Image credit: Jason LucasAbstract
I presented work at the 2023 CRA-WP Workshop detecting COVID-19 false claims in the linguistically diverse, low-resource setting of the Caribbean islands. This project analyzed how computational solutions trained solely on English data fail to capture the nuances around misinformation propagation in developing regions. Our experiments found neural networks and even powerful transformer architectures struggle when tested on non-English claims translated from Caribbean languages. My talk discussed insights around the difficulty of transferring AI models across low-resource languages and vastly different information ecosystems. I also highlighted ideas for enhancing cross-lingual understanding and inclusion in misinformation detection systems deployed in at-risk communities.
Slides can be added in a few ways:
- Create slides using Hugo Blox Builder’s Slides feature and link using
slidesparameter in the front matter of the talk file - Upload an existing slide deck to
static/and link usingurl_slidesparameter in the front matter of the talk file - Embed your slides (e.g. Google Slides) or presentation video on this page using shortcodes.
Further event details, including page elements such as image galleries, can be added to the body of this page.
