Suche

Wo soll gesucht werden?
Erweiterte Literatursuche

Ariadne Pfad:

Inhalt

Literaturnachweis - Detailanzeige

 
Autor/inn/enKashinath Boral; Krishna Kanta Mondal
TitelComparing AI-Generated Responses: A Study on ChatGPT, Gemini, and Copilot in Education
QuelleIn: Journal of Educational Technology Systems, 54 (2025) 2, S. 291-309Infoseite zur Zeitschrift
PDF als Volltext  Link als defekt meldenVerfügbarkeit 
ZusatzinformationORCID (Kashinath Boral)
Spracheenglisch
Dokumenttypgedruckt; online; Zeitschriftenaufsatz
ISSN0047-2395
DOI10.1177/00472395251368385
SchlagwörterForschungsbericht; Artificial Intelligence; Technology Uses in Education; Multiple Choice Tests; Program Effectiveness; Accuracy; Affordances; Barriers; Test Construction
AbstractThis study evaluates the performance of three leading AI chatbots--OpenAI's ChatGPT, Google's Gemini, and Microsoft Bing Copilot--in answering multiple choice questions (MCQs) from the UGC-NET Education paper. Using 150 randomly selected questions from examination cycles between June 2019 and December 2023, the chatbots' accuracy was assessed against the official answer key. Copilot demonstrated the highest accuracy (86%), followed by Gemini (79.33%) and ChatGPT (78.67%). Unit-wise analysis revealed distinct strengths: Copilot excelled in "Pedagogy and Technology in Education," Gemini performed best in "Research in Education," while ChatGPT demonstrated a balanced performance. Chi-square analysis indicated no statistically significant differences among the chatbots. These findings highlight AI's potential as a supplementary educational tool while underscoring the need for improvements in handling complex topics. The study offers recommendations for enhancing chatbot algorithms to improve their effectiveness in academic contexts, providing valuable insights for educators and developers regarding AI integration in education. (As Provided).
AnmerkungenSAGE Publications. 2455 Teller Road, Thousand Oaks, CA 91320. Tel: 800-818-7243; Tel: 805-499-9774; Fax: 800-583-2665; e-mail: journals@sagepub.com; Web site: https://sagepub.com
BegutachtungPeer reviewed
Erfasst vonERIC (Education Resources Information Center), Washington, DC
Update2025/4/11
Literaturbeschaffung und Bestandsnachweise in Bibliotheken prüfen
 

Standortunabhängige Dienste
Bibliotheken, die die Zeitschrift "Journal of Educational Technology Systems" besitzen:
Link zur Zeitschriftendatenbank (ZDB)

Artikellieferdienst der deutschen Bibliotheken (subito):
Übernahme der Daten in das subito-Bestellformular

Tipps zum Auffinden elektronischer Volltexte im Video-Tutorial

Trefferlisten Einstellungen

Permalink als QR-Code

Permalink als QR-Code

Inhalt auf sozialen Plattformen teilen (nur vorhanden, wenn Javascript eingeschaltet ist)

Teile diese Seite: