Quantifying and filtering knowledge generated by literature based discovery

Preiss, J; Stevenson, M

Abstract

Background
Literature based discovery (LBD) automatically infers missed connections between concepts in literature. It is often assumed that LBD generates more information than can be reasonably examined.

Methods
We present a detailed analysis of the quantity of hidden knowledge produced by an LBD system and the effect of various filtering approaches upon this. The investigation of filtering combined with single or multi-step linking term chains is carried out on all articles in PubMed.

Results
The evaluation is carried out using both replication of existing discoveries, which provides justification for multi-step linking chain knowledge in specific cases, and using timeslicing, which gives a large scale measure of performance.

Conclusions
While the quantity of hidden knowledge generated by LBD can be vast, we demonstrate that (a) intelligent filtering can greatly reduce the number of hidden knowledge pairs generated, (b) for a specific term, the number of single step connections can be manageable, and (c) in the absence of single step hidden links, considering multiple steps can provide valid links.

Citation

Preiss, J., & Stevenson, M. (2017). Quantifying and filtering knowledge generated by literature based discovery. BMC Bioinformatics, 18(Sup. 7), 249. https://doi.org/10.1186/s12859-017-1641-9

• Journal Article Type: Article
• Publication Date: May 31, 2017
• Deposit Date: Nov 11, 2020
• Publicly Available Date: Nov 11, 2020
• Journal: BMC Bioinformatics
• Publisher: Springer Verlag
• Volume: 18
• Issue: Sup. 7
• Pages: 249
• DOI: https://doi.org/10.1186/s12859-017-1641-9
• Publisher URL: https://doi.org/10.1186/s12859-017-1641-9
• Related Public URLs: http://www.biomedcentral.com/bmcbioinformatics/
• Additional Information: Funders : Engineering and Physical Sciences Research Council (EPSRC); Grant Number: EP/J008427/1