Invasion Biology WikiProject Scientific Papers: Text Data Mining and LLM-based Information Extraction of Species, Locations, Habitats, and Ecosystems

This dataset contains the abstract and full-text for publication DOIs from the Invasion Biology WikiProject (DOI: 10.5281/zenodo.12518036). The data was retrieved using the ask.orkg.org API. For the script used to obtain the data, refer to the accompanying GitHub repository: https://github.com/jd-coderepos/invasion-biology-IE/.

The resulting CSV file includes the following fields: "ASK ID", "DOI", "Title", "Abstract", and "Full-text".

Of the 49,438 queried DOIs, the ASK database provided:

• Total DOIs processed: 12,636
• DOIs with neither abstract nor full-text: 36 (abstract token count was less than 10)
• DOIs with abstracts but no full-text: 12,636
• DOIs with both abstract and full-text: 2,834

The second part of the dataset contains structured information extracted from the publications using the GPT-4o Large Language Model. This structured data is included in the zipped folder structured-publications.zip.

The accompanying GitHub repository provides access to the code and scripts used at various stages of the information extraction (IE) process.

Theme of the Study:
"Mining for Species, Locations, Habitats, and Ecosystems from Scientific Papers in Invasion Biology: A Large-Scale Exploratory Study with Large Language Models."