Abstract
Sharing successful practices with other stakeholders is important for achieving SDGs. In this study, with a deep-learning natural language processing model, bidirectional encoder representations from transformers (BERT), the authors aimed to build (1) a classifier that enables semantic mapping of practices and issues in the SDGs context, (2) a visualizing method of SDGs nexus based on co-occurrence of goals (3) a matchmaking process between local issues and initiatives that may embody solutions. A data frame was built using documents published by official organizations and multi-labels corresponding to SDGs. A pretrained Japanese BERT model was fine-tuned on a multi-label text classification task, while nested cross-validation was conducted to optimize the hyperparameters and estimate cross-validation accuracy. A system was then developed to visualize the co-occurrence of SDGs and to couple the stakeholders by evaluating embedded vectors of local challenges and solutions. The paper concludes with a discussion of four future perspectives to improve the natural language processing system. This intelligent information system is expected to help stakeholders take action to achieve the sustainable development goals.
Highlights
The decade ending in 2030 is the Decade of Action (United Nations 2020). 2030 is the milestone year of limiting global warming to well below 1.5° (UNFCCC 2015) and of “livingHandled by Osamu Saito, Institute for Global Environmental Strategies, Japan.Since sustainable development goals (SDGs) require multistakeholder partnerships, knowledge platforms must be established at both multiscale and multisector levels
This study aims to build a natural language processing system with three functions; (1) a text classifier to map challenges and activities to SDGs context at the goal level; (2) an interlinkage visualizer of the SDGs nexus; (3) semantic matchmaking between local challenges and potential solutions from a variety of stakeholders
The bidirectional encoder representations from transformers (BERT) model (Devlin et al 2019), which is a natural language processing model used for this research, originally has the specification that the maximum length of the input length of the tokens is = < 512
Summary
The sustainable development knowledge platform (UNDESA 2021) is representative, while (Sustainable Development Solutions Network 2021) created a tracking and monitoring platform to share government sectors’ progress and maintain accountability. Higher Education Sustainability Initiative (United Nations 2012) is a networking platform for over 300 universities from around the world and the Technology Facilitation Mechanism (UNDESA and UNOICT 2020) has a platform for sharing scientific and technological suggestions, ideas, and solutions for enhancing SDG activities. The Local 2030 (United Nations 2017) support municipalities’ in monitoring, evaluating, and reviewing their SDGs progress, and the Voluntary Local Review Lab (Institute of Global Environment Strategy 2019) networks the municipalities released the Voluntary Local Review (VLR) reports. The private sector launched an open innovation platform named “SHIP (SDGs Holistic Innovation Platform)” to share technologies and know-how (Japan Innovation Network and UNDP 2021)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have