Can Google Trends search queries contribute to risk diversification?

The influencing mechanism of scenic spot online attention and tourists' purchase behavior: an AISAS model based investigation

Introduction

In the era of the Internet, online digital traces have become a new way to study the online attention of scenic spots and tourists' purchase behavior. The public's information search on major search platforms is a series of manifestations of potential tourists' attention and interest in scenic spots, but there are few studies on how attention, interest and information search affect potential tourists to generate real purchase behavior.

Method

This paper selects four dimensions of short video platform, travel website, search engine and social media to comprehensively measure the online attention of high-quality scenic spots in Yunnan Province, and then establishes a gray association analytic hierarchy process based on the relevant variables of the AISAS model to empirically analyze the primary and secondary factors affecting tourists' purchase behavior.

Results

(1) From the perspective of the online attention of scenic spots on different platforms, the intensity of the public's scenic spots online attention on the four types of media platforms is in the order of travel websites, search engines, short videos and social media (2) From the perspective of spatial distribution characteristics, the online attention of high-quality scenic spots in Yunnan Province is unevenly distributed, that is, there is a big difference between the attention of higher star scenic spots and their star rating and popularity, while the attention of low-star scenic spots is not much different from their star rating and popularity (3) From the perspective of spatial agglomeration characteristics, the comprehensive online attention of high-quality scenic spots in Yunnan Province presents the spatial agglomeration characteristics of "the multi-core linkage of high-density in the east and north, and sub-high-density in the south" (4) The factors influencing the purchase behavior of potential tourists are sharing experience, attracting attention, generating interest and searching information.

Discussion

By exploring the formation mechanism of high-quality scenic spots online attention in Yunnan Province and the mechanism of its spatial differentiation, this study not only enriches the logical chain of "tourism information source → potential tourists → demand driven → tourism information search → travel preference → destination selection → purchase decision → travel experience → real tourists → feelings after traveling → focus on feedback → tourism information source," but also broadens the application scenarios and application boundaries of travel preference theory and AISAS behavior model to a certain extent.

Effects of the first wave of COVID-19 pandemic on implied stock market volatility: International evidence using a google trend measure

This paper investigates the relationship between investors' attention, as measured by Google search queries, and equity implied volatility during the COVID-19 outbreak. Recent studies show that search investors' behavior data is an extremely abundant repository of predictive data, and investor-limited attention increases when the uncertainty level is high. Our study using data from thirteen countries across the globe during the first wave of the COVID-19 pandemic (January-April 2020) examines whether the search "topic and terms" for the pandemic affect market participants' expectations about future realized volatility. With the panic and uncertainty about COVID-19, our empirical findings show that increased internet searches during the pandemic caused the information to flow into the financial markets at a faster rate and thus resulting in higher implied volatility directly and via the stock return-risk relation. More specifically for the latter, the leverage effect in the VIX becomes stronger as Google search queries intensify. Both the direct and indirect effects on implied volatility, highlight a risk-aversion channel that operates during the pandemic. We also find that these effects are stronger in Europe than in the rest of the world. Moreover, in a panel vector autoregression framework, we show that a positive shock on stock returns may soothe COVID-related Google searches in Europe. Our findings suggest that Google-based attention to COVID-19 leads to elevated risk aversion in stock markets.

Conservation in the Amazon rainforest and Google searches: A DCCA approach

In this paper we analyze the descriptive statistics of the Google search volume for the terms related to the National Reserve of Copper and Associates (RENCA), a Brazilian mineral reserve in the Amazon of 4.6 million hectares, before and after the government signed the decree releasing it for exploration. First, we analyze the volume of searches for expressions related to RENCA in Google Trends using descriptive statistics; second, we assess the cross-correlation coefficient ρDCCA, which measures the cross-correlation between two nonstationary time series across different time scales. After the government announced the release of the RENCA reserve, there was an increase in the average volume of Google searches for related terms, showing people's concern about the announcement. By using the cross-correlation coefficient ρDCCA, we identify strong cross-correlations between the different expressions related to RENCA in Google Trends. Our work shows the utility of Google Trends as an indicator of the perception of environmental policies. Additionally, we show that ρDCCA can be used as a tool to measure the cross-correlation between synonyms extracted from Google Trends for various time scales.

