![]() ![]() Nevertheless, that work does not answer the question about which one is best as a data source: Google or Twitter.Ĭomputer technology offers nowadays many useful tools for mining the Web. Some previous research use both data sources for health purposes, such as the recent work of Jung et al. It has been found that nearly two thirds (65.70%) of Internet data fulfill the previous goal originating from the Google Search engine and Twitter 8. Previous works used the Google search engine or social media to track or discuss epidemics, and these two are the main sources for detecting and predicting the spread, the size and the peak of serious diseases. ![]() The latter approach considers social media data as a word cloud, from which useful metrics and results can be measured and studied. In addition, recent advances cover the analysis of real-time data or even the sentiment of the data found inside social media 7, such as Twitter. Some researchers further extend this approach to benefit from Internet of Things (IoT) technologies 6. Also, in some cases, infection dynamics are discussed 3– 5 based on complex networks of exogenous transmitting or environmental factors. Some of these tools 2 combine risk management, signal processing and econometrics to construct a novel method towards a forecast of disease outbreaks in Europe. These models also include event-based surveillance (EBS) systems and risk modelling 1 and use available Internet data to detect the evidence of an emerging threat, such as the onset of an epidemic. Results show that this approach may provide a complementary source to detect and predict the volume and spread of unfolding for severe epidemics. However, several studies have recently included non-epidemiological data obtained through the Internet as an alternative, concretely data extracted from search engines or messages interchanged in social media. Traditional systems and techniques mainly use epidemiological data, such as medical data or health log files obtained from doctors and hospitals. The early detection and prediction of the spread of epidemics is an important concern in public health. The alternative model is slightly worse than the ARIMA(X) ( R = 0.863, MAPE = 22.614), but with a higher mean deviation (abs. Google data show a high Pearson correlation and a relatively low Mean Absolute Percentage Error ( R = 0.933, MAPE = 21.358). ![]() Results indicate that influenza was successfully monitored during the test period. The data were analyzed by using two models: the ARIMA model computed estimations based on weekly sums and a customized approximate model which uses daily sums. Data on influenza in Greece have been collected from Google and Twitter and they have been compared to influenza data from the official authority of Europe. Data have been acquired from the Internet by means of a system which gathered real-time data for 23 weeks. Concretely, this study aims at gathering evidence on which kind of data source leads to better results. This paper reports the feasibility of building such a system with search engine and social network data. In diverse cases, electronic surveillance systems can be created by obtaining and analyzing on-line data, complementing other existing monitoring resources. Internet technologies have demonstrated their value for the early detection and prediction of epidemics.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |