ABSTRACT
: The effects of the pandemic can translate into a variety of physical and emotional reactions that are affecting the population, particularly the elderly Panamanian population, who have not been able to overcome the mainly emerging challenges of an infectious disease with health implications. physical and has also profoundly affected their well-being and mental health. To allow the Panamanian elderly population to improve emotional self-control and mental relaxation, we propose a software architecture for the development of a recommendation system integrating: artificial intelligence (AI), internet of things (IoT) and mobile applications. Keywords: Covid-19, AI, IoT, Mobile apps, Machine learning. 1.Introducción La Covid-19 es, sin lugar a duda, la mayor catástrofe del siglo XXI, probablemente la crisis global más significativa después de la segunda guerra mundial. En este artículo, proponemos el diseño de una arquitectura altamente integral y flexible basada en diferentes elementos de TIC que permitirá extraer datos de un sensor, analizarlos y realizar recomendaciones a pacientes panameños adultos mayores con afecciones psicológicas o reacciones emocionales posteriores al contagio de la Covid-19 (post-covid-19), basado en la utilización de componentes como IA, IoT y aplicaciones móviles para lograr el autocontrol emocional y relajación mental.
ABSTRACT
: Twitter is an important social network and information channel where opinions (tweets) can be obtained and processed in real time that can be explored, analyzed and organized to make better decisions. Opinion mining is a natural language processing task that identifies user opinions as positive, negative, or neutral. To allow Panamanian health organizations to detect opportunities to improve the quality of medical care, we propose to classify the tweets the analysis of two approaches: deep learning and machine learning for to appreciate which is more precise. En su estudio (Islam & Zhang, 2016) proponen un marco de trabajo usando una red neuronal convolucional (CNN) para el análisis de sentimiento visual que busca predecir el sentimiento del contenido visual.