EHECA-HSWS: A Holistic Method for Improving Menstrual Health App User Experience

Menstrual health and hygiene apps play a crucial role in empowering users to manage their reproductive health. This paper introduces a novel approach, the Ensemble Hybrid Extreme Convolutional Autoencoder-based Harbor Seal Whisker Search algorithm for enhancing menstrual health and hygiene management. The Extreme Gradient Boosting is applied for user segmentation, a Swin Transformer for issue extraction from user reviews, a hybrid Convolutional Neural Network for menstrual pattern tracking, and Autoencoders for anomaly detection. The weighted average ensemble combines outputs, and the Harbor Seal Whiskers Optimization algorithm enhances hyperparameter optimization. Evaluation metrics, including Area Under the Receiver Operating Characteristic Curve, precision, recall, accuracy, F1-score, Mean Squared Error, Mean Absolute Error, computational time, and specificity, demonstrate the model's effectiveness. Comparative analysis with existing methods affirms the superior performance of the Ensemble Hybrid Extreme Convolutional Autoencoder-based Harbor Seal Whisker Search Algorithm in analyzing user behavior and feedback data, ultimately improving the overall user experience during menstruation.