Distinguishing AI-Generated and Human-Written Text Through Psycholinguistic Analysis

TL;DR

This paper introduces a novel framework combining stylometric features and psycholinguistic theories to improve the detection of AI-generated versus human-written texts, emphasizing interpretability and cognitive insights.

Contribution

It integrates psycholinguistic analysis with stylometric features, providing a transparent and cognitively grounded method for text attribution.

Findings

Identified 31 stylometric features linked to cognitive processes

Mapped psycholinguistic patterns to distinguish AI and human writing

Enhanced interpretability of detection models

Abstract

The increasing sophistication of AI-generated texts highlights the urgent need for accurate and transparent detection tools, especially in educational settings, where verifying authorship is essential. Existing literature has demonstrated that the application of stylometric features with machine learning classifiers can yield excellent results. Building on this foundation, this study proposes a comprehensive framework that integrates stylometric analysis with psycholinguistic theories, offering a clear and interpretable approach to distinguishing between AI-generated and human-written texts. This research specifically maps 31 distinct stylometric features to cognitive processes such as lexical retrieval, discourse planning, cognitive load management, and metacognitive self-monitoring. In doing so, it highlights the unique psycholinguistic patterns found in human writing. Through the intersection of computational linguistics and cognitive science, this framework contributes to the development of reliable tools aimed at preserving academic integrity in the era of generative AI.