OSDG is an open source initiative that aims to integrate various existing attempts to classify research according to Sustainable Development Goals, and to make this process open, transparent and user-friendly.
We integrate existing research into a comprehensive approach that avoids the shortcomings of previous individual approaches and the duplication of research efforts.
OSDG is a partnership between PPMI, UNDP SDG AI Lab, and a growing community of researchers led by Dr. Nuria Bautista Puig.
In our whitepaper, we present OSDG 2.0, a new iteration of the partnership’s work, which marks a significant improvement in the OSDG framework.
The paper explains the partnership behind the project, presents the methodology of OSDG 2.0, reviews key milestones and existing use cases taken up by various project partners and stakeholders.
Using our methodology? Cite us:
Pukelis, L., Bautista-Puig, N., Statulevičiūtė, G., Stančiauskas, V., Dikmener, G., & Akylbekova, D. (2022, November 21). OSDG 2.0: A multilingual tool for classifying text data by UN Sustainable Development Goals (SDGs). https://doi.org/10.48550/arXiv.2211.11252
In the current OSDG workflow, the first stage uses machine learning (ML) models, trained on the data collected via OSDG Community Platform
In the second stage, OSDG uses its ontology/keyword map to verify the initial labels. keyword matching helps to locate evidence that a given text is related to that particular SDG.
For each SDG label to be assigned, both the ML and ontology approaches must be in agreement.
The OSDG team curates an API, which allows to automatically assign SDG labels to both text snippets and documents. API access is offered free of charge to scholars, conducting research that would be made available to the public in the form of a journal publication, conference paper, etc.
See a few examples below, and if you’re planning on conducting research that would benefit from classifying content to SDGs, contact us for free access.
A methodology for linking the Energy- related Policies of the E uropean Green Deal to the 17 SDGs using M achine Learning
Phoebe Koundouri, Nicolaos Theodossiou, Charalampos Stavridis, Stathis Devves, Angelos Plataniotis
Does your academic work use OSDG methodology? Contact us to be featured.
We maintain an up-to-date list of data sources that are used to build the ontology as well as copies of the input datasets, processing scripts and the resulting combined ontology in the project GitHub repository .The ontology of terms used in the OSDG tool is derived from the following data sources:
Be the first one to find out about OSDG developments and improvements.