The International Google Trends dataset will provide critical signals that individual users and businesses alike can leverage to make better data-driven decisions. This dataset simplifies the manual interaction with the existing Google Trends UI by automating and exposing anonymized, aggregated, and indexed search data in BigQuery. This dataset includes the Top 25 stories and Top 25 Rising queries from Google Trends. It will be made available as two separate BigQuery tables, with a set of new top terms appended daily. Each set of Top 25 and Top 25 rising expires after 30 days, and will be accompanied by a rolling five-year window of historical data for each country and region across the globe, where data is available. This Google dataset is hosted in Google BigQuery as part of Google Cloud's Datasets solution and is included in BigQuery's 1TB/mo of free tier processing. This means that each user receives 1TB of free BigQuery processing every month, which can be used to run queries on this public dataset. Watch this short video to learn how to get started quickly using BigQuery to access public datasets. What is BigQuery

Background: Alongside the COVID-19 pandemic, government authorities around the world have had to face a growing infodemic capable of causing serious damages to public health and economy. In this context, the use of infoveillance tools has become a primary necessity.Objective: The aim of this study is to test the reliability of a widely used infoveillance tool which is Google Trends. In particular, the paper focuses on the analysis of relative search volumes (RSVs) quantifying their dependence on the day they are collected.Methods: RSVs of the query coronavirus + covid during February 1—December 4, 2020 (period 1), and February 20—May 18, 2020 (period 2), were collected daily by Google Trends from December 8 to 27, 2020. The survey covered Italian regions and cities, and countries and cities worldwide. The search category was set to all categories. Each dataset was analyzed to observe any dependencies of RSVs from the day they were gathered. To do this, by calling i the country, region, or city under investigation and j the day its RSV was collected, a Gaussian distribution Xi=X(σi,x¯i) was used to represent the trend of daily variations of xij=RSVsij. When a missing value was revealed (anomaly), the affected country, region or city was excluded from the analysis. When the anomalies exceeded 20% of the sample size, the whole sample was excluded from the statistical analysis. Pearson and Spearman correlations between RSVs and the number of COVID-19 cases were calculated day by day thus to highlight any variations related to the day RSVs were collected. Welch’s t-test was used to assess the statistical significance of the differences between the average RSVs of the various countries, regions, or cities of a given dataset. Two RSVs were considered statistical confident when t

Afghanistan Google Search Trends: Computer & Electronics: Apple data was reported at 42.000 Score in 14 May 2025. This stayed constant from the previous number of 42.000 Score for 13 May 2025. Afghanistan Google Search Trends: Computer & Electronics: Apple data is updated daily, averaging 36.000 Score from Dec 2021 (Median) to 14 May 2025, with 1261 observations. The data reached an all-time high of 100.000 Score in 25 Aug 2024 and a record low of 0.000 Score in 02 May 2025. Afghanistan Google Search Trends: Computer & Electronics: Apple data remains active status in CEIC and is reported by Google Trends. The data is categorized under Global Database’s Afghanistan – Table AF.Google.GT: Google Search Trends: by Categories.

The dataset contains:

1) The list of tweets corresponding to the keywords "heat wave india" and "heatwave india" between 2010 and 2017.

2) The daily count of the same tweets

3) The monthly Google Trends data corresponding to the keywords "heat wave", "heatwave", "heat wave india", and "heatwave india" limited to the searches from India in the period 2010-2017

The Twitter data has been obtained wth the Python package Get-Old-Tweets (https://github.com/Jefferson-Henrique/GetOldTweets-python); the Google Trends data are obtained from the Google Trends webpage (https://trends.google.com/trends/?geo=US).

As response rates continue to decline, the need to learn more about the survey participation process remains an important task for survey researchers. Search engine data may be one possible source for learning about what information some potential respondents are looking up about a survey when they are making a participation decision. In the present study, we explored the potential of search engine data for learning about survey participation and how it can inform survey design decisions. We drew on freely available Google Trends (GT) data to learn about the use of Google Search with respect to our case study: participation in the Family Research and Demographic Analysis (FReDA) panel survey. Our results showed that some potential respondents were using Google Search to gather information on the FReDA survey. We also showed that the additional data obtained via GT can help survey researchers to discover topics of interest to respondents and geographically stratified search patterns. Moreover, we introduced different approaches for obtaining data via GT, discussed the challenges that come with these data, and closed with practical recommendations on how survey researchers might utilize GT data to learn about survey participation.

