Search Query Volume Research Articles

Ethical research standards in a world of big data

In 2009 Ginsberg et al. reported using Google search query volume to estimate influenza activity in advance of traditional methodologies. It was a groundbreaking example of digital disease detection, and it still remains illustrative of the power of gathering data from the internet for important research. In recent years, the methodologies have been extended to include new topics and data sources; Twitter in particular has been used for surveillance of influenza-like-illnesses, political sentiments, and even behavioral risk factors like sentiments about childhood vaccination programs. As the research landscape continuously changes, the protection of human subjects in online research needs to keep pace. Here we propose a number of guidelines for ensuring that the work done by digital researchers is supported by ethical-use principles. Our proposed guidelines include: 1) Study designs using Twitter-derived data should be transparent and readily available to the public. 2) The context in which a tweet is sent should be respected by researchers. 3) All data that could be used to identify tweet authors, including geolocations, should be secured. 4) No information collected from Twitter should be used to procure more data about tweet authors from other sources. 5) Study designs that require data collection from a few individuals rather than aggregate analysis require Institutional Review Board (IRB) approval. 6) Researchers should adhere to a user’s attempt to control his or her data by respecting privacy settings. As researchers, we believe that a discourse within the research community is needed to ensure protection of research subjects. These guidelines are offered to help start this discourse and to lay the foundations for the ethical use of Twitter data.

Forecasting Chinese tourist volume with search engine data

The queries entered into search engines register hundreds of millions of different searches by tourists, not only reflecting the trends of the searchers' preferences for travel products, but also offering a prediction of their future travel behavior. This study used web search query volume to predict visitor numbers for a popular tourist destination in China, and compared the predictive power of the search data of two different search engines, Google and Baidu. The study verified the co-integration relationship between search engine query data and visitor volumes to Hainan Province. Compared to the corresponding auto-regression moving average (ARMA) models, both types of search engine data helped to significantly decrease forecasting errors. However, Baidu data performed better due to its larger market share in China. The study demonstrated the value of search engine data, proposed a method for selecting predictive queries, and showed the locality of the data for forecasting tourism demand.

Correlation between reported human infection with avian influenza A H7N9 virus and cyber user awareness: what can we learn from digital epidemiology?

Data on the topic of novel avian influenza A (H7N9) were collected based on the web analysis tool 'Baidu Index', a major Chinese search engine. We found a positive correlation between the volume of H7N9-related 'cyber user awareness' and the epidemic situation during the H7N9 outbreak in China (r=0.98, p<0.01, cumulative; r=0.43, p=0.018, daily) except in the early stage; the ranks of H7N9-related topics changed at different epidemic stages. This study may improve our understanding of the role of web-based media in infectious disease surveillance in China.

Web search query volume as a measure of pharmaceutical utilization and changes in prescribing patterns

Monitoring prescription drug utilization is important for both drug safety and drug marketing purposes. However, access to utilization data is often expensive, limited and not timely. To demonstrate and validate the use of web search engine queries as a method for timely monitoring of drug utilization and changes in prescribing behaviors. Drug utilization time series were obtained from the Medical Expenditure Panel Survey and normalized search volume was obtained from Google Trends. Correlation between the series was estimated using a cross-correlation function. Changes in the search volume following knowledge events were detected using a cumulative sums changepoint method. Search volume tracks closely with the utilization rates of several seasonal prescription drugs. Additionally, search volume exhibits changes following known major knowledge events, such as the publication of new information. Search volume provides a first order approximation to pharmaceutical utilization in the community and can be used to detect changes in prescribing behavior.

Nowcasting unemployment rate and new car sales in south-western Europe with Google Trends

This work presents a study describing the use of Internet search information to achieve an improved nowcasting ability with simple autoregressive models, using data from four countries and two different application domains with social and economic significance: unemployment rate and car sales. The results we obtained differ by country/language and application area. In the case of unemployment, we find that Google Trends data lead to the improvement of nowcasts in three out of the four considered countries: Portugal, France and Italy. However, there are sometimes important differences in the predictive ability of these data when we consider different out-of-sample periods. For car sales, we find that, in some cases, the volume of search queries helps explaining the variance of the car sales data. However, we find little support for the hypothesis that search query data may improve predictions, and we present several possible reasons for these results. Taking all results into account, we conclude that, when Google Trends variables are significantly different from zero in-sample, they tend to lead to improvements in out-of-sample predictive ability. The results can have implications for nowcasting, by providing some indications regarding the advantage or not of the use of search data to improve simple models and indirectly by highlighting the sensitivity of the approach to the actual country-specific base, nowcasting period and search data.

Seasonal trends in restless legs symptomatology: evidence from Internet search query data

ObjectivePatients with Willis-Ekbom disease (restless legs syndrome [RLS]) frequently report seasonal worsening of their symptoms; however, seasonal patterns in this disorder have not been systematically evaluated. The purpose of our investigation was to utilize Internet search query data to test the hypothesis that restless legs symptoms vary by season, with worsening in the summer months. MethodsInternet search query data were obtained from Google Trends. Monthly normalized search volume was determined for the term restless legs between January 2004 and December 2012. Using cosinor analysis, seasonal effects were tested for data from the United States, Australia, Germany, the United Kingdom, and Canada. ResultsCosinor analysis revealed statistically significant seasonal effects on search queries in the United States (P=.005), Australia (P=.00007), Germany (P=.00009), and the United Kingdom (P=.003), though a trend was present in the search data from Canada (P=.098). Search queries peaked in summer months in both northern (June and July) and southern (January) hemispheres. Search query volume increased by 24–40% during summer relative to winter months across all evaluated countries. ConclusionsEvidence from Internet search queries across a wide range of dates and geographic areas suggested a seasonality of restless legs symptomatology with a peak in summer months. Our novel finding in RLS epidemiology needs to be confirmed in additional samples, and underlying mechanisms must be elucidated.

