Testing network clustering algorithms with Natural Language Processing

TL;DR

This paper proposes a hybrid approach combining community detection and NLP classification to evaluate social network clustering algorithms, achieving high accuracy in identifying social groups based on online textual content.

Contribution

It introduces a novel method to assess community detection algorithms by leveraging NLP classification, linking social structure with cultural content.

Findings

Community detection algorithms can be scored based on their agreement with NLP classification.

The method can identify a random user's opinion with over 85% accuracy.

The approach bridges social network structure and cultural content analysis.

Abstract

The advent of online social networks has led to the development of an abundant literature on the study of online social groups and their relationship to individuals' personalities as revealed by their textual productions. Social structures are inferred from a wide range of social interactions. Those interactions form complex -- sometimes multi-layered -- networks, on which community detection algorithms are applied to extract higher order structures. The choice of the community detection algorithm is however hardily questioned in relation with the cultural production of the individual they classify. In this work, we assume the entangled nature of social networks and their cultural production to propose a definition of cultural based online social groups as sets of individuals whose online production can be categorized as social group-related. We take advantage of this apparently self-referential description of online social groups with a hybrid methodology that combines a community detection algorithm and a natural language processing classification algorithm. A key result of this analysis is the possibility to score community detection algorithms using their agreement with the natural language processing classification. A second result is that we can assign the opinion of a random user at >85% accuracy.