|
|
Demo: EbizPort
|
| [Start
EbizPort demo]
| Introduction |
 |
To
make good decisions, businesses try
to gather good intelligence information.
Yet managing large quantities of unstructured
information and data stand in the
way of greater business knowledge.
Effective tools for increasing business
intelligence used to access relevant
content, in different formats must
include analysis tools for searching,
browsing, and summarization.
Useful business intelligence content
needs to be credible, timely, and
relevant. We created eBizPort
to facilitate the process of acquiring
business intelligence in the Information
Technology industry. The eBizPort
contains content from the leading
news and commentary providers in the
IT domain, which was collected using
a new vertical collection-building
technique. We have integrated
a number of post-retrieval tools to
support browsing and investigate techniques
to overcome information overload.
|
|
| Acknowledgements |
|
We
would like to express our gratitude
to NSF Digital Library Initiative-2,
"High-performance Digital Library
Systems: From Information Retrieval
to Knowledge Management,"
IIS-9817473, April 1999-March 2002
|
|
| Approach
& Methodology |
|
Content
(over 400,00 URLs) from the following
providers:
-
Computerworld
- The Industry Standard
-
Wired
- PCWorld
-
InternetWeek
-
InfoWorld
-
C|Net
-
IDG
-
ITWord
-
CIO
- Business 2.0
- Informationweek
-
RedHerring
Techniques:
- Meta-searching spider that gathers
content from major news providers
- Java parsing and indexing programs
to create importable database files
- Kohonen Self-Organization Map
(SOM): Algorithms-single and multi-layer
self-organizing maps for information
categorization and visualization.
- Database stored procedures to
import and manage inverted index
and provide searching functionality
- SOM display
- Folder Clustering of main document
topics
- AZ Noun Phraser for topic extraction
|
|
| Team
Members |
|
| Publications |
|
Byron
Marshall, Dan McDonald, Hsinchun Chen,
Wingyan Chung
“EBizPort: Collecting
and Analyzing Business Intelligence
Information”
Journal of the American Society for
Information Science and Technology (JASIST)
Special Issue on Document Search Interface
Design for Large-scale Collections and
Intelligent Access, (accepted for publication
2003, forthcoming 2004)
|
|
|
| |
|
|
|
|
|
|
|
