Quantitative Discourse Cohesion Analysis of Scientific Scholarly Texts using Multilayer Networks

Discourse cohesion facilitates text comprehension and helps the reader form a coherent narrative. In this study, we aim to computationally analyze discourse in scientific scholarly texts using multilayer network representation quantify writing quality of document. Exploiting hierarchical structure texts, design section-level document-level metrics assess extent lexical text. We use publicly available dataset along with curated set contrasting examples validate proposed by comparing them against select indices computed existing analysis tools. observe that correlate as expected indices. also present an analytical framework, CHIAA (CHeck It Again, Author), provide pointers author for potential improvements manuscript help metrics. The framework furnishes clear precise prescription improving localizing regions gaps. demonstrate efficacy succinct from cohesion-deficient excerpts experimental dataset.