Causality Analysis of Google Trends and Dengue Incidence in Bandung, Indonesia With Linkage of Digital Data Modeling: Longitudinal Observational Study

BackgroundThe popularity of dengue can be inferred from Google Trends that summarizes Google searches of related topics. Both the disease and its Google Trends have a similar source of causation in the dengue virus, leading us to hypothesize that dengue incidence and Google T...

Full description

Bibliographic Details
Main Authors: Syamsuddin, Muhammad, Fakhruddin, Muhammad, Sahetapy-Engel, Jane Theresa Marlen, Soewono, Edy
Format: Article
Language:English
Published: JMIR Publications 2020-07-01
Series:Journal of Medical Internet Research
Online Access:http://www.jmir.org/2020/7/e17633/
id doaj-2ec3a43c6171413680cbb3cb17f018f6
record_format Article
spelling doaj-2ec3a43c6171413680cbb3cb17f018f62021-04-02T21:36:35ZengJMIR PublicationsJournal of Medical Internet Research1438-88712020-07-01227e1763310.2196/17633Causality Analysis of Google Trends and Dengue Incidence in Bandung, Indonesia With Linkage of Digital Data Modeling: Longitudinal Observational StudySyamsuddin, MuhammadFakhruddin, MuhammadSahetapy-Engel, Jane Theresa MarlenSoewono, Edy BackgroundThe popularity of dengue can be inferred from Google Trends that summarizes Google searches of related topics. Both the disease and its Google Trends have a similar source of causation in the dengue virus, leading us to hypothesize that dengue incidence and Google Trends results have a long-run equilibrium. ObjectiveThis research aimed to investigate the properties of this long-run equilibrium in the hope of using the information derived from Google Trends for the early detection of upcoming dengue outbreaks. MethodsThis research used the cointegration method to assess a long-run equilibrium between dengue incidence and Google Trends results. The long-run equilibrium was characterized by their linear combination that generated a stationary process. The Dickey-Fuller test was adopted to check the stationarity of the processes. An error correction model (ECM) was then adopted to measure deviations from the long-run equilibrium to examine the short-term and long-term effects. The resulting models were used to determine the Granger causality between the two processes. Additional information about the two processes was obtained by examining the impulse response function and variance decomposition. ResultsThe Dickey-Fuller test supported an implicit null hypothesis that the dengue incidence and Google Trends results are nonstationary processes (P=.01). A further test showed that the processes were cointegrated (P=.01), indicating that their particular linear combination is a stationary process. These results permitted us to construct ECMs. The model showed the direction of causality of the two processes, indicating that Google Trends results will Granger-cause dengue incidence (not in the reverse order). ConclusionsVarious hypothesis testing results in this research concluded that Google Trends results can be used as an initial indicator of upcoming dengue outbreaks.http://www.jmir.org/2020/7/e17633/
collection DOAJ
language English
format Article
sources DOAJ
author Syamsuddin, Muhammad
Fakhruddin, Muhammad
Sahetapy-Engel, Jane Theresa Marlen
Soewono, Edy
spellingShingle Syamsuddin, Muhammad
Fakhruddin, Muhammad
Sahetapy-Engel, Jane Theresa Marlen
Soewono, Edy
Causality Analysis of Google Trends and Dengue Incidence in Bandung, Indonesia With Linkage of Digital Data Modeling: Longitudinal Observational Study
Journal of Medical Internet Research
author_facet Syamsuddin, Muhammad
Fakhruddin, Muhammad
Sahetapy-Engel, Jane Theresa Marlen
Soewono, Edy
author_sort Syamsuddin, Muhammad
title Causality Analysis of Google Trends and Dengue Incidence in Bandung, Indonesia With Linkage of Digital Data Modeling: Longitudinal Observational Study
title_short Causality Analysis of Google Trends and Dengue Incidence in Bandung, Indonesia With Linkage of Digital Data Modeling: Longitudinal Observational Study
title_full Causality Analysis of Google Trends and Dengue Incidence in Bandung, Indonesia With Linkage of Digital Data Modeling: Longitudinal Observational Study
title_fullStr Causality Analysis of Google Trends and Dengue Incidence in Bandung, Indonesia With Linkage of Digital Data Modeling: Longitudinal Observational Study
title_full_unstemmed Causality Analysis of Google Trends and Dengue Incidence in Bandung, Indonesia With Linkage of Digital Data Modeling: Longitudinal Observational Study
title_sort causality analysis of google trends and dengue incidence in bandung, indonesia with linkage of digital data modeling: longitudinal observational study
publisher JMIR Publications
series Journal of Medical Internet Research
issn 1438-8871
publishDate 2020-07-01
description BackgroundThe popularity of dengue can be inferred from Google Trends that summarizes Google searches of related topics. Both the disease and its Google Trends have a similar source of causation in the dengue virus, leading us to hypothesize that dengue incidence and Google Trends results have a long-run equilibrium. ObjectiveThis research aimed to investigate the properties of this long-run equilibrium in the hope of using the information derived from Google Trends for the early detection of upcoming dengue outbreaks. MethodsThis research used the cointegration method to assess a long-run equilibrium between dengue incidence and Google Trends results. The long-run equilibrium was characterized by their linear combination that generated a stationary process. The Dickey-Fuller test was adopted to check the stationarity of the processes. An error correction model (ECM) was then adopted to measure deviations from the long-run equilibrium to examine the short-term and long-term effects. The resulting models were used to determine the Granger causality between the two processes. Additional information about the two processes was obtained by examining the impulse response function and variance decomposition. ResultsThe Dickey-Fuller test supported an implicit null hypothesis that the dengue incidence and Google Trends results are nonstationary processes (P=.01). A further test showed that the processes were cointegrated (P=.01), indicating that their particular linear combination is a stationary process. These results permitted us to construct ECMs. The model showed the direction of causality of the two processes, indicating that Google Trends results will Granger-cause dengue incidence (not in the reverse order). ConclusionsVarious hypothesis testing results in this research concluded that Google Trends results can be used as an initial indicator of upcoming dengue outbreaks.
url http://www.jmir.org/2020/7/e17633/
work_keys_str_mv AT syamsuddinmuhammad causalityanalysisofgoogletrendsanddengueincidenceinbandungindonesiawithlinkageofdigitaldatamodelinglongitudinalobservationalstudy
AT fakhruddinmuhammad causalityanalysisofgoogletrendsanddengueincidenceinbandungindonesiawithlinkageofdigitaldatamodelinglongitudinalobservationalstudy
AT sahetapyengeljanetheresamarlen causalityanalysisofgoogletrendsanddengueincidenceinbandungindonesiawithlinkageofdigitaldatamodelinglongitudinalobservationalstudy
AT soewonoedy causalityanalysisofgoogletrendsanddengueincidenceinbandungindonesiawithlinkageofdigitaldatamodelinglongitudinalobservationalstudy
_version_ 1721544822440853504