Recent research suggests that search volumes of the most popular search engine worldwide, Google, provided via Google Trends, could be associated with national suicide rates in the USA, UK, and some Asian countries. However, search volumes have mostly been studied in an ad hoc fashion, without controls for spurious associations. This study evaluated the validity and utility of Google Trends search volumes for behavioral forecasting of suicide rates in the USA, Germany, Austria, and Switzerland. Suicide-related search terms were systematically collected and respective Google Trends search volumes evaluated for availability. Time spans covered 2004 to 2010 (USA, Switzerland) and 2004 to 2012 (Germany, Austria). Temporal associations of search volumes and suicide rates were investigated with time-series analyses that rigorously controlled for spurious associations. The number and reliability of analyzable search volume data increased with country size. Search volumes showed various temporal associations with suicide rates. However, associations differed both across and within countries and mostly followed no discernable patterns. The total number of significant associations roughly matched the number of expected Type I errors. These results suggest that the validity of Google Trends search volumes for behavioral forecasting of national suicide rates is low. The utility and validity of search volumes for the forecasting of suicide rates depend on two key assumptions (“the population that conducts searches consists mostly of individuals with suicidal ideation”, “suicide-related search behavior is strongly linked with suicidal behavior”). We discuss strands of evidence that these two assumptions are likely not met. Implications for future research with Google Trends in the context of suicide research are also discussed.

Google Search Trends: Online Shopping: Wayfair data was reported at 0.000 Score in 29 Nov 2025. This stayed constant from the previous number of 0.000 Score for 28 Nov 2025. Google Search Trends: Online Shopping: Wayfair data is updated daily, averaging 0.000 Score from Dec 2021 (Median) to 29 Nov 2025, with 1460 observations. The data reached an all-time high of 9.000 Score in 09 Jan 2022 and a record low of 0.000 Score in 29 Nov 2025. Google Search Trends: Online Shopping: Wayfair data remains active status in CEIC and is reported by Google Trends. The data is categorized under Global Database’s Laos – Table LA.Google.GT: Google Search Trends: by Categories.

In the week from October 19 to 25, 2025, global Google searches for the word "ChatGPT" reached a peak of 100 index points, indicating a significant increase in interest and thus the highest interest over the observed period. On October 21, 2025, OpenAI introduced ChatGPT Atlas, a web browser with ChatGPT built in. Interest in the chatbot, developed by U.S.-based OpenAI and launched in November 2022, started rising in the week ending December 3, 2022. ChatGPT, which stands for Chat Generative Pre-trained Transformer, is an AI-powered auto-generative text system able to give human-sounding replies and reproduce human-like interactions when prompted.

Context

Time-based Popularity:

Tracks search interest over time, showing peaks and troughs in popularity for specific keywords.

Regional Insights:

Provides data on search trends by location, allowing for geographic comparisons of interest.

Related Queries:

Lists associated search terms, highlighting related topics that are frequently searched alongside the primary keywords.

Top vs. Rising Trends:

Distinguishes between the most popular queries and those with a sharp increase in search volume.

Category Analysis:

Organizes search data by category, enabling focused insights into specific industries, interests, or demographic groups.

Search Volume Index: Uses an index score (0–100) to represent search volume relative to the highest point on the chart for the selected region and time.

Real-time Data Availability:

Offers access to both historical and real-time data, ideal for identifying ongoing or emerging trends.

Google Search Trends: Travel & Accommodations: Emirates data was reported at 0.000 Score in 29 Nov 2025. This stayed constant from the previous number of 0.000 Score for 28 Nov 2025. Google Search Trends: Travel & Accommodations: Emirates data is updated daily, averaging 0.000 Score from Dec 2021 (Median) to 29 Nov 2025, with 1460 observations. The data reached an all-time high of 99.000 Score in 03 Apr 2025 and a record low of 0.000 Score in 29 Nov 2025. Google Search Trends: Travel & Accommodations: Emirates data remains active status in CEIC and is reported by Google Trends. The data is categorized under Global Database’s Laos – Table LA.Google.GT: Google Search Trends: by Categories.

I scraped data from Google Trends relating to serach queries of the virus 'Coronavirus' and 'COVID-19'. This is based on several research articles showing that google trends has the potential to help with the prediction and detection of disease outbreaks, such as the 2015 Zika outbreak, Influenza and Dengue fever. Other search queries such as the symptoms of the virus can in turn be used to make predictions as they should be correlated with people feeling unwell and presenting with symptoms as well as physician visits. I have not yet scraped the data for search queries for symptoms keywords, but would highly encourage someone else to do it!

