Enhancing the Predictive Power of Google Trends Data Through Network Analysis: Infodemiology Study of COVID-19
Bibliographic record
Abstract
BACKGROUND: The COVID-19 outbreak has revealed a high demand for timely surveillance of pandemic developments. Google Trends (GT), which provides freely available search volume data, has been proven to be a reliable forecast and nowcast measure for public health issues. Previous studies have tended to use relative search volumes from GT directly to analyze associations and predict the progression of pandemic. However, GT's normalization of the search volumes data and data retrieval restrictions affect the data resolution in reflecting the actual search behaviors, thus limiting the potential for using GT data to predict disease outbreaks. OBJECTIVE: This study aimed to introduce a merged algorithm that helps recover the resolution and accuracy of the search volume data extracted from GT over long observation periods. In addition, this study also aimed to demonstrate the extended application of merged search volumes (MSVs) in combination of network analysis, via tracking the COVID-19 pandemic risk. METHODS: We collected relative search volumes from GT and transformed them into MSVs using our proposed merged algorithm. The MSVs of the selected coronavirus-related keywords were compiled using the rolling window method. The correlations between the MSVs were calculated to form a dynamic network. The network statistics, including network density and the global clustering coefficients between the MSVs, were also calculated. RESULTS: Our research findings suggested that although GT restricts the search data retrieval into weekly data points over a long period, our proposed approach could recover the daily search volume over the same investigation period to facilitate subsequent research analyses. In addition, the dynamic time warping diagrams show that the dynamic networks were capable of predicting the COVID-19 pandemic trends, in terms of the number of COVID-19 confirmed cases and severity risk scores. CONCLUSIONS: The innovative method for handling GT search data and the application of MSVs and network analysis to broaden the potential for GT data are useful for predicting the pandemic risk. Further investigation of the GT dynamic network can focus on noncommunicable diseases, health-related behaviors, and misinformation on the internet.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.006 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.004 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".