The process of a chemical risk assessment includes exposure assessment, hazard identification, hazard characterization and risk characterization. This often involves experts exhaustively reading published scientific articles, which is an extremely time consuming task. Finding all relevant information is often nearly impossible.
We apply natural language processing and text mining methods to support the chemical risk assessment process. Some examples of our work include CRAB, a tool that targets chemical cancer risk assessment. We also have used text mining for exposure assessment.
You can find CRAB here: http://crab3.lionproject.net/
This work is a collaboration with Karolinska Institutet (Institute of Environmental Medicine).