Title: Optimal neural network to enhance classification accuracy for mining online reviews and opinions using improved PSO

Authors: B. Dhanalakshmi; Arumugam Chandra Sekar

Addresses: Department of Computer Science and Engineering, Sathyabama University, Chennai, India ' Department of Computer Science and Engineering, St. Joseph's College of Engineering, Old Mamallapuram Road, Chennai, India

Abstract: While using rapid growth from World Wide Web, there is volatile improve in the user-produced subject matter such as purchaser evaluations, websites, discussion community forums, social networks and so forth In previous work, we have implemented opinion mining using three phase. They are: 1) data pre-processing; 2) opinion extraction; 3) opinion mining. In feature extraction, features, such as term frequency, part of speech (POS), syntax, negation and term-based features beyond term unigrams were extracted from the words in documents. In the final step, ranking and classification was done. In the present work, we will implement the same three phases as previous work but with different process in each of the following steps such as: 1) data reprocessing; 2) opinion extraction; 3) opinion mining. The second phase will be classified into two, i.e., feature extraction and opinion extraction. After feature extraction, we extract useful information related to item's features and use to rate them as positive, neutral, or negative.

Keywords: artificial neural network; ANN; improved PSO algorithm; decision tree algorithm; opinion extraction; opinion mining.

DOI: 10.1504/IJNVO.2018.093653

International Journal of Networking and Virtual Organisations, 2018 Vol.18 No.4, pp.338 - 356

Received: 27 Jun 2016
Accepted: 24 Nov 2016
Published online: 31 Jul 2018 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article