A0388
Title: Difference in SDG reportings of research articles using zero-shot text classification
Authors: Elena Toenjes - Justus-Liebig-University Giessen (Germany)
Lutz Breuer - Justus-Liebig-University Giessen (Germany)
Ramona Teuber - Justus-Liebig-University Giessen (Germany)
Christoph Funk - Justus-Liebig-University Giessen (Germany) [presenting]
Abstract: In September 2015, the United Nations (UN) set an agenda to transform our world by 2030 with the adoption of 17 Sustainable Development Goals (SDGs) and 169 targets and 231 indicators for monitoring. Since then, the academic literature on the SDGs has grown steadily. So far, it is not clear in which countries SDGs are predominantly addressed. We apply zero-shot classification as a text mining tool on SDG-related scientific articles to analyze the scientific discourse on the 17 SDGs. First, we review the scientific literature on the SDGs, which allows us to draw conclusions about the focal points of scientific discourse worldwide. Second, we show that abstracts contain the most relevant information from scientific articles related to the discussed SDGs. Third, we demonstrate that zero-shot text classification can be a useful tool to label extensive textual information, thus providing an efficient tool for policymakers to screen the scientific literature, but also to provide information beyond the typical UN indicators. Our results suggest that SDGs 1, 2, 4 and 5 are less likely to be discussed than the remaining 13 SDGs. We find considerable variations in the scientific discourse across countries worldwide. SDGs 1 and 3 show the most negative correlation between the likelihood of discussion and their indicators. In addition, SDGs 7, 9, 15 and 16 show a positive relationship and have a higher probability of being discussed, even if their indicators perform well.
