Have you ever feel overwhelmed by the task of finding puntual information about an specific species of interest on tons of published literature? Researches on biodiversity are often reading and sorting out many published academic works in order to gather important data to test our predictions or develop new hypothesis. Much of this process is done manually, and important biodiversity knowledge is locked up on pdf versions of and article. Biodiversity Observations Miner is a tool that has been developed with the intention to facilitate the discovery of biodiversity information stored in pdf versions of scientific articles using open source text mining tools.
You can check out the application on the links below:
Online server:
https://fgabriel1891.shinyapps.io/biodiversityobservationsminer/
GitHub repo:
https://github.com/fgabriel1891/BiodiversityObservationsMiner
This is a work in progress and has many features to work and add to the application.
I'd like to hear from you with suggestions and comments.