Decision-making process has become extremely difficult especially for the large amount of textual data that companies must analyse to be competitive. The use of Natural Language Processing and Text mining in data discovery allows extracting knowledge from business texts that in the majority occur in unstructured form. The Decision Support System and the Information Technology departments face the new challenges that change poses, relying on linguistic analysis capabilities, no longer based on keyword research but on the syntactic properties, lexical and semantic word. In this paper, we focus on document-driven decision support, describing ways in which business communication performance can be improved by using a natural language interface as NooJ. In order to achieve our goals, we develop Linguistic Resources typically used in Economy knowledge domain, with regard to compound words and multi-word atomic linguistic units (MWALUs).
Using Text Mining and Natural Language Processing to Support Business Decision: Towards a Nooj Application
DELLA VOLPE, Maddalena
;ESPOSITO, FRANCESCA
2016
Abstract
Decision-making process has become extremely difficult especially for the large amount of textual data that companies must analyse to be competitive. The use of Natural Language Processing and Text mining in data discovery allows extracting knowledge from business texts that in the majority occur in unstructured form. The Decision Support System and the Information Technology departments face the new challenges that change poses, relying on linguistic analysis capabilities, no longer based on keyword research but on the syntactic properties, lexical and semantic word. In this paper, we focus on document-driven decision support, describing ways in which business communication performance can be improved by using a natural language interface as NooJ. In order to achieve our goals, we develop Linguistic Resources typically used in Economy knowledge domain, with regard to compound words and multi-word atomic linguistic units (MWALUs).I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.