Improving Article Navigation for FlyBase Curators with NLP
Author Information
Author(s): Karamanis Nikiforos, Seal Ruth, Lewin Ian, McQuilton Peter, Vlachos Andreas, Gasperin Caroline, Drysdale Rachel, Briscoe Ted
Primary Institution: University of Cambridge
Hypothesis
Can Natural Language Processing (NLP) technology facilitate database curation tasks?
Conclusion
PaperBrowser significantly improves navigational efficiency and utility for FlyBase curators compared to previous methods.
Supporting Evidence
- PaperBrowser reduces the number of navigation actions needed by about 58%.
- Curators using PaperBrowser experienced a 74% increase in navigational utility.
- The study involved observing curators to inform the design of PaperBrowser.
Takeaway
The study shows that a new tool called PaperBrowser helps scientists find important information in articles much faster and easier.
Methodology
Curators highlighted text in articles while using PaperBrowser's navigational aids, and their actions were logged for analysis.
Limitations
The study did not assess curation accuracy or agreement between curators.
Participant Demographics
Two curators with over two years of curation experience.
Statistical Information
P-Value
p<0.001
Statistical Significance
p<0.001
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website