Pestobserver is a text mining project to explore bulletins on pest and crops interactions. Important data are locked in ancient literature. It would be uneconomic to produce these data again and today or to extract them without the help of text mining technologies.

Pestobserver is a text mining project whose aim is to extract data on pest and crops interactions, to model and predict attacks on crops, and to reduce the use of pesticides. A few attempts proposed an agricultural information access. Another originality of our work is to parse documents with a dependency of the document architecture.

More detailed version of the application are accessible in the Publication Cornell University Library and on this document.