The Effect of Quantitative Easing through Google Metrics on US Stock Indices

The purpose of this study is to investigate the fluctuations that occur in stock returns of US stock indices when there is an increase in the volume of Google internet searches for the phrase “quantitative easing” in the US. The exponential generalized autoregressive conditional heteroscedasticity model (EGARCH) was applied based on weekly data of stock indices using the three-factor model of Fama and French for the period of 1 January 2006 to 30 October 2020. The existence of a statistically significant relationship between searches and financial variables, especially in the stock market, is evident. The result is strong in three of the four stock indices studied. Specifically, the SVI index was statistically significant, with a positive trend for the S&P 500 and Dow Jones indices and a negative trend for the VIX index. Investor focus on quantitative easing (QE), as determined by Google metrics, seems to calm stock market volatility and increase stock returns. Although there is a large body of research using Google Trends as a crowdsourcing method of forecasting stock returns, this paper is the first to examine the relationship between the increase in internet searches of “quantitative easing” and stock market returns.

Google search volumes and the financial markets during the COVID-19 outbreak

During the outbreak of the COVID-19, concerns related to the severity of the pandemic have played a prominent role in investment decisions. In this paper, we analyze the relationship between public attention and the financial markets using search engine data from Google Trends. Our findings show that search query volumes in Italy, Germany, France, Great Britain, Spain, and the United States are connected with stock markets. The Italian Google Trends index is found to be the main driver of all the considered markets. Furthermore, the country-specific market impacts of COVID-19-related concerns closely follow the Italian lockdown process.

A short-and long-term analysis of the nexus between Bitcoin, social media and Covid-19 outbreak

In this paper, we attempt to analyze the dynamic interplay between Bitcoin, social media, and the Covid-19 health crisis. For this end, we apply the fractional autoregressive vector model, fractional error correction model and impulse response functions on daily data over the period 31/12/2019-30/10/2020. Our results clearly show the short- and long-term evidence of the nexus between the Bitcoin price, social media metrics (Tweets and Google Trends) and the intensity of the Covid-19 pandemic. As well, the Covid-19 pandemic does not impact on social media metrics in the short- and long-term. On the other hand, the Covid-19 pandemic positively affects social media metrics. Also, the Covid-19 pandemic encourages investing in digital currencies such as Bitcoin. So, the Covid-19 health crisis significantly influences social media networks and Bitcoin prices.

Worldwide antipsychotic drug search intensities: pharmacoepidemological estimations based on Google Trends data

Prescription patterns of antipsychotic drugs (APDs) are typically sourced from country-specific data. In this study, a digital pharmacoepidemiological approach was used to investigate APD preferences globally. Publicly available data on worldwide web search intensities in Google for 19 typical and 22 atypical APDs were temporally and spatially normalized and correlated with reported prescription data. The results demonstrated an increasing global preference for atypical over typical APDs since 2007, with quetiapine, olanzapine, risperidone, and aripiprazole showing the largest search intensities in 2020. Cross-sectional analysis of 122 countries in 2020 showed pronounced differences in atypical/typical APD preferences that correlated with gross domestic product per capita. In conclusion, the investigation provides temporal and spatial assessments of global APD preferences and shows a trend towards atypical APDs, although with a relative preference for typical APDs in low-income countries. Similar data-sourcing methodologies allow for prospective studies of other prescription drugs.

Revisiting the use of web search data for stock market movements

Advances in Big Data make it possible to make short-term forecasts for market trends from previously unexplored sources. Trading strategies were recently developed by exploiting a link between the online search activity of certain terms semantically related to finance and market movements. Here we build on these earlier results by exploring a data-driven strategy which adaptively leverages the Google Correlate service and automatically chooses a new set of search terms for every trading decision. In a backtesting experiment run from 2008 to 2017 we obtained a 499% cumulative return which compares favourably with benchmark strategies. A crowdsourcing exercise reveals that the term selection process preferentially selects highly specific terms semantically related to finance (e.g. Wells Fargo Bank), which may capture the transient interests of investors, but at the cost of a shorter span of validity. The adaptive strategy quickly updates the set of search terms when a better combination is found, leading to more consistent predictability. We anticipate that this adaptive decision framework can be of value not only for financial applications, but also in other areas of computational social science, where linkages between facets of collective human behavior and online searches can be inferred from digital footprint data.

