Google Trends Search Research Articles

The impact of Sino–US trade war on price discovery of soybean: A double‐edged sword?

AbstractIn 2018, the world witnessed a full‐fledged trade war between United States and China with both countries levying successive tariffs on each other. Though the impact of trade war could be visibly assessed from declining export volume and rising bankruptcy filing from farmers, what went unnoticed was a far‐reaching negative impact at a granular market microstructure level. In this study, the effect of trade war on the leading role of US soybean futures in price discovery has been evaluated. The results corroborate the negative impact of trade war on the information leadership share of US soybean futures market. Moreover, the results shows that the negative impact gets manifested through various sentiment indicators such as Google search trends, hedger's sentiment, and so on. Hence, trade war may have given some temporary economic and strategic benefit to the United States, but it is no less than the proverbial double‐edged sword as it nearly killed the soybean market of the United States.

Using Google Trends to Estimate the Geographic Distribution of Soil-Transmitted Helminthiasis in the United States from 2016 to 2021.

Soil-transmitted helminth infections are assumed to be uncommon in the US, despite numerous studies in the past few decades showing high burdens in Appalachia and the southern states. We assessed trends of interest in the Google search engine to gauge spatiotemporal patterns of potential soil-transmitted helminth transmission. We conducted a further ecological study comparing Google search trends to risk factors for soil-transmitted helminth transmission. Google search trends for terms related to soil-transmitted helminths were clustered in Appalachia and the south, with seasonal surges suggestive of endemic transmission for hookworm, roundworm (Ascaris), and threadworm. Furthermore, lower access to plumbing, increased septic tank use, and more rural environments were associated with increased soil-transmitted helminth-related Google search terms. Together, these results suggest that soil-transmitted helminthiasis remains endemic in parts of Appalachia and the south.

Regenerative therapies for erectile dysfunction: the influence of direct-to-consumer marketing on patient interest.

Despite a lack of evidence, a number of "regenerative" therapies have become popularized treatments for erectile dysfunction (ED). Platelet-rich plasma (PRP) injections and shockwave therapy have received significant attention through direct-to-consumer marketing and are advertised as viable alternatives to guideline-backed therapies. Additionally, focused low-intensity shock wave therapy (LiSWT) has become conflated with acoustic or radial wave therapy (rWT), although their mechanism of wave generation and tissue penetration is distinct. GAINSWave, a marketing platform for acoustic wave therapy, has also pervaded the marketplace. We aim to evaluate the relative impact of direct-to-consumer marketing of shockwave therapy and PRP by analyzing the quantity of Google internet search queries for selected regenerative and guideline-backed non-regenerative therapies for ED. National Google Search trends in the United States (www.google.com/trends) were analyzed to characterize interest in different forms of therapy for ED. Search trends for PRP, LiSWT (and various iterations), intracavernosal injections (ICI), intraurethral injections (IU), vacuum erectile device (VED), and GAINSWave were analyzed. Monthly search data were compiled over multiple years, ending at 2/28/2020, just before the COVID-19 pandemic and state of emergency in the United States. Macro-level changes in public interest were quantified using yearly averages. Patterns in Google Search interest in PRP and LiSWT increased respectively by 3-fold and 275-fold over the decade, representing a larger share of Google Searches by 2020. Trends in Google Search interest in selected types of shockwave therapy for ED also show that queries for GAINSWave commanded public interest, increasing by 219-fold from 2016 to 2020. Regenerative therapies for ED have produced interest surpassing other adjunct guideline-backed therapies, despite receiving the designation of "experimental" or "investigational" therapies. The establishment of GAINSWave also constitutes an inflection point for the whole shockwave market: searches for shockwave therapy increased by 782% between 2016 and 2020. Direct-to-consumer marketing of PRP and shockwave therapy has upturned the customary role of physicians in counseling patients about evidence-based therapies for ED. This increase in public interest in GAINSWave emphasizes its success as a marketing platform. The urological community should consider strategies to address misinformation, such as search-engine optimization, social media, and educational outreach.

Tracking Population-Level Anxiety Using Search Engine Data: Ecological Study.

