bioreader
Machine learning-based document classification
Science Score: 18.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
✓CITATION.cff file
Found CITATION.cff file -
○codemeta.json file
-
○.zenodo.json file
-
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (4.9%) to scientific vocabulary
Repository
Machine learning-based document classification
Basic Info
- Host: GitHub
- Owner: mikkelnrasmussen
- License: mit
- Language: R
- Default Branch: main
- Size: 96.6 MB
Statistics
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 0
Metadata Files
README.md
BioReader - 2.0
Biomedical Research Article Distiller
Do you have a large number of research articles to go through, but do not know where to start? BioReader can help you distill your reading list by ranking articles by relevance. Simply collect the PubMed IDs of a number of articles you found relevant and a similar number of articles not relevant to you (we recommend at least 20 in each category - see Tips and Tricks in instruction for successful classification). These two sets of PubMed IDs represent your positive and negative text mining training corpora to be pasted below. Then, either paste the PubMed IDs of up to 1000 articles that you would like to have ranked according to you content of interest, or enter a PubMed search term, and BioReader will provide you with a ranked reading list to limit the time wasted on reading irrelevant literature.
Owner
- Name: Mikkel Niklas Rasmussen
- Login: mikkelnrasmussen
- Kind: user
- Repositories: 1
- Profile: https://github.com/mikkelnrasmussen
Citation (citation.md)
**ABSTRACT** This web service enables complex queries of scientific literature by machine learning-based classification of article abstracts. BioReader (Biomedical Research Article Distiller) is trained by uploading corpora for two training categories - e.g. one positive and one negative for specific content - as well as one corpora of abstracts to be classified. The corpora are submitted as lists of PubMed IDs and the abstracts are automatically downloaded from PubMed, preprocessed, and the test corpus classified using the best performing classifier selected from ten implemented machine learning algorithms. BioReader is freely available for all users at http://www.cbs.dtu.dk/services/BioReader-1.2.