Senti‐eSystem: A sentiment‐based eSystem‐using hybridized fuzzy and deep neural network for measuring customer satisfaction. (3rd August 2020)

• Record Type: Journal Article
• Authors: Asghar, Muhammad Zubair; Subhan, Fazli; Ahmad, Hussain; Khan, Wazir Zada; Hakak, Saqib; Gadekallu, Thippa Reddy; Alazab, Mamoun
• Other Names: Baker Thar guestEditor.; Al‐Jumeily Dhiya guestEditor.; Maamar Zakaria guestEditor.; Tari Zahir guestEditor.
• Is Part Of: Software, practice & experience. Volume 51:Number 3(2021)
• Page Start: 571
• Page End: 594
• Publication Date: 2020-08-03
• Subjects: attention mechanism -- customer satisfaction -- deep neural network -- eSystem -- fuzzy system -- hybridized fuzzy and deep neural network -- twitter; Computer software -- Periodicals; Computer programming -- Periodicals; Computer programs -- Periodicals; 005.3
• DOI: 10.1002/spe.2853
• Languages: English
• ISSNs: 0038-0644

Abstract

Summary: In the competing era of online industries, understanding customer feedback and satisfaction is one of the important concern for any business organization. The well‐known social media platforms like Twitter are a place where customers share their feedbacks. Analyzing customer feedback is beneficial, as it provides an advantage way of unveiling customer interests. The proposed system, namely Senti‐eSystem, aims at the development of sentiment‐based eSystem using hybridized Fuzzy and Deep Neural Network for Measuring Customer Satisfaction to assist business organizations for improving the quality of their services and products. The proposed approach initially deploys a Bidirectional Long Short Term Memory with attention mechanism to predict the sentiment polarity that is positive and negative, followed by Fuzzy logic approach to determine the customer satisfaction level, which further strengthens the capabilities of the proposed approach. The system achieves an accuracy of 92.86%, outperforming the previous state‐of‐art lexicon‐based approaches. Moreover, the effectiveness of the proposed system is also validated by applying the statistical test.