithm outperforms baseline methods in identifying relevant subgraphs

System supports personalized social media analysis

Abstract

Social media data are often modeled as heterogeneous graphs with multiple types of nodes and edges. We present a discovery algorithm that first chooses a "background" graph based on a user's analytical interest and then automatically discovers subgraphs that are structurally and content-wise distinctly different from the background graph. The technique combines the notion of a \texttt{group-by} operation on a graph and the notion of subjective interestingness, resulting in an automated discovery of interesting subgraphs. Our experiments on a socio-political database show the effectiveness of our technique.