The use of ChatGPT to generate summative feedback in programming assessments that is consistent, prompt, without bias and scalable

Research output: Chapter in Book/Report/Conference proceedingConference contribution

28 Downloads (Pure)

Abstract

This paper explores the automated integration of ChatGPT into the feedback process for a large-scale and complex university programming assignment. It aims to explore the feasibility of using ChatGPT to facilitate prompt, efficient, and valued feedback to students. The study presents case studies illustrating the use of the ChatGPT API in generating feedback through an automated tool (AutoFeed) developed by the researchers. The findings report on the advantages as well as the limitations of employing Prompt Engineering for this purpose.
Original languageEnglish
Title of host publicationAICCONF '24: Proceedings of the Cognitive Models and Artificial Intelligence Conference
PublisherAssociation for Computing Machinery
Pages39-43
ISBN (Electronic)9798400716928
DOIs
Publication statusPublished - 23 Jun 2024
EventAICCONF '24: Cognitive Models and Artificial Intelligence Conference - Istanbul, Turkey
Duration: 25 May 202426 May 2024

Publication series

NameProceedings of the Cognitive Models and Artificial Intelligence Conference
PublisherAssociation for Computing Machinery

Conference

ConferenceAICCONF '24: Cognitive Models and Artificial Intelligence Conference
Country/TerritoryTurkey
CityIstanbul
Period25/05/202426/05/2024

Fingerprint

Dive into the research topics of 'The use of ChatGPT to generate summative feedback in programming assessments that is consistent, prompt, without bias and scalable'. Together they form a unique fingerprint.

Cite this