Using Google Trends to Examine the Spatio-Temporal Incidence and Behavioral Patterns of Dengue Disease: A Case Study in Metropolitan Manila, Philippines

Dengue is a major public health concern and an economic burden in the Philippines. Despite the country's improved dengue surveillance, it still suffers from various setbacks and needs to be complemented with alternative approaches. Previous studies have demonstrated the potential of Internet-based surveillance such as Google Dengue Trends (GDT) in supplementing current epidemiological methods for predicting future dengue outbreaks and patterns. With this, our study has two objectives: (1) assess the temporal relationship of weekly GDT and dengue incidence in Metropolitan Manila from 2009⁻2014; and (2) examine the health-seeking behavior based on dengue-related search queries of the population. The study collated the population statistics and reported dengue cases in Metropolitan Manila from respective government agencies to calculate the dengue incidence (DI) on a weekly basis for the entire region and annually per city. Data processing of GDT and dengue incidence was performed by conducting an 'adjustment' and scaling procedures, respectively, and further analyzed for correlation and cross-correlation analyses using Pearson's correlation. The relative search volume of the term 'dengue' and top dengue-related search queries in Metropolitan Manila were obtained and organized from the Google Trends platform. Afterwards, a thematic analysis was employed, and word clouds were generated to examine the health behavior of the population. Results showed that weekly temporal GDT pattern are closely similar to the weekly DI pattern in Metropolitan Manila. Further analysis showed that GDT has a moderate and positive association with DI when adjusted or scaled, respectively. Cross-correlation analysis revealed a delayed effect where GDT leads DI by 1⁻2 weeks. Thematic analysis of dengue-related search queries indicated 5 categories namely; (a) dengue, (b) sign and symptoms of dengue, (c) treatment and prevention, (d) mosquito, and (e) other diseases. The majority of the search queries were classified in 'signs and symptoms' which indicate the health-seeking behavior of the population towards the disease. Therefore, GDT can be utilized to complement traditional disease surveillance methods combined with other factors that could potentially identify dengue hotspots and help in public health decisions.

Fluctuation-driven price dynamics and investment strategies

Investigation of the driven mechanism of the price dynamics in complex financial systems is important and challenging. In this paper, we propose an investment strategy to study how dynamic fluctuations drive the price movements. The strategy is successfully applied to different stock markets in the world, and the result indicates that the driving effect of the dynamic fluctuations is rather robust. We investigate how the strategy performance is influenced by the market states and optimize the strategy performance by introducing two parameters. The strategy is also compared with several typical technical trading rules. Our findings not only provide an investment strategy which extends investors’ profits, but also offer a useful method to look into the dynamic properties of complex financial systems.

Direct oral anticoagulants: analysis of worldwide use and popularity using Google Trends

BACKGROUND

Four direct oral anticoagulants (DOACs) have been approved for clinical use by many medicines regulatory agencies around the world. Due to increasing use of these drugs in routine practice, we planned an original study to investigate their worldwide diffusion using a popular Web-search engine.

METHODS

Two electronic searches were performed using Google Trends, the former using the keywords "warfarin" AND "heparin" AND "fondaparinux", and the latter using the keywords "warfarin" AND "dabigatran" AND "rivaroxaban" AND "apixaban" AND "edoxaban", both using the search criterion "prescription drug". No language restriction was applied, and the searches were carried out from the first date available in Google Trends (January 1^st, 2004) to present time (June 1^st, 2017).

RESULTS

The median Google Trends score of warfarin (i.e., 86) was consistently higher than that of heparin (54; P<0.001), fondaparinux (6; P<0.001), dabigatran (11; P<0.001), rivaroxaban (5; P<0.001), apixaban (1; P<0.001) and edoxaban (1; P<0.001). Specific analysis of the trends shows that the score of warfarin exhibits a highly significant decrease over time (r=-0.40; P<0.001), whilst that of heparin has remained virtually unchanged (r=0.12; P=0.127), and that of fondaparinux has marginally increased (r=0.16; P=0.038). As regards DOACs, the scores of these drugs significantly increased during the search period (dabigatran, r=0.79; rivaroxaban, r=0.99; apixaban, r=0.98; edoxaban, r=0.78; all P<0.001). When the analysis was limited to the past five years, the dabigatran score significantly decreased (r=-0.57; P<0.001), whereas that of the other DOACs exhibited an even sharper increase. Most Google searches for DOACs were performed in North America, central-eastern Europe and Australia.

