Automated Analysis of the Interactions Between Sustainable Development Goals Extracted from Models and Texts of Sustainability Science

Abstract

The design and monitoring of sustainable policies should rely on models that can handle complex and interconnected variables and subsystems of sustainability issues. Structuring knowledge has been identified as an essential first step in building models of sustainability science. Although it is known that all models yield a reduced view of the examined topic and no models can include all the variables that would make the representation closed and comprehensive, in the case of sustainability issues it is critical to synthesize as many critical aspects as possible that could have an impact on the studied problem. The key idea of our research is that strategic plans, sustainability reports and scientific studies reflect these variables, therefore, with the tools of text mining, the most important focus points and interactions can be determined. These key aspects and their connections can be represented by a network structure and compared to the subsystems of the dynamic models of sustainability to explore the deficiencies of the models or the lack of focus of the related policies and documentations. In the present work, the proposed methodology through the analysis of five strategical documents is demonstrated and the determined aspects with the structure of the famous World3 system dynamics model compared. The comparison highlighted the incomplete view of the original World3 model since certain topics were not critical issues whilst the World3 model was in development.