ACIRD: Intelligent Internet Document Organization and Retrieval

Authors

  • Shian-Hua Lin Author
  • Meng C. Chen Author
  • Jan-Ming Ho Author
  • Yueh-Ming Huang Author

DOI:

https://doi.org/10.70705/ppp.ir.2023.v01.i01.pp23-29

Keywords:

Document classification, Data mining, Information retrieval, Search engine

Abstract

Automatic Classifier for the Internet Resource Discovery (ACIRD) is a smart Internet information system that employs machine
learning to categorize and retrieve documents from the Internet. It is presented in this article. The three parts that make
up ACIRD are a two-stage search engine, a document classifier, and a knowledge acquisition procedure. Automatically acquiring
classification information from classified Internet documents is part of ACIRD’s knowledge acquisition methodology. In order
to sort freshly acquired documents from the Internet into one or more categories, the document classifier uses its learnt categorization
expertise. When compared to human specialists, ACIRD achieves comparable or higher performance in knowledge
acquisition and document categorization, according to the experimental findings. In order to help users find information from
diverse and large-scale Internet documents, the ACIRD two-phase search engine uses the learned classification knowledge and
the provided class lattice to provide results that are hierarchically organized and easy to navigate, rather than the usual flatranked
document list.

Downloads

Published

2023-05-22

How to Cite

ACIRD: Intelligent Internet Document Organization and Retrieval. (2023). Intelligent Retrieval Journal, 1(1), 23-29. https://doi.org/10.70705/ppp.ir.2023.v01.i01.pp23-29