CONCLUSIONS

The results of our analysis suggest that the popularity of DOACs is constantly increasing around the world, whereas that of warfarin has exhibited a constant and inexorable decline.

Quantifying the effect of investors' attention on stock market

The investors’ attention has been extensively used to predict the stock market. Different from existing proxies of the investors’ attention, such as the Google trends, Baidu index (BI), we argue the collective attention from the stock trading platforms could reflect the investors’ attention more closely. By calculated the increments ofthe attention volumefor each stock (IAVS) from the stock trading platforms, we investigate the effect of investors’ attention measured by the IAVS on the movement of the stock market. The experimental results for Chinese Securities Index 100 (CSI100) show that the BI is significantly correlated with the returns of CSI100 at 1% significance level only in 2014. However, it should be emphasized that the correlation of the new proposed measure, namely IAVS, is significantly at 1% significance level in 2014 and 2015. It shows that the effect of the measure IAVS on the movement of the stock market is more stable and significant than BI. This study yields important invest implications and better understanding of collective investors’ attention.

When Bitcoin encounters information in an online forum: Using text mining to analyse user opinions and predict value fluctuation

Bitcoin is an online currency that is used worldwide to make online payments. It has consequently become an investment vehicle in itself and is traded in a way similar to other open currencies. The ability to predict the price fluctuation of Bitcoin would therefore facilitate future investment and payment decisions. In order to predict the price fluctuation of Bitcoin, we analyse the comments posted in the Bitcoin online forum. Unlike most research on Bitcoin-related online forums, which is limited to simple sentiment analysis and does not pay sufficient attention to note-worthy user comments, our approach involved extracting keywords from Bitcoin-related user comments posted on the online forum with the aim of analytically predicting the price and extent of transaction fluctuation of the currency. The effectiveness of the proposed method is validated based on Bitcoin online forum data ranging over a period of 2.8 years from December 2013 to September 2016.

Twitter sentiment around the Earnings Announcement events

We investigate the relationship between social media, Twitter in particular, and stock market. We provide an in-depth analysis of the Twitter volume and sentiment about the 30 companies in the Dow Jones Industrial Average index, over a period of three years. We focus on Earnings Announcements and show that there is a considerable difference with respect to when the announcements are made: before the market opens or after the market closes. The two different timings of the Earnings Announcements were already investigated in the financial literature, but not yet in the social media. We analyze the differences in terms of the Twitter volumes, cumulative abnormal returns, trade returns, and earnings surprises. We report mixed results. On the one hand, we show that the Twitter sentiment (the collective opinion of the users) on the day of the announcement very well reflects the stock moves on the same day. We demonstrate this by applying the event study methodology, where the polarity of the Earnings Announcements is computed from the Twitter sentiment. Cumulative abnormal returns are high (2–4%) and statistically significant. On the other hand, we find only weak predictive power of the Twitter sentiment one day in advance. It turns out that it is important how to account for the announcements made after the market closes. These after-hours announcements draw high Twitter activity immediately, but volume and price changes in trading are observed only on the next day. On the day before the announcements, the Twitter volume is low, and the sentiment has very weak predictive power. A useful lesson learned is the importance of the proper alignment between the announcements, trading and Twitter data.

Predicting Virtual World User Population Fluctuations with Deep Learning

This paper proposes a system for predicting increases in virtual world user actions. The virtual world user population is a very important aspect of these worlds; however, methods for predicting fluctuations in these populations have not been well documented. Therefore, we attempt to predict changes in virtual world user populations with deep learning, using easily accessible online data, including formal datasets from Google Trends, Wikipedia, and online communities, as well as informal datasets collected from online forums. We use the proposed system to analyze the user population of EVE Online, one of the largest virtual worlds.