Assessing the Impact of the National Smoking Ban in Indoor Public Places in China: Evidence from Quit Smoking Related Online Searches

BackgroundDespite the tremendous economic and health costs imposed on China by tobacco use, China lacks a proactive and systematic tobacco control surveillance and evaluation system, hampering research progress on tobacco-focused surveillance and evaluation studies.MethodsThis paper uses online search query analyses to investigate changes in online search behavior among Chinese Internet users in response to the adoption of the national indoor public place smoking ban. Baidu Index and Google Trends were used to examine the volume of search queries containing three key search terms “Smoking Ban(s),” “Quit Smoking,” and “Electronic Cigarette(s),” along with the news coverage on the smoking ban, for the period 2009–2011.FindingsOur results show that the announcement and adoption of the indoor public place smoking ban in China generated significant increases in news coverage on smoking bans. There was a strong positive correlation between the media coverage of smoking bans and the volume of “Smoking Ban(s)” and “Quit Smoking” related search queries. The volume of search queries related to “Electronic Cigarette(s)” was also correlated with the smoking ban news coverage.InterpretationTo the extent it altered smoking-related online searches, our analyses suggest that the smoking ban had a significant effect, at least in the short run, on Chinese Internet users’ smoking-related behaviors. This research introduces a novel analytic tool, which could serve as an alternative tobacco control evaluation and behavior surveillance tool in the absence of timely or comprehensive population surveillance system. This research also highlights the importance of a comprehensive approach to tobacco control in China.

Media-Induced Or Search-Driven?

In an effort to advance knowledge of the online agenda-setting process during a trigger event, this longitudinal macro-level study explores the over-time relationship between US news media attention and aggregate search interest of the online public in BP plc throughout the Gulf of Mexico oil spill in 2010. The results provide strong evidence of an interactive two-way street in the transfer of salience between the media and search agendas. In addition to slower-moving, basic agenda-setting effects of news coverage volumes on aggregate search query volumes, this study documents an instance of faster-moving “reverse agenda setting” with the news media responding to search trends during the prolonged oil spill disaster. The theoretical, methodological, and practical implications of these findings are discussed.

How does market concern derived from the Internet affect oil prices?

With the acceleration of oil marketisation and the rapid development of electronic information carriers, external information shocks can be easily and quickly transmitted to the oil market through the Internet. This paper analyses the impact of short- and long-run market concerns, derived from search query volumes in Google for different domains around the oil market on oil volatility using co-integration and the modified EGARCH model. Empirical results suggest there is a long-term equilibrium relationship between oil prices and long-run market concern for oil prices and oil demand. The short-run market concerns for the 2008 financial crisis and the Libyan war convulsion have a significant and asymmetric influence on oil price volatility. This indicates that market concern transmitted through the Internet can strengthen the linkage between oil price changes and external events by influencing the expectation of market traders, and to some extent it can exaggerate the impact of nonfundamental information shocks.

Forecasting hotel room demand using search engine data

PurposeThe purpose of this paper is to investigate the usefulness of search query volume data in forecasting demand for hotel rooms and identify the best econometric forecasting model.Design/methodology/approachThe authors used search volume data on five related queries to predict demand for hotel rooms in a specific tourist city and employed three ARMA family models and their ARMAX counterparts to evaluate the usefulness of these data. The authors also evaluated three widely used causal econometric models – ADL, TVP, and VAR – for comparison.FindingsAll three ARMAX models consistently outperformed their ARMA counterparts, validating the value of search volume data in facilitating the accurate prediction of demand for hotel rooms. When the three causal econometric models were included for forecasting competition, the ARX model produced the most accurate forecasts, suggesting its usefulness in forecasting demand for hotel rooms.Research limitations/implicationsTo demonstrate the usefulness of this data type, the authors focused on one tourist city with five specific tourist‐related queries. Future studies could focus on other aspects of tourist consumption and on more destinations, using a larger number of queries to increase accuracy.Practical implicationsSearch volume data are an early indicator of travelers' interest and could be used to predict various types of tourist consumption and activities, such as hotel occupancy, spending, and event attendance.Originality/valueThe paper's findings validate the value of search query volume data in predicting hotel room demand, and the paper is the first of its kind in the field of tourism and hospitality research.

Predicting consumer behavior with Web search

Recent work has demonstrated that Web search volume can "predict the present," meaning that it can be used to accurately track outcomes such as unemployment levels, auto and home sales, and disease prevalence in near real time. Here we show that what consumers are searching for online can also predict their collective future behavior days or even weeks in advance. Specifically we use search query volume to forecast the opening weekend box-office revenue for feature films, first-month sales of video games, and the rank of songs on the Billboard Hot 100 chart, finding in all cases that search counts are highly predictive of future outcomes. We also find that search counts generally boost the performance of baseline models fit on other publicly available data, where the boost varies from modest to dramatic, depending on the application in question. Finally, we reexamine previous work on tracking flu trends and show that, perhaps surprisingly, the utility of search data relative to a simple autoregressive model is modest. We conclude that in the absence of other data sources, or where small improvements in predictive performance are material, search queries provide a useful guide to the near future.