Values are calculated on a scale from 0 to 100, where 100 is the location with the most popularity as a fraction of total searches in that location, a value of 50 indicates a location which is half as popular. A value of 0 indicates a location where there was not enough data for this term. Note: A higher value means a higher proportion of all queries, not a higher absolute query count. So a tiny country where 80% of the queries are for "covid19" will get twice the score of a giant country where only 40% of the queries are for "covid19".

UPDATED: Keywords 'lockdown', 'symptoms of coronavirus', 'social distancing'

From September 2024 to September 2025, global interest in the search term “***********” on Google increased overall. Over the period considered, the keyword reached its highest level of popularity in the week ending **************. Meanwhile, Google searches for the term “**************” peaked in the week ending ***************.

Oman Google Search Trends: Computer & Electronics: Apple data was reported at 38.000 Score in 28 Nov 2025. This records an increase from the previous number of 35.000 Score for 27 Nov 2025. Oman Google Search Trends: Computer & Electronics: Apple data is updated daily, averaging 50.000 Score from Dec 2021 (Median) to 28 Nov 2025, with 1459 observations. The data reached an all-time high of 100.000 Score in 09 Sep 2025 and a record low of 0.000 Score in 30 Jul 2023. Oman Google Search Trends: Computer & Electronics: Apple data remains active status in CEIC and is reported by Google Trends. The data is categorized under Global Database’s Oman – Table OM.Google.GT: Google Search Trends: by Categories.

Morocco Google Search Trends: Government Measures: Government Subsidy data was reported at 0.000 Score in 29 Nov 2025. This stayed constant from the previous number of 0.000 Score for 28 Nov 2025. Morocco Google Search Trends: Government Measures: Government Subsidy data is updated daily, averaging 0.000 Score from Dec 2021 (Median) to 29 Nov 2025, with 1460 observations. The data reached an all-time high of 9.000 Score in 24 Aug 2023 and a record low of 0.000 Score in 29 Nov 2025. Morocco Google Search Trends: Government Measures: Government Subsidy data remains active status in CEIC and is reported by Google Trends. The data is categorized under Global Database’s Morocco – Table MA.Google.GT: Google Search Trends: by Categories.

With the continuous growth of internet usage, Google Trends has emerged as a source of information to investigate how social trends evolve over time. Knowing how the level of interest in conservation topics—approximated using Google search volume—varies over time can help support targeted conservation science communication. However, the evolution of search volume over time and the mechanisms that drive peaks in searches are poorly understood. We conducted time series analyses on Google search data from 2004 to 2013 to investigate: (i) whether interests in selected conservation topics have declined and (ii) the effect of news reporting and academic publishing on search volume. Although trends were sensitive to the term used as benchmark, we did not find that public interest towards conservation topics such as climate change, ecosystem services, deforestation, orangutan, invasive species and habitat loss was declining. We found, however, a robust downward trend for endangered species and an upward trend for ecosystem services. The quantity of news articles was related to patterns in Google search volume, whereas the number of research articles was not a good predictor but lagged behind Google search volume, indicating the role of news in the transfer of conservation science to the public.

Uzbekistan Google Search Trends: Travel & Accommodations: Airbnb data was reported at 2.000 Score in 30 Nov 2025. This stayed constant from the previous number of 2.000 Score for 29 Nov 2025. Uzbekistan Google Search Trends: Travel & Accommodations: Airbnb data is updated daily, averaging 0.000 Score from Dec 2021 (Median) to 30 Nov 2025, with 1461 observations. The data reached an all-time high of 24.000 Score in 29 Aug 2024 and a record low of 0.000 Score in 18 Nov 2025. Uzbekistan Google Search Trends: Travel & Accommodations: Airbnb data remains active status in CEIC and is reported by Google Trends. The data is categorized under Global Database’s Uzbekistan – Table UZ.Google.GT: Google Search Trends: by Categories.

Context

For a project of mine, I wanted to use Google Trends data to predict the stock market. However, over large timespans, only monthly data is provided, so I had to use this data—together with the daily and weekly data from smaller timespans—to create daily and weekly data over the large timespan. I have created a script for this purpose, and thought I would share the data from 98 financial keywords.

Content

In each file there are only two columns; "date" and "adjusted". "date" is obviously the date. "adjusted" is the adjusted data, derived from the monthly and weekly data — in the case of the daily data.

