@article{article_1815607, title={A deep learning approach for assessing consumer sentiment in amazon dataset}, journal={Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi}, volume={31}, year={2025}, DOI={10.5505/pajes.2025.45753}, author={Khalıd, Nazeeha Sayghn Khalid and Savaş, Serkan}, keywords={Tüketici Duyarlılık Analizi, Derin Öğrenme, Uzun Kısa Süreli Bellek, Amazon, Makine Öğrenmesi}, abstract={This study investigates the effectiveness of machine learning techniques in consumer sentiment analysis using Amazon product reviews. The main objective of the study is to use machine learning models to evaluate and predict the correspondence between textual reviews and the corresponding star ratings. In addition to classical machine learning algorithms such as Support Vector Machine, Decision Tree and K-Nearest Neighbor, deep learning algorithm such as Long Short-Term Memory is also used in the study. The performances of these models are compared and the impact of the number of hidden layers on the accuracy of deep learning models is analyzed. The findings of the study demonstrate the effectiveness of Long Short-Term Memory networks in handling the complexities of natural language in consumer reviews. The Long Short-Term Memory model performed best on the test dataset with an accuracy of 98%. In contrast, the Decision Tree model performed the worst with an accuracy of 77.8%. These results provide important insights into the effectiveness of different machine learning techniques in sensitivity analysis. Furthermore, these results provide an important foundation for future research in this rapidly evolving field.}, number={7}, publisher={Pamukkale Üniversitesi}