|
Abstract:
Literature-based discovery (LBD) is a systematic two-component approach to bridging unconnected disciplines (front-end component, back-end component) based on text mining procedures. LBD allows potentially radical discovery and innovation (radical discovery and innovation is used in the sense of discovery and innovation arising from unexpected insights originating in very disparate disciplines) to be hypothesized. Classically, the LBD front-end component has been used to identify the pool of potential discovery and innovation candidates, and the LBD back-end component has been used to hypothesize the potential discovery and innovation based on literature analysis alone (1). In this report, a systematic two-component approach to bridging unconnected disciplines and accelerating potentially radical discovery and innovation (based wholly or partially on text mining procedures) is presented. The front-end component has similar objectives to those in the classical LBD approach, although it is different mechanistically and operationally. The front- end component in the present report will systematically identify technical disciplines/ technologies (and their associated leading experts) that are directly or indirectly-related to solving technical problems of high interest. The back-end component in the present report is actually a family of back-end techniques, only one of which shares the strictly literature-based analysis of the classical LBD approach. These multiple back-end techniques will identify potential radical discovery and innovation for many different applications. In the present report, the two component techniques that use strictly literature- based analysis for the backend are termed literature-based discovery. The two- component techniques that do not focus on literature-based analysis for the back-end are termed literature-assisted discovery.
| Limitations: |
 APPROVED FOR PUBLIC RELEASE |
| Pages: |
84 |
| Report Date: |
2005 |
| Report Number: |
A027034 |
|
|
|
|
|
Keywords relating to this report:
Email This Abstract
