An intelligent agent-based system for multilingual financial news digest. (1st October 2010)

• Record Type: Journal Article
• Authors: Liu, James N.K.; Ho, M.K.
• Is Part Of: International journal of intelligent information and database systems. Volume 4:Number 4(2010)
• Page Start: 337
• Page End: 354
• Publication Date: 2010-10-01
• Subjects: intelligent agents -- multilingual news extraction -- document categorisation -- fuzzy classification -- agent-based systems -- multi-agent systems -- MAS -- financial news digest -- online financial news -- internet -- keyword classification -- information retrieval -- fuzzy clustering -- category profiles -- search interface -- document browsing; Database management -- Computer programs -- Periodicals; Information retrieval -- Computer programs -- Periodicals; Information storage and retrieval systems -- Computer programs -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Intelligent agents (Computer software) -- Periodicals; 006.33
• Languages: English
• ISSNs: 1751-5858

Abstract

Online financial news from different sources is widely available on the internet. There are systems available to help investors extract and analyse the financial news from these sources but many of these systems present news articles without categorisation and do not provide enough query options to accurately yet comprehensively search for news. In this paper, we extend our previous work to develop an intelligent agent-based system for multilingual news extraction. We adopt a document categorisation approach based on fuzzy keyword classification. The system applies fuzzy clustering to obtain a classification of keywords by concepts of the category. A category profile is developed and used as a search interface for document browsing. Experimental results show that the proposed categorise news agent is capable of categorising news documents with a reasonable rate of accuracy and the grouping news agent is able to assemble news groups of similar contents to facilitate information retrieval.