Kurniasari, Dian and Riswinda, Azzahra Zulfa and Wamiliana, Wamiliana and Warsono, Warsono (2025) Optimization of Nutrimax Food Supplement Rating Classification Using a Hybrid CNN-LSTM Approach. International Journal of Multidisciplinary Research and Growth Evaluation, 6 (1). pp. 2075-2083. ISSN 2582-7138

Text Optimization of Nutrimax Food Supplement Rating Classification Using a Hybrid CNN-LSTM Approach.pdf Download (433kB)

Abstract

Nutrimax Food Supplement is a company specializing in the production of vitamins and pharmaceuticals, with a 4.9-star rating on the Shopee e-commerce platform. Product ratings and reviews play a crucial role in online purchasing decisions, as consumers often rely on previous buyers' experiences to mitigate the risk of making poor purchasing choices. These reviews typically consist of textual feedback and ratings on a scale of 1 to 5. This study aims to evaluate the performance of product rating classification for Nutrimax Food Supplement using a hybrid Convolutional Neural Network – Long Short-Term Memory (CNN-LSTM) approach. The classification performance is assessed based on accuracy, precision, recall, and F1-score. CNN and LSTM are widely used techniques in text processing, each offering distinct advantages. CNN excels at extracting features from text, while LSTM is particularly effective in capturing and retaining sequential context over longer periods. By integrating these models, this study leverages their complementary strengths to enhance classification accuracy. The experimental results demonstrate that the hybrid CNN-LSTM approach achieves outstanding performance, with an accuracy of 0.994, precision of 0.994, recall of 1.00, and an F1-score of 0.996. These findings indicate that the hybrid CNN-LSTM model is highly effective for consumer review classification. The insights gained from this study can help businesses better understand customer feedback and improve product quality.

Item Type:	Article
Subjects:	Q Science > QA Mathematics
Divisions:	Fakultas Matematika dan Ilmu Pengetahuan Alam (FMIPA) > Prodi Matematika
Depositing User:	DIAN KURNIASARI
Date Deposited:	28 May 2025 01:25
Last Modified:	28 May 2025 01:25
URI:	http://repository.lppm.unila.ac.id/id/eprint/54591

Actions (login required)

View Item