Estimating suicide occurrence statistics using Google Trends

Data on the number of people who have committed suicide tends to be reported with a substantial time lag of around two years. We examine whether online activity measured by Google searches can help us improve estimates of the number of suicide occurrences in England before official figures are released. Specifically, we analyse how data on the number of Google searches for the terms 'depression' and 'suicide' relate to the number of suicides between 2004 and 2013. We find that estimates drawing on Google data are significantly better than estimates using previous suicide data alone. We show that a greater number of searches for the term 'depression' is related to fewer suicides, whereas a greater number of searches for the term 'suicide' is related to more suicides. Data on suicide related search behaviour can be used to improve current estimates of the number of suicide occurrences.

ELECTRONIC SUPPLEMENTARY MATERIAL

The online version of this article (doi:10.1140/epjds/s13688-016-0094-0) contains supplementary material.

Tracking Protests Using Geotagged Flickr Photographs

Recent years have witnessed waves of protests sweeping across countries and continents, in some cases resulting in political and governmental change. Much media attention has been focused on the increasing usage of social media to coordinate and provide instantly available reports on these protests. Here, we investigate whether it is possible to identify protest outbreaks through quantitative analysis of activity on the photo sharing site Flickr. We analyse 25 million photos uploaded to Flickr in 2013 across 244 countries and regions, and determine for each week in each country and region what proportion of the photographs are tagged with the word "protest" in 34 different languages. We find that higher proportions of "protest"-tagged photographs in a given country and region in a given week correspond to greater numbers of reports of protests in that country and region and week in the newspaper The Guardian. Our findings underline the potential value of photographs uploaded to the Internet as a source of global, cheap and rapidly available measurements of human behaviour in the real world.

Quantifying the Search Behaviour of Different Demographics Using Google Correlate

Vast records of our everyday interests and concerns are being generated by our frequent interactions with the Internet. Here, we investigate how the searches of Google users vary across U.S. states with different birth rates and infant mortality rates. We find that users in states with higher birth rates search for more information about pregnancy, while those in states with lower birth rates search for more information about cats. Similarly, we find that users in states with higher infant mortality rates search for more information about credit, loans and diseases. Our results provide evidence that Internet search data could offer new insight into the concerns of different demographics.

Coupling News Sentiment with Web Browsing Data Improves Prediction of Intra-Day Price Dynamics

The new digital revolution of big data is deeply changing our capability of understanding society and forecasting the outcome of many social and economic systems. Unfortunately, information can be very heterogeneous in the importance, relevance, and surprise it conveys, affecting severely the predictive power of semantic and statistical methods. Here we show that the aggregation of web users’ behavior can be elicited to overcome this problem in a hard to predict complex system, namely the financial market. Specifically, our in-sample analysis shows that the combined use of sentiment analysis of news and browsing activity of users of Yahoo! Finance greatly helps forecasting intra-day and daily price changes of a set of 100 highly capitalized US stocks traded in the period 2012–2013. Sentiment analysis or browsing activity when taken alone have very small or no predictive power. Conversely, when considering a news signal where in a given time interval we compute the average sentiment of the clicked news, weighted by the number of clicks, we show that for nearly 50% of the companies such signal Granger-causes hourly price returns. Our result indicates a “wisdom-of-the-crowd” effect that allows to exploit users’ activity to identify and weigh properly the relevant and surprising news, enhancing considerably the forecasting power of the news sentiment.

Assessing Ebola-related web search behaviour: insights and implications from an analytical study of Google Trends-based query volumes

Background

The 2014 Ebola epidemic in West Africa has attracted public interest worldwide, leading to millions of Ebola-related Internet searches being performed during the period of the epidemic. This study aimed to evaluate and interpret Google search queries for terms related to the Ebola outbreak both at the global level and in all countries where primary cases of Ebola occurred. The study also endeavoured to look at the correlation between the number of overall and weekly web searches and the number of overall and weekly new cases of Ebola.

Methods

Google Trends (GT) was used to explore Internet activity related to Ebola. The study period was from 29 December 2013 to 14 June 2015. Pearson’s correlation was performed to correlate Ebola-related relative search volumes (RSVs) with the number of weekly and overall Ebola cases. Multivariate regression was performed using Ebola-related RSV as a dependent variable, and the overall number of Ebola cases and the Human Development Index were used as predictor variables.

