ABSTRACT
Medical wearable gadgets have gained popularity due to their ability to improve healthcare and enable personalized monitoring and treatment. To improve these devices’ design and operation, consumers’ experiences and preferences must be understood. This chapter offers a short text mining (STM) based machine learning model to analyze medical wearable device user experiences. STM may find and analyze underlying trends in a large collection of user reviews, revealing user perspectives and concerns. We collected user evaluations from multiple internet sites to operationalize our methodology. Fitness trackers, smartwatches, and continuous glucose monitors are included in this dataset. Textual data allowed us to use natural language processing (NLP) to extract subjects and sentiments. To boost model performance, text data was tokenized, stemmed, and stopped. Using the short-term memory (STM) model, we found several key elements that describe medical wearable device users’ experiences. Device precision and dependability, user interface and friendliness, data confidentiality and protection, device compatibility and integration, and user satisfaction were covered. We identified key areas for improvement and addressed user complaints by quantifying the prevalence and sentiment of each topic.
