ISSN: 0973-7510

E-ISSN: 2581-690X

K.M. Subramanian1 and K. Venkatachalam2
1Department of Computer Science Engineering, Erode Sengunthar Engineering College, Erode, Tamilnadu, India.
2Department of Electronics and Communication Engineering, Velalar College of Engineering and Technology, Erode, Tamilnadu, India.
J Pure Appl Microbiol. 2015;9(Spl. Edn. Aug.):139-146
© The Author(s). 2015
Received: 10/02/2015 | Accepted: 28/04/2015 | Published: 31/08/2015
Abstract

With search for health related information increasing in the web and availability of various blogs for medical information, analysis of subjective information is challenging. Opinion Mining is an emerging area, which labels an opinion as positive or negative. Opinion mining has been extensively used in product / movie reviews and to the best of our knowledge has not been investigated on data collected from medical question and answer blogs. Feature selection for labelling is challenging, due to the various medical terminology used. For example, the common cold is also called rhino pharyngitis, upper respiratory tract infection or naso-pharyngitis. This work investigates a novel feature selection technique using Fish Swarm Optimization, which identifies key medical concepts found in blogs and labels whether the opinion of the patient is positive or negative for the treatment undertaken.Three classification algorithms Naïve Bayes, K Nearest Neighbour and Classification and Regression Trees (CART) algorithms were used to investigate the quality of the extracted features.

Keywords

Opinion Mining, Principal Component Analysis (PCA), Kernel PCA, Fish Swarm Optimization (FSO)

Article Metrics

Article View: 0

Share This Article

© The Author(s) 2015. Open Access. This article is distributed under the terms of the Creative Commons Attribution 4.0 International License which permits unrestricted use, sharing, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.