Dataset Information

Need of care in interpreting Google Trends-based COVID-19 infodemiological study results: potential risk of false-positivity.

ABSTRACT:

Background

Google Trends (GT) is being used as an epidemiological tool to study coronavirus disease (COVID-19) by identifying keywords in search trends that are predictive for the COVID-19 epidemiological burden. However, many of the earlier GT-based studies include potential statistical fallacies by measuring the correlation between non-stationary time sequences without adjusting for multiple comparisons or the confounding of media coverage, leading to concerns about the increased risk of obtaining false-positive results. In this study, we aimed to apply statistically more favorable methods to validate the earlier GT-based COVID-19 study results.

Methods

We extracted the relative GT search volume for keywords associated with COVID-19 symptoms, and evaluated their Granger-causality to weekly COVID-19 positivity in eight English-speaking countries and Japan. In addition, the impact of media coverage on keywords with significant Granger-causality was further evaluated using Japanese regional data.

Results

Our Granger causality-based approach largely decreased (by up to approximately one-third) the number of keywords identified as having a significant temporal relationship with the COVID-19 trend when compared to those identified by Pearson or Spearman's rank correlation-based approach. "Sense of smell" and "loss of smell" were the most reliable GT keywords across all the evaluated countries; however, when adjusted with their media coverage, these keyword trends did not Granger-cause the COVID-19 positivity trends (in Japan).

Conclusions

Our results suggest that some of the search keywords reported as candidate predictive measures in earlier GT-based COVID-19 studies may potentially be unreliable; therefore, caution is necessary when interpreting published GT-based study results.

SUBMITTER: Sato K

PROVIDER: S-EPMC8286439 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundCOVID-19 has caused the worst international crisis since World War II. Italy was one of the countries most affected by both the pandemic and the related infodemic. The success of anti-COVID-19 strategies and future public health policies in Italy cannot separate itself from the containment of fake news and the divulgation of correct information.ObjectiveThe aim of this paper was to analyze the impact of COVID-19 on web interest in conspiracy hypotheses and risk perception of Italian web users.MethodsGoogle Trends was used to monitor users' web interest in specific topics, such as conspiracy hypotheses, vaccine side effects, and pollution and climate change. The keywords adopted to represent these topics were mined from Bufale.net-an Italian website specializing in detecting online hoaxes-and Google Trends suggestions (ie, related topics and related queries). Relative search volumes (RSVs) of the time-lapse periods of 2016-2020 (pre-COVID-19) and 2020-2021 (post-COVID-19) were compared through percentage difference (∆%) and the Welch t test (t). When data series were not stationary, other ad hoc criteria were used. The trend slopes were assessed through Sen slope (SS). The significance thresholds have been indicatively set at P=.05 and t=1.9.ResultsThe COVID-19 pandemic drastically increased Italian netizens' interest in conspiracies (∆% ∈ [60, 288], t ∈ [6, 12]). Web interest in conspiracy-related queries across Italian regions increased and became more homogeneous compared to the pre-COVID-19 period (average RSV=80±2.8, t min=1.8, ∆min%=+12.4, min∆SD%=-25.8). In addition, a growing trend in web interest in the infodemic YouTube channel ByoBlu has been highlighted. Web interest in hoaxes has increased more than interest in antihoax services (t 1=11.3 vs t 2=4.5; Δ1%=+157.6 vs Δ2%=+84.7). Equivalently, web interest in vaccine side effects exceeded interest in pollution and climate change (SSvaccines=0.22, P<.001 vs SSpollution=0.05, P<.001; ∆%=+296.4). To date, a significant amount of fake news related to COVID-19 vaccines, unproven remedies, and origin has continued to circulate. In particular, the creation of SARS-CoV-2 in a Chinese laboratory constituted about 0.04% of the entire web interest in the pandemic.ConclusionsCOVID-19 has given a significant boost to web interest in conspiracy hypotheses and has made it more uniform across regions in Italy. The pandemic accelerated an already-growing trend in users' interest toward some fake news sources, including the 500,000-subscriber YouTube channel ByoBlu, which was removed from the platform by YouTube for disinformation in March 2021. The risk perception related to COVID-19 vaccines has been so distorted that vaccine side effect-related queries outweighed those relating to pollution and climate change, which are much more urgent issues. Moreover, a large amount of fake news has circulated about COVID-19 vaccines, remedies, and origin. Based on these findings, it is recommended that the Italian authorities implement more effective infoveillance systems, and that communication by the mass media be less sensationalistic and more consistent with the available scientific evidence. In this context, Google Trends can be used to monitor users' response to specific infodemiological countermeasures. Further research is needed to understand the psychological mechanisms that regulate risk perception.

