 |
International Society of Science and Applied Technologies |
| Review Rating Prediction for Smart Health Monitoring Wearable Devices Using Neural Networks | ||||
| Author |
Rui Wang
|
|||
| Co-Author(s) |
Jeongsub Choi; Yaoyao Jia; James Bardes; Bradley S Price; Mengmeng Zhu
|
|||
| Abstract | Smart health-monitoring wearable devices
(SHMWDs) have gained increasing attention used in personal healthcare because of their ability to monitor physiological signals and physical activities at relatively low cost. Despite SHMWDs incorporate diverse product features, the relationships between these features and customer satisfaction remain underexplored. Customer reviews provide valuable information regarding product performance and user experience, yet they have rarely been systematically utilized in SHMWD analysis. This study proposes a neural network-based framework to predict customer review ratings using SHMWD product features. The proposed framework integrates feature characterization, model development, and prediction evaluation through data preprocessing, hyperparameter tuning, and results comparison. A realworld dataset collected from SHMWD customer reviews is used for evaluation. Experimental results demonstrate that the proposed model outperforms benchmark machine learning methods in predicting customer reviews. The findings highlight the effectiveness of neural networks in capturing complex relationships between SHMWD features and customer satisfaction, providing practical insights for the design and development of future SHMWDs.
|
|||
| Keywords | Smart health-monitoring wearable device, review rating prediction, neural networks | |||
| Article #: RQD2026-55 | ||||
Proceedings of 31st ISSAT International Conference on Reliability & Quality in Design |