SMS sentiment classification using an evolutionary optimization based fuzzy recurrent neural network
- 11 April 2023
- journal article
- research article
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 82 (27) , 42207-42238
Abstract
Sentiment analysis using the inbox message polarity is a challenging task in text mining, this analysis is used to differentiate spam and ham messages in mail. Polarity estimation is mandatory for spam and ham identification, whereas developing a perfect architecture for such classification is the hot demanding topic. To fulfill that, fuzzy based Recurrent Neural network-based Harris Hawk optimization (FRNN-HHO) is introduced, which performs post-classification over the classified messages (spam and ham). Previously the authors tried to classify the spam and ham messages from the collection of SMSs. But sometimes, the spam messages may incorrectly be classified within the ham classes. This misclassification may reduce the accuracy. The sentiment analysis process is performed over the classified messages to improve such classification accuracy. The spam and ham messages from the available data are classified using a Kernel Extreme Learning Machine (KELM) classifier. The sentiment analysis and classification based experimental evaluation is carried out using accuracy, recall, f-measure, precision, RMSE, and MAE. The performance of the proposed architecture is evaluated using threedifferent datasets: SMS, Email, and spam-assassin. The Area under the curve (AUC) of the proposed approach is found to be 0.9699 (SMS dataset), 0.958 (Email dataset), and 0.95 (spam assassin).Keywords
This publication has 36 references indexed in Scilit:
- An unsupervised aspect extraction strategy for monitoring real-time reviews streamInformation Processing & Management, 2019
- LSA Based Smart Assessment Methodology for SDN Infrastructure in IoT EnvironmentInternational Journal of Parallel Programming, 2018
- Web spam classification method based on deep belief networksExpert Systems with Applications, 2018
- Sentiment analysis in teaching evaluations using sentiment phrase pattern matching (SPPM) based on association miningInternational Journal of Machine Learning and Cybernetics, 2018
- Lexicon based feature extraction for emotion text classificationPattern Recognition Letters, 2017
- Feature selection based on a normalized difference measure for text classificationInformation Processing & Management, 2017
- Empirical Study of Feature Selection Methods for High Dimensional DataIndian Journal of Science and Technology, 2016
- Word sense disambiguation based sentiment lexicons for sentiment classificationKnowledge-Based Systems, 2016
- SMS spam filtering and thread identification using bi-level text classification and clustering techniquesJournal of Information Science, 2016
- Email thread identification using latent Dirichlet allocation and non-negative matrix factorization based clustering techniquesJournal of Information Science, 2015