logo
ResearchBunny Logo
A large-scale comparison of human-written versus ChatGPT-generated essays

Education

A large-scale comparison of human-written versus ChatGPT-generated essays

S. Herbold, A. Hautli-janisz, et al.

This groundbreaking study by Steffen Herbold, Annette Hautli-Janisz, Ute Heuer, Zlata Kikteva, and Alexander Trautsch reveals that ChatGPT produces superior argumentative essays compared to human high-school students. The findings highlight significant differences in writing styles and suggest a pressing need for educators to adapt their teaching methods to incorporate AI tools effectively.

00:00
00:00
Playback language: English
Abstract
This study compares human-written and ChatGPT-generated argumentative essays using a large-scale assessment by expert raters. Results indicate that ChatGPT generates higher-quality essays than those written by German high-school students across all evaluation criteria. ChatGPT-4 outperforms ChatGPT-3 in several aspects. Significant differences in writing styles exist between human and AI-generated texts. The authors suggest that educators must adapt teaching methods to integrate AI tools effectively.
Publisher
Scientific Reports
Published On
Oct 30, 2023
Authors
Steffen Herbold, Annette Hautli-Janisz, Ute Heuer, Zlata Kikteva, Alexander Trautsch
Tags
ChatGPT
argumentative essays
human writing
AI
education
writing styles
quality assessment
Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny