Benchmark de chatbots para o redesign das interfaces conversacionais do projeto Amive

Abstract

Major depression is a serious illness that affects more than 15% of the Brazilian population. Among university students, the prevalence is even higher. Researchers from the Amive project, funded by FAPESP, are training computational models to identify university students with a possible depressive profile. The model considers mobile sensors and Online Social Networks (RSO) data. The outputs of the classification model influence the delivery of interventions designed within the scope of the Amive project. Based on the classification, a chatbot starts conversations about determinants of mental suffering in the university context, offering health education content and pointing out support techniques and places. Therefore, these conversations must be carried out welcoming and intuitive. With this in mind, this undergraduate final work aims to explore successful chatbot solutions, to extract design elements to add to the Amive project proposal. To this end, a Benchmark was carried out with eight systems comparing aspects that included communication format, demonstration of user reaction to messages, and graphic representation (avatar). As a result, five suggestions for improvements to the design solution were listed and applied in a redesign process that generated a medium-fidelity prototype.