Home // IMMM 2013, The Third International Conference on Advances in Information Mining and Management // View article

Analysis of Medical Publications with Latent Semantic Analysis Method

Authors:
José Román Herrera-Morales
Liliana Ibeth Barbosa-Santillán

Keywords: Latent Semantic Analysis; Semantic Relatedness; Semantic Relevance; Text Processing

Abstract:
This article presents a review of the Latent Semantic Analysis (LSA) method used to extract knowledge from large sets of text documents, describing its origins, main applications, basic operation and dimensionality optimization. To evaluate its performance and usefulness in identifying semantic relatedness a series of experiments were conducted with various collections of texts, varying number of files that were part of each corpus and using different indexes. It was shown that LSA can serve as a mechanism for grouping and classifying documents that are related to the themes, in particular in obedience, to the search expressions according to their semantic relevance. It was also evident, however, that the computational performance of LSA will deteriorate as more files are added to generate indexes, since index and search response times increased significantly.

Pages: 81 to 86

Copyright: Copyright (c) IARIA, 2013

Publication date: November 17, 2013

Published in: conference

ISSN: 2326-9332

ISBN: 978-1-61208-311-7

Location: Lisbon, Portugal

Dates: from November 17, 2013 to November 21, 2013