Utilizing Big Data From Google Trends to Map Population Depression in the United States: Exploratory Infodemiology Study
Bibliographic record
Abstract
BACKGROUND: The epidemiology of mental health disorders has important theoretical and practical implications for health care service and planning. The recent increase in big data storage and subsequent development of analytical tools suggest that mining search databases may yield important trends on mental health, which can be used to support existing population health studies. OBJECTIVE: This study aimed to map depression search intent in the United States based on internet-based mental health queries. METHODS: Weekly data on mental health searches were extracted from Google Trends for an 11-year period (2010-2021) and separated by US state for the following terms: "feeling sad," "depressed," "depression," "empty," "insomnia," "fatigue," "guilty," "feeling guilty," and "suicide." Multivariable regression models were created based on geographic and environmental factors and normalized to the following control terms: "sports," "news," "google," "youtube," "facebook," and "netflix." Heat maps of population depression were generated based on search intent. RESULTS: Depression search intent grew 67% from January 2010 to March 2021. Depression search intent showed significant seasonal patterns with peak intensity during winter (adjusted P<.001) and early spring months (adjusted P<.001), relative to summer months. Geographic location correlated with depression search intent with states in the Northeast (adjusted P=.01) having higher search intent than states in the South. CONCLUSIONS: The trends extrapolated from Google Trends successfully correlate with known risk factors for depression, such as seasonality and increasing latitude. These findings suggest that Google Trends may be a valid novel epidemiological tool to map depression prevalence in the United States.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.007 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.005 | 0.008 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 source (direct Gemma or distilled Codex), 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".