LINGUISTIC FEATURES OF AI-GENERATED TEXTS AND METHODS FOR THEIR AUTOMATED IDENTIFICATION
The article examines linguistic features of Ukrainian socio-political news texts generated by large language models and methods for their automated identification. The aim is to substantiate lexical, stylistic, compositional and semantic markers that may indicate AI-generated text and to outline a computational-linguistic detection framework. The study proposes combining philological interpretation with NLP procedures: preprocessing, lexical diversity assessment, clustering, vectorization and transformer-based classification. It is argued that automated detection should not replace expert linguistic analysis but should serve as an auxiliary tool for evaluating the probable origin of a text in media linguistics, fact-checking, and educational practic