Feature-level decomposition of text complexity: cross-domain empirical evidence [Articol]

Abstract

This study presents a feature-level analysis of text complexity using large language models (LLMs) in a two-phase design. Phase I operationalized six core features – lexical diversity, density, syntactic complexity, coherence, named entities, and readability – achieving Spearman correlations of 0.55–0.60 across domains. Phase II employed indirect prompting to surface additional qualitative dimensions (e.g., inferential load, rhetorical structure), yielding a mean correlation of 0.42 and revealing that the six features account for 40% of complexity variance. Domain dependencies were limited to named entities and lexical diversity. We propose a hybrid model combining normalization, root-based synergies, and newly quantified metrics with domain-tuned formulae for improved prediction.