Back to search

Institutional Repository of Vilnius University

A comparative analysis of evaluative adjectives in human written and chat-gpt generated journalistic texts /

Abstract

dc:description

The world as it exists today could not be imaginable without evaluative adjectives, which allow us to express ourselves more clearly and thus enrich our language. This study covers the comparative analysis of evaluative adjectives that appear in human-written and ChatGPT-generated journalistic texts. The research was done using Martin and White’s (2005) appraisal framework, which helped to classify evaluative adjectives. The Subject: The evaluative adjectives used in human-written and ChatGPT-generated journalistic texts. The aim: To conduct the analysis of the use of evaluative adjectives in human-written and ChatGPT-generated journalistic texts. In order to achieve the aim, the following objectives were set: 1. To analyse the scientific literature regarding evaluative adjectives, their classification and the differences in human-written and AI generated texts. 2. To identify evaluative adjectives used in human-written journalistic texts from National Geographic and ChatGPT-generated journalistic texts on the same topics. 3. To analyse the 20 most frequently used evaluative adjectives in both corpora. In order to achieve the objectives quantitative and qualitative methods were applied. Quantitative analysis was done to find the frequency of evaluative adjectives in both corpora and also to distinguish the 20 most frequent evaluative adjectives used. The analysis revealed that there is a clear difference in occurrence of evaluative adjectives, with it being more frequent in ChatGPT-generated journalistic articles. The qualitative analysis helped further investigate the examples and see the differences, with ChatGPT utilizing an overly positive and impactful evaluative adjectives, compared to more factual and context sensitive ones seen in human-written works.

Degree

thesis:*
Grantor dc:publisher
Institutional Repository of Vilnius University
Year dc:date
2025

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Tomašiūnaitė, Emilija,

Subjects

dc:subject × 1

Rights

dc:rights
Statement dc:rights
  • info:eu-repo/semantics/openAccess
Language dc:language
eng

Identifiers

dc:identifier.*

Chain of custody

source
Harvested from
Vilnius University
Base URL
epublications.vu.lt/oai
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Tomašiūnaitė, Emilija,. A comparative analysis of evaluative adjectives in human written and chat-gpt generated journalistic texts /. Institutional Repository of Vilnius University, 2025. https://repository.vu.lt/VU:ELABAETD239015617&prefLang=en_US