Results

The greatest RSV was registered in the three West African countries mainly affected by the Ebola epidemic. The queries varied in the different countries. Both quantitative and qualitative differences between the affected African countries and other Western countries with primary cases were noted, in relation to the different flux volumes and different time courses. In the affected African countries, web query search volumes were mostly concentrated in the capital areas. However, in Western countries, web queries were uniformly distributed over the national territory. In terms of the three countries mainly affected by the Ebola epidemic, the correlation between the number of new weekly cases of Ebola and the weekly GT index varied from weak to moderate. The correlation between the number of Ebola cases registered in all countries during the study period and the GT index was very high.

Conclusion

Google Trends showed a coarse-grained nature, strongly correlating with global epidemiological data, but was weaker at country level, as it was prone to distortions induced by unbalanced media coverage and the digital divide. Global and local health agencies could usefully exploit GT data to identify disease-related information needs and plan proper communication strategies, particularly in the case of health-threatening events.

Electronic supplementary material

The online version of this article (doi:10.1186/s40249-015-0090-9) contains supplementary material, which is available to authorized users.

The Effects of Twitter Sentiment on Stock Price Returns

Social media are increasingly reflecting and influencing behavior of other complex systems. In this paper we investigate the relations between a well-known micro-blogging platform Twitter and financial markets. In particular, we consider, in a period of 15 months, the Twitter volume and sentiment about the 30 stock companies that form the Dow Jones Industrial Average (DJIA) index. We find a relatively low Pearson correlation and Granger causality between the corresponding time series over the entire time period. However, we find a significant dependence between the Twitter sentiment and abnormal returns during the peaks of Twitter volume. This is valid not only for the expected Twitter volume peaks (e.g., quarterly announcements), but also for peaks corresponding to less obvious events. We formalize the procedure by adapting the well-known “event study” from economics and finance to the analysis of Twitter data. The procedure allows to automatically identify events as Twitter volume peaks, to compute the prevailing sentiment (positive or negative) expressed in tweets at these peaks, and finally to apply the “event study” methodology to relate them to stock returns. We show that sentiment polarity of Twitter peaks implies the direction of cumulative abnormal returns. The amount of cumulative abnormal returns is relatively low (about 1–2%), but the dependence is statistically significant for several days after the events.

Collective attention and stock prices: evidence from Google Trends data on Standard and Poor's 100

Today´s connected world allows people to gather information in shorter intervals than ever before, widely monitored by massive online data sources. As a dramatic economic event, recent financial crisis increased public interest for large companies considerably. In this paper, we exploit this change in information gathering behavior by utilizing Google query volumes as a "bad news" indicator for each corporation listed in the Standard and Poor´s 100 index. Our results provide not only an investment strategy that gains particularly in times of financial turmoil and extensive losses by other market participants, but reveal new sectoral patterns between mass online behavior and (bearish) stock market movements. Based on collective attention shifts in search queries for individual companies, hence, these findings can help to identify early warning signs of financial systemic risk. However, our disaggregated data also illustrate the need for further efforts to understand the influence of collective attention shifts on financial behavior in times of regular market activities with less tremendous changes in search volumes.

Nowcasting unemployment rates with Google searches: evidence from the Visegrad Group countries

The online activity of Internet users has repeatedly been shown to provide a rich information set for various research fields. We focus on job-related searches on Google and their possible usefulness in the region of the Visegrad Group - the Czech Republic, Hungary, Poland and Slovakia. Even for rather small economies, the online searches of inhabitants can be successfully utilized for macroeconomic predictions. Specifically, we study unemployment rates and their interconnection with job-related searches. We show that Google searches enhance nowcasting models of unemployment rates for the Czech Republic and Hungary whereas for Poland and Slovakia, the results are mixed.

Nowcasting and forecasting the monthly food stamps data in the US using online search data

We propose the use of Google online search data for nowcasting and forecasting the number of food stamps recipients. We perform a large out-of-sample forecasting exercise with almost 3000 competing models with forecast horizons up to 2 years ahead, and we show that models including Google search data statistically outperform the competing models at all considered horizons. These results hold also with several robustness checks, considering alternative keywords, a falsification test, different out-of-samples, directional accuracy and forecasts at the state-level.

