Context identification of scientific papers via agent-based model for text mining (ABM-TM)

Moamin A. Mahmoud, Mohd Sharifuddin Ahmad, Mohd Zaliman M. Yusoff, Aida Mustapha

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

In this paper, we propose an agent-based text mining algorithm to extract potential context of papers published in the WWW. A user provides the agent with keywords and assigns a threshold value for each given keyword, the agent in turn attempts to find papers that match the keywords within a defined threshold. To achieve context recognition, the algorithm mines the keywords and identifies the potential context from analysing a paper’s abstract. The mining process entails data cleaning, formatting, filtering, and identifying the candidate keywords. Subsequently, based on the strength of each keyword and the threshold value, the algorithm facilitates the identification of the paper’s potential context.

Original languageEnglish
Pages (from-to)51-61
Number of pages11
JournalStudies in Computational Intelligence
Volume572
DOIs
Publication statusPublished - 01 Jan 2015

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Context identification of scientific papers via agent-based model for text mining (ABM-TM)'. Together they form a unique fingerprint.

  • Cite this