No abstract

Since March 6, when Colombia confirmed its first case of the coronavirus disease (Covid-19), the country healthcare system, with a limited testing capability, has struggled to monitor and report current cases. At the outbreak of a virus, data on cases is sparse and commonly severe cases, with a higher probability of a fatal resolution, are detected at a higher rate than mild cases. In addition, in an under-sampling situation, the number of total cases is under-estimated leading to a biased case fatality rate estimation, most likely inflating the virus mortality. Real time estimation of case fatality ratio can also be biased downwards by overlooking the delay between symptoms onset to death. In this communication, using reported data from Instituto Nacional de Salud up to December 28, we estimate the case fatality rate for Covid-19 in Colombia and some of its regions and cities adjusting for delay from onset to death. We then apply the method proposed by Russell et al., and use our corrected case fatality rate to estimate the percentage of Covid-19 cases reported in Colombia as 42.95% (95% confidence interval: 42.50-43.41), which corresponds to a total of 3'661,621 estimated Covid-19 cases in the country.

Students' perception of classes measured through their opinions on teaching surveys allows to identify deficiencies and problems, both in the environment and in the learning methodologies. The purpose of this paper is to study, through sentiment analysis using natural language processing (NLP) and machine learning (ML) techniques, those opinions in order to identify topics that are relevant for students, as well as predicting the associated sentiment via polarity analysis. As a result, it is implemented, trained and tested two algorithms to predict the associated sentiment as well as the relevant topics of such opinions. The combination of both approaches then becomes useful to identify specific properties of the students' opinions associated with each sentiment label (positive, negative or neutral opinions) and topic. Furthermore, we explore the possibility that students' perception surveys are carried out without closed questions, relying on the information that students can provide through open questions where they express their opinions about their classes.

No abstract