Abstract
The organization of a technical meeting, workshop, or conference involving submitted abstracts or full-text documents can be quite an onerous task. To gain a sense of what topic each submission addresses may require more than just a quick glimpse at the title or abstract. The use of automated indexing and text mining can revolutionize the manner and speed of information assessment and organization. In this work, we demonstrate the use of Latent Semantic Indexing (LSI) for probing and labeling conference abstracts using an intuitive Web interface and client-server internal software design using grid-based middleware such as NetSolve. Automated text parsing and keyword extraction is facilitated using the General Text Parser software (C++) developed in the UTK Department of Computer Science.
| Original language | English |
|---|---|
| Title of host publication | Statistical Data Mining and Knowledge Discovery |
| Publisher | CRC Press |
| Pages | 571-581 |
| Number of pages | 11 |
| ISBN (Electronic) | 9780203497159 |
| ISBN (Print) | 9781584883449 |
| State | Published - Jan 1 2003 |
| Externally published | Yes |