Classification-based Search and Knowledge Discovery

A significant bottleneck in advancing toward the Semantic Web for supporting intelligent web services is efficient assignment of content-based terminologies to vast quantities of web resources.  Researches considering prospective solutions tend to take two extreme positions: fully automated or fully manual approaches.  We believe there is a middle ground that can take advantage of existing pre-classified content and also integrate the human in the loop in useful ways.

The Classification-based Search and Knowledge Discovery (CSKD) project aims to leverage an existing body of manually classified documents to enhance information retrieval and knowledge discovery on the Web.  CSKD research, which explores methods of leveraging both the ontological and link-structural knowledge embedded in classified corpora of Web documents for searching and organizing the Web, is a multi-dimensional project that entails investigations in such area as machine learning, classification, clustering, link analysis, and fusion.

• CSKD Overview

• EPA Topics applications
  • Tree View
  • Concept Search
  • Topic Search

Project Members:
Elin Jacob,   Kiduk Yang,   Barbara Gelwick   Nicholas George,   Gavin La Rowe,   Seungmin Lee,   Aaron Loehrlein,   Ning Yu,   Hui Zhang,