Visitors   Views   Downloads

Data-driven classification of the certainty of scholarly assertions

View preprint
RT @markmoby: Version 2 of our paper about classifying certainty scholarly narratives. This version includes our machine-learning model, t…
RT @markmoby: Version 2 of our paper about classifying certainty scholarly narratives. This version includes our machine-learning model, t…
11 days ago
Version 2 of our paper about classifying certainty scholarly narratives. This version includes our machine-learning model, that shows ~80% accuracy in certainty classification of biomedical statements. https://t.co/rwxqSlCUaE via @PeerJPreprints
29 days ago
Data-driven classification of the certainty of scholarly assertions https://t.co/SbpABka25p https://t.co/KAzTUB2L9w
80 days ago
@khinsen @natesjacobs @soilandreyes @flashpub_io My student has a paper in PeerJ preprints that describes a certainty classifier (trained on biomed data, so possibly tuned specifically to that domain)... https://t.co/rwxqSlCUaE
RT @anitawaard: Our paper is in PeerJ preprints: "Classifying scholarly certainty..." https://t.co/TiExLQK1R5 via @PeerJPreprints
Our paper is in PeerJ preprints: "Classifying scholarly certainty..." https://t.co/TiExLQK1R5 via @PeerJPreprints
205 days ago
Data-driven classification of the certainty of scholarly assertions https://t.co/UOeciy4lml https://t.co/FXCujjm7uZ
NOT PEER-REVIEWED
"PeerJ Preprints" is a venue for early communication or feedback before peer review. Data may be preliminary.

Supplemental Information

Horn’s parallel analysis result for S1

DOI: 10.7287/peerj.preprints.27829v2/supp-1

Horn’s parallel analysis result for S2

DOI: 10.7287/peerj.preprints.27829v2/supp-2

Horn’s parallel analysis result for S3

DOI: 10.7287/peerj.preprints.27829v2/supp-3

Additional Information

Competing Interests

Helena Deus is employed by Elsevier Inc. Anita de Waard is Vice President, Research Data Collaborations at Elsevier. Erik Schultes is employed by the GO FAIR International Support and Coordination Office.

Author Contributions

Mario Prieto conceived and designed the experiments, performed the experiments, analyzed the data, prepared figures and/or tables, authored or reviewed drafts of the paper, and approved the final draft.

Helena Deus conceived and designed the experiments, analyzed the data, authored or reviewed drafts of the paper, and approved the final draft.

Anita De Waard conceived and designed the experiments, analyzed the data, authored or reviewed drafts of the paper, and approved the final draft.

Erik Schultes conceived and designed the experiments, analyzed the data, authored or reviewed drafts of the paper, and approved the final draft.

Beatriz García-Jiménez analyzed the data, authored or reviewed drafts of the paper, and approved the final draft.

Mark D Wilkinson conceived and designed the experiments, performed the experiments, analyzed the data, prepared figures and/or tables, authored or reviewed drafts of the paper, and approved the final draft.

Data Deposition

The following information was supplied regarding data availability:

All code and Jupyter notebooks, along with raw and processed data, are available in this publicly accessible folder on GitHub: https://github.com/Guindillator/Certainty

Funding

This work has been funded by the Isaac Peral/Marie Curie cofund with the Universidad Politécnica de Madrid, and the Spanish Ministerio de Economía y Competitividad grant number TIN2014-55993-RM and the "Severo Ochoa Program for Centres of Excellence in R&D” from the Agencia Estatal de nvestigación of Spain (grant SEV-2016-0672 (2017-2021) to the CBGP). Additional support was provided by the Consejo Social de la Universidad Politécnica de Madrid. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.

Feedback on other revisions


Add your feedback

Before adding feedback, consider if it can be asked as a question instead, and if so then use the Question tab. Pointing out typos is fine, but authors are encouraged to accept only substantially helpful feedback.

Some Markdown syntax is allowed: _italic_ **bold** ^superscript^ ~subscript~ %%blockquote%% [link text](link URL)
 
By posting this you agree to PeerJ's commenting policies