Tengjie Qiu¹ and Daniel Carter², ¹USA, ²California State Polytechnic University, USA

We wanted to create a better, more trustworthy solution for caretakers to determine the emotion and feelings their patients are experiencing. This is useful for caretakers to adjust how they go about caring for their patients. To solve this, we decided to create a mobile consumer application. Architecturally, the user (caretaker) will be using this mobile app as a front end which will record and send audio of the patient to a backend service. The service will be hosted on AWS and it will be a sentiment analysis algorithm written in Python. The service will analyze and determine the feeling of the patient and send it back to the front end for the caretaker to see. The front end was written in Flutter. To evaluate the effectiveness of the proposed mobile application, we conducted testing focused on two key aspects: accuracy and response speed. The accuracy of the sentiment analysis algorithm was assessed by comparing the analysis results of pre-recorded audio with predetermined feelings. This evaluation aimed to measure the algorithm's ability to correctly identify and classify emotions. Additionally, we tested the speed of response by sending audio samples of varying lengths, ranging from 2 seconds to 60 seconds. The objective was to determine the optimal response time for providing feedback on the user's mood. Our findings revealed that the algorithm demonstrated high accuracy in detecting emotions within the tested audio samples. Moreover, the ideal response time for generating feedback was identified as 5 seconds, striking a balance between promptness and accuracy. These testing results validate the efficacy of the proposed application in accurately analyzing sentiment and providing timely responses, supporting its potential as an effective tool for monitoring and addressing the mental well-being of elderly individuals. This proposed mobile app, utilizing sentiment analysis, offers a convenient and accurate means of monitoring and addressing the mental well-being of elderly individuals. Its potential to combat loneliness and provide timely support makes it a valuable tool for improving their overall quality of life.

Sentiment Analysis, Audio Data, Mobile Application, Mental Disorder