Adaptive nowcasting of influenza outbreaks using Google searches

Seasonal influenza outbreaks and pandemics of new strains of the influenza virus affect humans around the globe. However, traditional systems for measuring the spread of flu infections deliver results with one or two weeks delay. Recent research suggests that data on queries made to the search engine Google can be used to address this problem, providing real-time estimates of levels of influenza-like illness in a population. Others have however argued that equally good estimates of current flu levels can be forecast using historic flu measurements. Here, we build dynamic 'nowcasting' models; in other words, forecasting models that estimate current levels of influenza, before the release of official data one week later. We find that when using Google Flu Trends data in combination with historic flu levels, the mean absolute error (MAE) of in-sample 'nowcasts' can be significantly reduced by 14.4%, compared with a baseline model that uses historic data on flu levels only. We further demonstrate that the MAE of out-of-sample nowcasts can also be significantly reduced by between 16.0% and 52.7%, depending on the length of the sliding training interval. We conclude that, using adaptive models, Google Flu Trends data can indeed be used to improve real-time influenza monitoring, even when official reports of flu infections are available with only one week's delay.

Adaptive nowcasting of influenza outbreaks using Google searches

Seasonal influenza outbreaks and pandemics of new strains of the influenza virus affect humans around the globe. However, traditional systems for measuring the spread of flu infections deliver results with one or two weeks delay. Recent research suggests that data on queries made to the search engine Google can be used to address this problem, providing real-time estimates of levels of influenza-like illness in a population. Others have however argued that equally good estimates of current flu levels can be forecast using historic flu measurements. Here, we build dynamic 'nowcasting' models; in other words, forecasting models that estimate current levels of influenza, before the release of official data one week later. We find that when using Google Flu Trends data in combination with historic flu levels, the mean absolute error (MAE) of in-sample 'nowcasts' can be significantly reduced by 14.4%, compared with a baseline model that uses historic data on flu levels only. We further demonstrate that the MAE of out-of-sample nowcasts can also be significantly reduced by between 16.0% and 52.7%, depending on the length of the sliding training interval. We conclude that, using adaptive models, Google Flu Trends data can indeed be used to improve real-time influenza monitoring, even when official reports of flu infections are available with only one week's delay.

Characterizing the time-perspective of nations with search engine query data

Vast quantities of data on human behavior are being created by our everyday internet usage. Building upon a recent study by Preis, Moat, Stanley, and Bishop (2012), we used search engine query data to construct measures of the time-perspective of nations, and tested these measures against per-capita gross domestic product (GDP). The results indicate that nations with higher per-capita GDP are more focused on the future and less on the past, and that when these nations do focus on the past, it is more likely to be the distant past. These results demonstrate the viability of using nation-level data to build psychological constructs.

Quantifying the relationship between financial news and the stock market

The complex behavior of financial markets emerges from decisions made by many traders. Here, we exploit a large corpus of daily print issues of the Financial Times from 2(nd) January 2007 until 31(st) December 2012 to quantify the relationship between decisions taken in financial markets and developments in financial news. We find a positive correlation between the daily number of mentions of a company in the Financial Times and the daily transaction volume of a company's stock both on the day before the news is released, and on the same day as the news is released. Our results provide quantitative support for the suggestion that movements in financial markets and movements in financial news are intrinsically interlinked.

BitCoin meets Google Trends and Wikipedia: quantifying the relationship between phenomena of the Internet era

Digital currencies have emerged as a new fascinating phenomenon in the financial markets. Recent events on the most popular of the digital currencies – BitCoin – have risen crucial questions about behavior of its exchange rates and they offer a field to study dynamics of the market which consists practically only of speculative traders with no fundamentalists as there is no fundamental value to the currency. In the paper, we connect two phenomena of the latest years – digital currencies, namely BitCoin, and search queries on Google Trends and Wikipedia – and study their relationship. We show that not only are the search queries and the prices connected but there also exists a pronounced asymmetry between the effect of an increased interest in the currency while being above or below its trend value.