VazaDengue: An information system for preventing and combating mosquito-borne diseases with social networks

Abstract

Dengue is a disease transmitted by the Aedes Aegypti mosquito, which also transmits the Zika virus and Chikungunya. Unfortunately, the population of different countries has been suffering from the diseases transmitted by the mosquito. The communities can play an important role in combatting and preventing the mosquito-borne diseases. However, due to the limited engagement of the population, new methods need to be used to strengthen the mosquito surveillance. VazaDengue is one of these solutions that provides services that stand out from the others solutions. Generally speaking VazaDengue is a system that offers the users a platform for preventing and combating mosquito-borne diseases. The system relies on social actions of reporting mosquito breeding sites and dengue cases, in which the reports are made available to the citizens and health agencies. In addition, the system monitors social media network Twitter to enrich the information provided. It processes the natural language text from the network to classify the tweets according to a set of the predefined categories. After the classification, the relevant tweets are provided to the users as reports. In this paper, we describe the VazaDengue features including its ability to harvest and classify tweets. Since the VazaDengue system aims at providing a dynamic and efficient environment to support rapid interventions of health agents, we present here two studies evaluating the potential contributions of the classified tweets in preventing and combating mosquito-borne diseases. The first evaluation uses a survey conducted by the Brazilian community of health agents. The goal is to evaluate the relevance of the classified tweets. The second study compares the official reports of the 2015-2016 epidemic waves in Brazil with the concentration of mosquito-related tweets found by VazaDengue. The goal is to verify if the concentration of tweets can be used for monitoring big cities. The results of these two evaluations are encouraging. We have found that the health agents tend to agree with the relevance of the classified tweets. Moreover, the concentration of tweets is likely to be effective for monitoring big cities. The results of these evaluations are helping us to further improve the VazaDengue system to make it more useful for combating and preventing the mosquito-borne diseases. VazaDengue: An Information System for Preventing and Combating Mosquito-Borne Diseases with Social Networks:

An intelligent healthcare system for predicting and preventing dengue virus infection

“…In this regard, another work by Missier et al [26] had depicted the extraction of dengue-related information from the social networking platform Twitter, where people use to discuss information online with others, for analyzing the outbreak of dengue infection in particular areas. Sousa et al [43] had designed a user-oriented platform for reporting mosquito-borne diseases and breeding sites, which helps in supporting the authorities for preventing and controlling mosquitoborne diseases. However, for reducing the dependence on information from the users, which is based on the willingness of the users, the platform has also explored alternate source of information through the mining of geolocated content from social networks.…”

Citizen Science: An Information Quality Research Frontier

“…Recent experiments demonstrate the advantages of this approach over traditional methods of data collection and storage in increasing simultaneously accuracy, completeness and discovery (Lukyanenko et al 2014b, a), however the ability of this approach to promote consistency is unknown, suggesting a need for additional research in this direction (Lukyanenko, Parsons, Wiersma, et al 2016). Other analytical techniques have also been applied, such as using effort information to standardize data (Bird et al 2014), or using modeling (Sousa et al 2018;Strien et al 2013), applying different analytic approaches to solving some of the problems in participant variability, which also may have utility for IS research. Considering this work, there is a clear need for further research on dimensions and the nature of IQ tradeoffs in citizen science.…”

Early Detection of Seasonal Outbreaks from Twitter Data Using Machine Learning Approaches

“…One of the easiest and latest classification techniques is the K-Nearest Neighbor (KNN) method [29]. It can be considered as a simplified version of the Naïve Bayes classifier.…”