Project description:BackgroundWeb-based analysis of search queries has become a very useful method in various academic fields for understanding timely and regional differences in the public interest in certain terms and concepts. Particularly in health and medical research, Google Trends has been increasingly used over the last decade.ObjectiveThis study aimed to assess the search activity of pain-related parameters on Google Trends from among the most populated regions worldwide over a 3-year period from before the report of the first confirmed COVID-19 cases in these regions (January 2018) until December 2020.MethodsSearch terms from the following regions were used for the analysis: India, China, Europe, the United States, Brazil, Pakistan, and Indonesia. In total, 24 expressions of pain location were assessed. Search terms were extracted using the local language of the respective country. Python scripts were used for data mining. All statistical calculations were performed through exploratory data analysis and nonparametric Mann-Whitney U tests.ResultsAlthough the overall search activity for pain-related terms increased, apart from pain entities such as headache, chest pain, and sore throat, we observed discordant search activity. Among the most populous regions, pain-related search parameters for shoulder, abdominal, and chest pain, headache, and toothache differed significantly before and after the first officially confirmed COVID-19 cases (for all, P<.001). In addition, we observed a heterogenous, marked increase or reduction in pain-related search parameters among the most populated regions.ConclusionsAs internet searches are a surrogate for public interest, we assume that our data are indicative of an increased incidence of pain after the onset of the COVID-19 pandemic. However, as these increased incidences vary across geographical and anatomical locations, our findings could potentially facilitate the development of specific strategies to support the most affected groups.

Project description:BackgroundGoogle Trends is a novel, freely accessible tool that allows users to interact with Internet search data, which may provide deep insights into population behavior and health-related phenomena. However, there is limited knowledge about its potential uses and limitations. We therefore systematically reviewed health care literature using Google Trends to classify articles by topic and study aim; evaluate the methodology and validation of the tool; and address limitations for its use in research.Methods and findingsPRISMA guidelines were followed. Two independent reviewers systematically identified studies utilizing Google Trends for health care research from MEDLINE and PubMed. Seventy studies met our inclusion criteria. Google Trends publications increased seven-fold from 2009 to 2013. Studies were classified into four topic domains: infectious disease (27% of articles), mental health and substance use (24%), other non-communicable diseases (16%), and general population behavior (33%). By use, 27% of articles utilized Google Trends for casual inference, 39% for description, and 34% for surveillance. Among surveillance studies, 92% were validated against a reference standard data source, and 80% of studies using correlation had a correlation statistic ≥0.70. Overall, 67% of articles provided a rationale for their search input. However, only 7% of articles were reproducible based on complete documentation of search strategy. We present a checklist to facilitate appropriate methodological documentation for future studies. A limitation of the study is the challenge of classifying heterogeneous studies utilizing a novel data source.ConclusionGoogle Trends is being used to study health phenomena in a variety of topic domains in myriad ways. However, poor documentation of methods precludes the reproducibility of the findings. Such documentation would enable other researchers to determine the consistency of results provided by Google Trends for a well-specified query over time. Furthermore, greater transparency can improve its reliability as a research tool.