User:Shawndouglas/Sandbox
 |
This is my sandbox, where I play with features and test MediaWiki code. If you wish to leave a comment for me, please see my discussion page instead. |
Sandbox begins below
| Full article title | Application of text analytics to extract and analyze material–application pairs from a large scientific corpus |
|---|---|
| Journal | Frontiers in Research Metrics and Analytics |
| Author(s) | Kalathil, Nikhil; Byrnes, John J.; Randazzese, Lucien; Hartnett, Daragh P.; Freyman, Christina A. |
| Author affiliation(s) | Center for Innovation Strategy and Policy and the Artificial Intelligence Center, SRI International |
| Primary contact | Email: christina dot freyman at sri dot com |
| Year published | 2018 |
| Volume and issue | 2 |
| Page(s) | 15 |
| DOI | 10.3389/frma.2017.00015 |
| ISSN | 2504-0537 |
| Distribution license | Creative Commons Attribution 4.0 International |
| Website | https://www.frontiersin.org/articles/10.3389/frma.2017.00015/full |
| Download | https://www.frontiersin.org/articles/10.3389/frma.2017.00015/pdf (PDF) |
 |
This article should not be considered complete until this message box has been removed. This is a work in progress. |
Abstract
When assessing the importance of materials (or other components) to a given set of applications, machine analysis of a very large corpus of scientific abstracts can provide an analyst a base of insights to develop further. The use of text analytics reduces the time required to conduct an evaluation, while allowing analysts to experiment with a multitude of different hypotheses. Because the scope and quantity of metadata analyzed can, and should, be large, any divergence from what a human analyst determines and what the text analysis shows provides a prompt for the human analyst to reassess any preliminary findings. In this work, we have successfully extracted material–application pairs and ranked them on their importance. This method provides a novel way to map scientific advances in a particular material to the application for which it is used. Approximately 438,000 titles and abstracts of scientific papers published from 1992 to 2011 were used to examine 16 materials. This analysis used coclustering text analysis to associate individual materials with specific clean energy applications, evaluate the importance of materials to specific applications, and assess their importance to clean energy overall. Our analysis reproduced the judgments of experts in assigning material importance to applications. The validated methods were then used to map the replacement of one material with another material in a specific application (batteries).
Keywords: machine learning classification, science policy, coclustering, text analytics, critical materials, big data
Introduction
Scientific research and technological development are inherently combinatorial practices (Arthur, 2009). Researchers draw from, and build on, existing work in advancing the state of the art. Increasing the ability of researchers to review and understand previous research can stimulate and accelerate scientific progress. However, the number of scientific publications grows exponentially every year both on the aggregate level and in an individual field (National Science Board, 2016). It is impossible for any single researcher or organization to keep up with the vastness of new scientific publications. The ability to use text analytics to map the current state of the art to detect progress would enable more efficient analyses of data.
References
Notes
This presentation is faithful to the original, with only a few minor changes to presentation. In some cases important information was missing from the references, and that information was added. The original article lists references alphabetically, but this version — by design — lists them in order of appearance.
