Journal of Computer Science and Technology Studies ISSN: 2709-104X DOI: 10.32996/jcsts Journal Homepage: www.al-kindipublisher.com/index.php/jcsts JCSTS AL-KINDI CENTER FOR RESEARCH AND DEVELOPMENT Copyright: © 2023 the Author(s). This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC-BY) 4.0 license (https://creativecommons.org/licenses/by/4.0/). Published by Al-Kindi Centre for Research and Development, London, United Kingdom. Page | 194 | RESEARCH ARTICLE Transforming Customer Experience in the Airline Industry: A Comprehensive Analysis of Twitter Sentiments Using Machine Learning and Association Rule Mining Maliha Tayaba 1 , Eftekhar Hossain Ayon 2 ✉ Md Tuhin Mia 3 , Malay Sarkar 4 , Rejon Kumar Ray 5 , Md Salim Chowdhury 6 , Md Al-Imran 7 Nur Nobe 8 Bishnu Padh Ghosh 9 , MD Tanvir Islam 10 and Aisharyja Roy Puja 11 1 Department of Computer Science, University of South Dakota, Vermillion, South Dakota, USA 2 Department of Computer & Info Science, Gannon University, Erie, Pennsylvania, USA 3,9 School of Business, International American University, Los Angeles, California, USA 4,11 Department of Management Science and Quantitative Methods, Gannon University, USA 5 Department of Business Analytics Business Analytics, Gannon University, USA 6,7 College of Graduate and Professional Studies Trine University, USA 8 Department of Healthcare Management, Saint Francis College, Brooklyn, New York, USA 10 Department of Computer Science, Monroe College, New Rochelle, New York, USA Corresponding Author: Eftekhar Hossain Ayon, E-mail: ayon001@gannon.edu | ABSTRACT The airline industry places significant emphasis on improving customer experience, and Twitter has emerged as a key platform for passengers to share their opinions. This research introduces a machine learning approach to analyze tweets and enhance customer experience. Features are extracted from tweets using both the Glove dictionary and n-gram methods for word embedding. The study explores various artificial neural network (ANN) architectures and Support Vector Machines (SVM) to create a classification model for categorizing tweets into positive and negative sentiments. Additionally, a Convolutional Neural Network (CNN) is developed for tweet classification, and its performance is compared with the most accurate model identified among SVM and multiple ANN architectures. The results indicate that the CNN model surpasses the SVM and ANN models. To provide further insights, association rule mining is applied to different tweet categories, revealing connections with sentiment categories. These findings offer valuable information to help airline industries refine and enhance their customer experience strategies. | KEYWORDS Airline Industry; Twitter Sentiments; Machine Learning; Rule Mining | ARTICLE INFORMATION ACCEPTED: 01 December 2023 PUBLISHED: 22 December 2023 DOI: 10.32996/jcsts.2023.5.4.20 1. Introduction In the dynamic landscape of the airline industry, enhancing customer experience has become a pivotal focus. With Twitter emerging as a prominent platform for air travelers to voice their opinions and feedback, this study employs a machine learning approach to analyze tweets, aiming to positively impact customer experience. The research involves feature extraction from tweets using both the Glove dictionary approach and the n-gram approach for word embedding. Subsequently, various (khan, 2022,2023,2023,2023) artificial neural network (ANN) architectures, Support Vector Machines (SVM), and Convolutional Neural Networks (CNN) are explored to construct a sentiment analysis classification model, categorizing tweets into positive and negative sentiments. The study delves into the methodological aspects, detailing the collection of tweets from prominent airlines and the application of techniques such as n-gram models and GloVe for effective feature representation. Sentiment classification, employing SVM,