Extracting and Coding Digital Sustainability Data using Text Mining and AI: A Design Science Approach

Information Systems (IS) scholars studying Digital Sustainability (DSus) (Kotlarsky et al., 2023) focus on how IS helps companies holistically address both environmental and social sustainability internally and externally. Collecting such DSus data from secondary sources (e.g. sustainability report) is time consuming and labor intensive as researchers have to rely on manual screening of such reports, followed by laborious manual content coding. Using Design Science (DSci) methodology, we develop a semi-automatic data collection and content coding process with the help of WordStat analytics and ChatGPT Artificial Intelligence tools. The process developed from this research is a DSci artifact that helps provide a foundational framework for a semi-automated process to enable for IS scholars to effectively collect and conduct content coding for larger sets of DSus data for future research.