Very delighted to annoouce a brandnew paper led by Violeta just published in Environmental Evidence!

Despite growing evidence showing the importance of non-English-langauge evidence, environmental evidence syntheses still remain predominantly monolingual (English), potentially leading to biased results and misinforming policy decisions. In this paper we trained supervised machine learning models using a corpus of Spanish-language peer-reviewed academic articles on the effectiveness of conservation actions. The best-performing model achieved a recall of 100%, meaning it missed no relevant articles, while filtering out over 70% of irrelevant documents based solely on titles and abstracts.

This is Violeta’s first paper developing ML/AI based approaches to multilingual evidence synthesis and a huge step forward for our project. Congratulations Violeta and the team!

Read the paper here.