GWRM: An R Package for Identifying Sources of Variation in Overdispersed Count Data

Modeling COVID-19 daily cases in Senegal using a generalized Waring regression model

The rapid spread of the COVID-19 pandemic has triggered substantial economic and social disruptions worldwide. The number of infection-induced deaths in Senegal in particular and West Africa in general are minimal when compared with the rest of the world. We use count regression (statistical) models such as the generalized Waring regression model to forecast the daily confirmed COVID-19 cases in Senegal. The generalized Waring regression model has an advantage over other models such as the negative binomial regression model because it considers factors that cannot be observed or measured, but that are known to affect the number of daily COVID-19 cases. Results from this study reveal that the generalized Waring regression model fits the data better than most of the usual count regression models, and could better explain some of the intrinsic characteristics of the disease dynamics.

How do sentiments affect virality on Twitter?

Virality on Twitter is catching the attention of researchers, trying to identify factors which increase or decrease the probability of retweeting. We study how terms expressing sentiments affect retweeting frequencies by means of a regression model on the number of retweets, which is specially accurate to deal with virality. We focus on the Spanish political situation during the pseudo-referendum held in Catalonia on 1 October 2017. We have found that the use of negativity in a tweet increases the probability of retweeting and that iSOL lexicon is the one that better determines the relationship between polarity and virality.