论文信息 - OSDG - Open-Source Approach to Classify Text Data by UN Sustainable Development Goals (SDGs)

OSDG - Open-Source Approach to Classify Text Data by UN Sustainable Development Goals (SDGs)

Sustainable Development Goals (SDGs) bring together the diverse development community and provide a clear set of development targets for 2030. Given a large number of actors and initiatives related to these goals, there is a need to have a way to accurately and reliably assign text to different input: scientific research, research projects, technological output or documents to specific SDGs. In this paper we present Open Source SDG (OSDG) project and tool which does so by integrating existing research and previous classification into a robust and coherent framework. This integration is based on linking the features from the variety of previous approaches, like ontology items, keywords or features from machine-learning models, to the topics in Microsoft Academic Graph.

[1] Walter Daelemans,et al. Using Domain Similarity for Performance Estimation , 2010, ACL 2010.

[2] Martin Pawelczyk,et al. Linking Aid to the Sustainable Development Goals – a machine learning approach , 2019, OECD Development Co-operation Working Papers.

[3] Nuria Bautista-Puig,et al. Unveiling the path towards sustainability: is there a research interest on sustainable goals? , 2019, ISSI.

[4] Fabio Vitali,et al. Deep learning based multi-label text classification of UNGA resolutions , 2020, ICEGOV.

[5] Yuxiao Dong,et al. A Review of Microsoft Academic Services for Science of Science Studies , 2019, Front. Big Data.

[6] Yang Song,et al. An Overview of Microsoft Academic Service (MAS) and Applications , 2015, WWW.

[7] W. Filho,et al. A literature-based review on potentials and constraints in the implementation of the sustainable development goals , 2018, Journal of Cleaner Production.