Abstract
A fundamental problem for analysis of multidimensional text databases is efficient and effective support of various kinds of online applications, such as summarizing the content of text cells and comparing the contents across multiple text cells. In this paper, we propose a new infrastructure called MicroTextCluster Cube (or MiTexCube) to support efficient online text analysis on multidimensional text databases by introducing micro-clusters of text documents as a compact representation of text content. Experimental results on a real multidimensional text database show that applications based on the proposed materialized MiTexCube are more efficient than the baseline method of direct analysis based on document units in each cell, without sacrificing much quality of analysis, and MiTexCube naturally accommodates flexible tradeoff between efficiency and quality of analysis.
| Original language | English (US) |
|---|---|
| Pages | 204-218 |
| Number of pages | 15 |
| State | Published - 2011 |
| Event | NASA Conference on Intelligent Data Understanding, CIDU 2011 - Mountain View, CA, United States Duration: Oct 19 2011 → Oct 21 2011 |
Other
| Other | NASA Conference on Intelligent Data Understanding, CIDU 2011 |
|---|---|
| Country/Territory | United States |
| City | Mountain View, CA |
| Period | 10/19/11 → 10/21/11 |
ASJC Scopus subject areas
- Artificial Intelligence
- Software