Institutional Repository
Technical University of Crete
Technical University of Crete
EN
|
EL
| URI: | http://purl.tuc.gr/dl/dias/A668BD61-3576-4F6C-8063-7A45749BEE72 | ||
| Year | 2025 | ||
| Type of Item | Diploma Work | ||
| License |
|
||
| Bibliographic Citation | Charalampos Tsapakos, "Comparison of natural language processing algorithms for customer satisfaction analysis", Diploma Work, School of Production Engineering and Management, Technical University of Crete, Chania, Greece, 2025 https://doi.org/10.26233/heallink.tuc.103482 | ||
| Appears in Collections |
This thesis explores the application of Natural Language Processing (NLP) techniques for analyzing customer satisfaction through online review data. The study begins by presenting the theoretical background and capabilities of the MATLAB Text Analytics Toolbox, followed by the implementation of core NLP tasks such as sentiment analysis, topic modeling, and text classification. To assess the effectiveness of different approaches, a comparative analysis is conducted between traditional methods available in the MATLAB environment and state-of-the-art language models, including GPT-4 and BERT.The research aims to evaluate the accuracy, interpretability, and practical applicability of each technique by extracting insights from customer feedback. By leveraging real-world data, this work highlights how advanced NLP can be integrated into consumer analytics, contributing to more informed business decisions and enhancing user experience evaluation. The findings are expected to inform future implementations of text analysis tools in both academic research and industry practices.
Copyright © DIAS 2013