Anxiety disorders are the most prevalent mental disorders globally, with a substantial impact on quality of life. The prevalence of anxiety disorders has increased substantially following the COVID-19 pandemic, and it is likely to be further affected by a global economic recession. Understanding anxiety themes and how they change over time and across countries is crucial for preventive and treatment strategies. The aim of this study was to track the trends in anxiety themes between 2004 and 2020 in the 50 most populous countries with high volumes of internet search data. This study extends previous research by using a novel search-based methodology and including a longer time span and more countries at different income levels. We used a crowdsourced questionnaire, alongside Bing search query data and Google Trends search volume data, to identify themes associated with anxiety disorders across 50 countries from 2004 to 2020. We analyzed themes and their mutual interactions and investigated the associations between countries' socioeconomic attributes and anxiety themes using time-series linear models. This study was approved by the Microsoft Research Institutional Review Board. Query volume for anxiety themes was highly stable in countries from 2004 to 2019 (Spearman r=0.89) and moderately correlated with geography (r=0.49 in 2019). Anxiety themes were predominantly long-term and personal, with "having kids," "pregnancy," and "job" the most voluminous themes in most countries and years. In 2020, "COVID-19" became a dominant theme in 27 countries. Countries with a constant volume of anxiety themes over time had lower fragile state indexes (P=.007) and higher individualism (P=.003). An increase in the volume of the most searched anxiety themes was associated with a reduction in the volume of the remaining themes in 13 countries and an increase in 17 countries, and these 30 countries had a lower prevalence of mental disorders (P<.001) than the countries where no correlations were found. Internet search data could be a potential source for predicting the country-level prevalence of anxiety disorders, especially in understudied populations or when an in-person survey is not viable.

Development of a Machine Learning Model to Estimate US Firearm Homicides in Near Real Time

Firearm homicides are a major public health concern; lack of timely mortality data presents considerable challenges to effective response. Near real-time data sources offer potential for more timely estimation of firearm homicides. To estimate near real-time burden of weekly and annual firearm homicides in the US. In this prognostic study, anonymous, longitudinal time series data were obtained from multiple data sources, including Google and YouTube search trends related to firearms (2014-2019), emergency department visits for firearm injuries (National Syndromic Surveillance Program, 2014-2019), emergency medical service activations for firearm-related injuries (biospatial, 2014-2019), and National Domestic Violence Hotline contacts flagged with the keyword firearm (2016-2019). Data analysis was performed from September 2021 to September 2022. Weekly estimates of US firearm homicides were calculated using a 2-phase pipeline, first fitting optimal machine learning models for each data stream and then combining the best individual models into a stacked ensemble model. Model accuracy was assessed by comparing predictions of firearm homicides in 2019 to actual firearm homicides identified by National Vital Statistics System death certificates. Results were also compared with a SARIMA (seasonal autoregressive integrated moving average) model, a common method to forecast injury mortality. Both individual and ensemble models yielded highly accurate estimates of firearm homicides. Individual models' mean error for weekly estimates of firearm homicides (root mean square error) varied from 24.95 for emergency department visits to 31.29 for SARIMA forecasting. Ensemble models combining data sources had lower weekly mean error and higher annual accuracy than individual data sources: the all-source ensemble model had a weekly root mean square error of 24.46 deaths and full-year accuracy of 99.74%, predicting the total number of firearm homicides in 2019 within 38 deaths for the entire year (compared with 95.48% accuracy and 652 deaths for the SARIMA model). The model decreased the time lag of reporting weekly firearm homicides from 7 to 8 months to approximately 6 weeks. In this prognostic study of diverse secondary data on machine learning, ensemble modeling produced accurate near real-time estimates of weekly and annual firearm homicides and substantially decreased data source time lags. Ensemble model forecasts can accelerate public health practitioners' and policy makers' ability to respond to unanticipated shifts in firearm homicides.

