EVALUATING CUSTOMER SATISFACTION USING MACHINE LEARNING TECHNIQUES / LYSE DEBORAH HAKIZIMANA; SUPERVISOR: ASST. PROF. DR KIAN JAZAYERI

Yazar: Katkıda bulunan(lar):Dil: İngilizce 2023Tanım: vii, 51 sheets; 31 cm. 1 CD-ROMİçerik türü:
  • text
Ortam türü:
  • unmediated
Taşıyıcı türü:
  • volume
Diğer başlık:
  • CASE STUDY OF U.S. AIRLINE INDUSTRY
Konu(lar): Tez notu: Thesis (MSc) - Cyprus International University. Institute of Graduate Studies and Research Management Information Systems Department Özet: ABSTRACT In today's industry environment, the airline company is increasingly focused on comprehending and responding to client needs and feedback to improve general levels of satisfaction. By measuring tweets sentiment, airlines can win a complete comprehension of customer‟s sentiments and opinions which can help airline industries in the creation of quality improvement plans. In this study, we used sentiment analysis, one of which understands text-sensitive applications, to find consumers‟ opinions. Machine learning algorithms have been developed for categorizing Twitter postings as positive, negative, or neutral. We trained our model on tweets from six US airlines, and this study explores the use of predictive analytics using the Naive Bayes algorithm which is a useful tool for extracting useful insights. The text data is cleaned using preprocessing techniques to ensure adequate input for the Naive Bayes classifier. Random Forest classifier and the K-Nearest Neighbors algorithm were combined with a model constraint classifier to increase the accuracy of Naive Bayes after selecting the most essential features using SelectKBest. This study examines the accuracy of Naive Bayes used for sentiment classification in Twitter data. The findings and insights can be utilized to discover effective practices as well as areas for more investment in order to improve customer satisfaction. The algorithm's probabilistic approach can classify tweets in negative, neutral, or positive sentiments by allowing airlines to identify areas of customer complaint and areas of excellence. In this work, the performance parameters of the proposed solution were considered to be recall, precision, and F1-score. Naive Bayes classifier shows a capacity to correctly categorize the opinions conveyed through tweets. The collected findings offer light on common consumer complaints, allowing airlines to promptly resolve issues and target initiatives to increase success. Keywords: Customer satisfaction, K-Nearest Neighbors, Naive Bayes, Random Forest, Select KBest, Sentiment Analysis, Stacking Model, Twitter Data and US Airline
Materyal türü: Thesis
Mevcut
Materyal türü Geçerli Kütüphane Koleksiyon Yer Numarası Durum Notlar İade tarihi Barkod Materyal Ayırtmaları
Thesis Thesis CIU LIBRARY Tez Koleksiyonu Tez Koleksiyonu YL 3163 H25 2023 (Rafa gözat(Aşağıda açılır)) Kullanılabilir Management Information Systems Department T3544
Suppl. CD Suppl. CD CIU LIBRARY Görsel İşitsel YL 3163 H25 2023 (Rafa gözat(Aşağıda açılır)) Kullanılabilir Management Information Systems Department CDT3544
Toplam ayırtılanlar: 0

Thesis (MSc) - Cyprus International University. Institute of Graduate Studies and Research Management Information Systems Department

Includes bibliography (sheets 50-51)

ABSTRACT
In today's industry environment, the airline company is increasingly focused on
comprehending and responding to client needs and feedback to improve general
levels of satisfaction. By measuring tweets sentiment, airlines can win a complete
comprehension of customer‟s sentiments and opinions which can help airline
industries in the creation of quality improvement plans. In this study, we used
sentiment analysis, one of which understands text-sensitive applications, to find
consumers‟ opinions. Machine learning algorithms have been developed for
categorizing Twitter postings as positive, negative, or neutral. We trained our model
on tweets from six US airlines, and this study explores the use of predictive analytics
using the Naive Bayes algorithm which is a useful tool for extracting useful insights.
The text data is cleaned using preprocessing techniques to ensure adequate input for
the Naive Bayes classifier. Random Forest classifier and the K-Nearest Neighbors
algorithm were combined with a model constraint classifier to increase the accuracy
of Naive Bayes after selecting the most essential features using SelectKBest. This
study examines the accuracy of Naive Bayes used for sentiment classification in
Twitter data. The findings and insights can be utilized to discover effective practices
as well as areas for more investment in order to improve customer satisfaction. The
algorithm's probabilistic approach can classify tweets in negative, neutral, or positive
sentiments by allowing airlines to identify areas of customer complaint and areas of
excellence. In this work, the performance parameters of the proposed solution were
considered to be recall, precision, and F1-score. Naive Bayes classifier shows a
capacity to correctly categorize the opinions conveyed through tweets. The collected
findings offer light on common consumer complaints, allowing airlines to promptly
resolve issues and target initiatives to increase success.
Keywords: Customer satisfaction, K-Nearest Neighbors, Naive Bayes, Random
Forest, Select KBest, Sentiment Analysis, Stacking Model, Twitter Data and US
Airline

Araştırmaya Başlarken  
   Sıkça Sorulan Sorular