Exploring Generative Pretrained Transformers to support Sustainability

Barbara Paech, Peter Kaiser, Peter Bambazek, Iris Groher, Norbert Seyff

Research output: Chapter in Book/Report/Conference proceedingConference proceedingspeer-review

Abstract

[Context] Sustainability is increasingly recognized as a critical aspect of software development. [Problem] However, identifying the potential sustainability effects of software systems during requirements engineering remains a complex and time-consuming task. [Principal idea] To address this challenge, we explore the use of Generative Pretrained Transformers (GPTs) to automate the generation of these effects across various sustainability dimensions. In this research preview paper, we present our research goals, key research questions, initial findings and next steps. Despite several challenges identified, our tentative conclusion is that GPTs, i.e. ChatGPT, are capable of generating relevant sustainability effects. [Contributions] Our findings aim to contribute to both research and practice by fostering AI-driven approaches for integrating sustainability considerations into requirements engineering.
Original languageEnglish
Title of host publicationProceedings of the 31st International Working Conference on Requirement Engineering: Foundation for Software Quality (REFSQ 2025), Barcelona, Spain, April 7 - 10, 2025
Pages226-234
DOIs
Publication statusPublished - 07 Apr 2025

Fields of science

  • 102022 Software development
  • 502050 Business informatics
  • 102040 Quantum computing 
  • 509026 Digitalisation research
  • 102034 Cyber-physical systems
  • 502032 Quality management
  • 102020 Medical informatics
  • 502052 Business administration
  • 102006 Computer supported cooperative work (CSCW)
  • 102027 Web engineering
  • 102016 IT security
  • 503015 Subject didactics of technical sciences
  • 102015 Information systems

JKU Focus areas

  • Digital Transformation

Cite this