Complex networks analysis of language complexity

TL;DR

This study uses complex network analysis from statistical physics to quantify and distinguish levels of textual complexity, showing that simpler texts have more regular and interconnected network structures.

Contribution

It introduces a novel application of complex network metrics combined with pattern recognition to classify text complexity levels, including the generation of simplified text versions.

Findings

Topological regularity correlates negatively with textual complexity

Simpler texts have decreased distances between concepts in the network

Pattern recognition effectively distinguishes original from simplified texts

Abstract

Methods from statistical physics, such as those involving complex networks, have been increasingly used in quantitative analysis of linguistic phenomena. In this paper, we represented pieces of text with different levels of simplification in co-occurrence networks and found that topological regularity correlated negatively with textual complexity. Furthermore, in less complex texts the distance between concepts, represented as nodes, tended to decrease. The complex networks metrics were treated with multivariate pattern recognition techniques, which allowed us to distinguish between original texts and their simplified versions. For each original text, two simplified versions were generated manually with increasing number of simplification operations. As expected, distinction was easier for the strongly simplified versions, where the most relevant metrics were node strength, shortest paths and diversity. Also, the discrimination of complex texts was improved with higher hierarchical network metrics, thus pointing to the usefulness of considering wider contexts around the concepts. Though the accuracy rate in the distinction was not as high as in methods using deep linguistic knowledge, the complex network approach is still useful for a rapid screening of texts whenever assessing complexity is essential to guarantee accessibility to readers with limited reading ability