Role of Text Mining in Information Extraction and Information Management
ENGLISH

M. Natarajan
2005 DESIDOC Bulletin of Information Technology  
This article deals with the definitions of text mining and the need for it. The components of text mining are explained as information retrieval, information processing and information integration. The powerful technique that helps to identify the relevant S&T literature is enumerated with five primary conditions for information extraction. The three stages of Knowledge Discovery in Data and Data Mining (KDD) process is given with the applications of text mining. Applications of text mining
more » ... from Information retrieval, bioinformatics, patent analysis, sorting gene expression, mining hospital records and multilingual approach to cross-lingual text retrieval (CLTR), analysis of e-mails, etc. Also explained the current status like new methods for text analysis in biology and medicine, the software viz. TextAnalyst meant for semantic analysis, navigation and search of unstructured texts with the 'Linking Information for Novel Discovery and Insight' (LINDI) project at Berkeley for helping the researchers. The internationally leading consortium for text mining viz. National Centre for Text Mining at UMIST with four UK partner institutions has been given. The limitations and benefits of text mining are given and concluded that library and information science professionals should implement the same for providing the relevant information from the vast amount of information.
doi:10.14429/dbit.25.4.3663 fatcat:qfzdgomajrdbnmjorplfaullfq