SDG Research: Multi-Lingual Text Classifier

Pilot domain:
Target group:
Task team name:
WP5.1 SDG Research Dashboard

For university administrators who want to predict how a piece of text, albeit a research paper or course description, relates to an SDG-Goal or even SDG-Target. The input texts can be in English but also in a national language. The output can be used in their internal systems. We have put the trained model in a web service to classify our papers and will make this service available for public use based on the FAIR use policy. The web service will contain an API for developers and a browser-friendly user interface (UI). The API will process a text fragment and return data, the confidence percentages of the text fragment to the SDG goals and SDG targets, and a link to an image one can use as an SDG badge. The UI offers a web form to enter a text fragment or upload a table. Using a text fragment, the UI will show a diagram of how this text fragment relates to each SDG goal and SDG target. Uploading a table will add columns to each row containing the confidence levels of each SDG goal and SDG target.