Main Article Content
Unfortunately, oficial reports on the development of dengue in Brazil take a long time to be released. This creates an environment where policy makers do not have enough accurate information they can use to improve how they act in order to prevent dengue to spread. In this paper we show how data collected in real time from Google Trends can be used to predict the current number of dengue cases in the state of
Sao Paulo. In order to estimate the number of new cases as a function of time, we use the least square method, lasso and random forests, having the search volume of several keywords as covariates such as "tratamento dengue", "sintomas dengue", and "febre dengue" in the models. The least square method presented better predictions and gave reasonable estimates for up to eight months after the last release of an ocial report. This allows authorities to take necessary actions to prevent dengue from spreading in a much cheaper and efective way.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).