Libya Google Search Trends: Economic Measures: Short-Time Working data was reported at 0.000 Score in 29 Nov 2025. This stayed constant from the previous number of 0.000 Score for 28 Nov 2025. Libya Google Search Trends: Economic Measures: Short-Time Working data is updated daily, averaging 0.000 Score from Dec 2021 (Median) to 29 Nov 2025, with 1460 observations. The data reached an all-time high of 84.000 Score in 08 May 2025 and a record low of 0.000 Score in 29 Nov 2025. Libya Google Search Trends: Economic Measures: Short-Time Working data remains active status in CEIC and is reported by Google Trends. The data is categorized under Global Database’s Libya – Table LY.Google.GT: Google Search Trends: by Categories.

explain the relationship between DMA, FIPS and county

ChatGPT said: Here's a breakdown of the relationship between DMA, FIPS, and county:

🗺️ 1. County A county is a geographic and administrative subdivision of a U.S. state.

For example: Cook County in Illinois or Los Angeles County in California.

The U.S. has over 3,000 counties or county-equivalents.

🔢 2. FIPS Code FIPS = Federal Information Processing Standards code.

Used to uniquely identify geographic areas like states and counties.

It consists of:

State FIPS (2 digits) — e.g., California = 06

County FIPS (3 digits) — e.g., Los Angeles County = 037

Together: 06037 (California + Los Angeles County)

FIPS codes are used in datasets, GIS, and federal data standards to track data consistently across agencies.

📺 3. DMA (Designated Market Area) DMA is a geographic region defined by Nielsen where the population receives the same (or similar) TV and radio content.

Used in advertising, media, and Google Trends to segment the market by media consumption patterns.

There are 210 DMAs in the U.S., each labeled by Nielsen with a DMA code or name (e.g., "New York", "Chicago", "Palm Springs").

📌 How They Relate Concept Level Code Type Example County Local FIPS Los Angeles County (06037) FIPS Code System Numeric Encodes state + county DMA Media Region Name/Index Los Angeles DMA

One DMA contains multiple counties.

Example: The Los Angeles DMA includes Los Angeles County, Orange County, Ventura County, etc.

Each county has a unique FIPS code, but a DMA might span counties in multiple states.

When mapping or analyzing data (e.g., in GIS or Google Trends), you often merge county-level data (FIPS) into DMAs for media or market analysis.

🧭 Example State County FIPS DMA Name DMA Code California Los Angeles 06037 Los Angeles 803 California Orange 06059 Los Angeles 803 California Riverside 06065 Palm Springs 804

👉 DMA for FIPS 02013?

Alaska is unique: it’s sparsely populated and has limited Nielsen DMA coverage.

Most of rural Alaska does not belong to a defined DMA. Instead, large parts of Alaska are treated as “non-DMA” or are grouped into a single large DMA (often labeled Anchorage DMA if included).

Context

The data was extracted to be used for my submission to the 2020 kaggle online survey. You can find the related submission here. I used it to analyze the searches related to Automated Machine learning.

Content

The data consists of google trends for AutoML /Automated machine learning. This data is Aggregated, **Anonymised **, Indexed and Normalized. The dataset consists of four files:

• Timeline Data(2015-2020) Timeline data shows interest over time. The Numbers represent search interest relative to the highest point on the chart for the given region and time. A value of 100 is the peak popularity for the term. A value of 50 means that the term is half as popular. A score of 0 means that there was not enough data for this term. I have used the search data from the year 2015 to 2020.

• GeoMap data for the year 2020 GeoMap data shows Interest by sub-region. It essentially highlights locations where the search term was most popular during the specified time frame. Values are calculated on a scale from 0 to 100, where 100 is the location with the most popularity as a fraction of total searches in that location, a value of 50 indicates a location that is half as popular. A value of 0 indicates a location where there was not enough data for this term.

• Related Entities data for the year 2020 Related entities mean users searching for your term also searched for these topics. Scoring is on a relative scale where a value of 100 is the most commonly searched topic and a value of 50 is a topic searched half as often as the most popular term, and so on

• Related Queries data Related Queries mean users searching for your term also searched for these queries. Scoring is on a relative scale where a value of 100 is the most commonly searched query, 50 is a query searched half as often as the most popular query, and so on.

The explanations have been taken from the Google trend official site.

Acknowledgements

• Banner Image: People vector created by pch.vector - www.freepik.com
• Google Trends

Useful links: - Google Trends - Google News Lab - @GoogleTrends