Euro-Integration Direction of Changes in Circular Industry 4.0

Problem setting. The innovativeness of changes in Industry 4.0 systems involves not only comprehensive digitalization and automation of production processes and management, but also solutions to issues of environmental protection and a closed production cycle. The circular economy and Industry 4.0 are interrelated topics and require additional research. Analysis of recent researches and publications. An in-depth study of many components of Industry 4.0 was conducted by Zadorozhnij G.V. The peculiarities of the relationship between the circular economy and Industry 4.0 and sustainable development were dealt with Hennemann Hilario da Silva, T. and Sehnem, S., Di Maria E., De Marchi V., Galeazzo A., Tang Y. M., Hallioui A. et al. Hnap A. studied the prospects for the development of circular Industry 4.0 until 2030. Target of the research is to determine the general principles of potential innovative changes of Industry 4.0 in the conditions of European integration under the influence of the circular economy. Article’s main body. The article examines the role and significance of the circular economy and Industry 4.0 processes, which are gaining particular importance in relation to the level of costs and the effectiveness of the changes that may occur. The problem lies in the parallel development of changes in the circular economy and Industry 4.0, which must be combined. Analysis of recent studies has shown that the circular economy and the concepts of Industry 4.0 together influence sustainable development. An essential characteristic of the changes taking place under the influence of Industry 4.0 is the increase in the impact of changes in the circular economy and the formation of the environmental factor. Prospective programs for the transition to a circular economy using Industry 4.0 technologies are potential application strategies in specific fields of research. According to the data of various studies in different countries, evidence of the relationship between these topics has been obtained. The European Commission considers the transition from Industry 4.0 to Industry 5.0 as a direction that strengthens the importance of European industry and is a key direction of economic and social change, it should lead the digital and environmental transition. In the article, a Google Trends search was made for the topics «circular economy», «Industry 4.0», 2Industry 5.0» for the time period of the last 12 months (as of March 5, 2023) all over the world, Ukraine, some EU countries, with the selection of an average level of interest in these topics The average level of interest in the topic of the circular economy in the world is much higher than in the topic of Industry 4.0. Similar to the world indicators of the country of Italy, while in Ukraine the ratio is similar, but at a much lower level. Ukraine is close to Poland, but the trends are opposite, in Ukraine the demand for the circular economy prevails, and in Poland for Industry 4.0. Only two countries, Germany and Italy, have a demand for Industry 5.0. Conclusions and prospects for the development. The conducted studies showed that in Ukraine at the state level, programs should be formed to increase attention to both Industry 4.0 and the circular economy. Taking into account the tasks of European integration, the process of informing about the tasks of the EU for the development of Industry 5.0 should begin. The European experience should be used at the national level in Ukraine to stimulate the development of the foundations of the circular economy in industry for the recovery of the Ukrainian economy.

The Chinese Debt Trap Diplomacy Narrative: An Empirical Analysis

Abstract China’s debt trap diplomacy has been debated among academia, think tanks, and the policymaking community. Unlike previous research, which mainly focuses on China’s lending practice and strategic intentions, this study looks at the measurement of this narrative and its relations with the Belt and Road Initiative (BRI) and the China threat narratives. In particular, based on Google Trends search results from 1 February 2018 to 7 November 2021, this study creatively created weekly time series data to measure the narratives. Based on an autoregressive distributed lag model, this study finds that the BRI narrative and the China threat narrative make significant contributions to the debt trap diplomacy narrative. Results based on sub-datasets show that these significant relations are mainly driven by the English-speaking Indian public and that these relations are insignificant in the United States. This study contributes to the literature on China’s debt trap diplomacy by bringing solid empirical evidence and to academia as well in methods by presenting a (still) new quantitative approach to international relations.

Using weather factors and google data to predict COVID-19 transmission in Melbourne, Australia: A time-series predictive model

BackgroundForecast models have been essential in understanding COVID-19 transmission and guiding public health responses throughout the pandemic. This study aims to assess the effect of weather variability and Google data on COVID-19 transmission and develop multivariable time series AutoRegressive Integrated Moving Average (ARIMA) models for improving traditional predictive modelling for informing public health policy. MethodsCOVID-19 case notifications, meteorological factors and Google data were collected over the B.1.617.2 (Delta) outbreak in Melbourne, Australia from August to November 2021. Timeseries cross-correlation (TSCC) was used to evaluate the temporal correlation between weather factors, Google search trends, Google Mobility data and COVID-19 transmission. Multivariable time series ARIMA models were fitted to forecast COVID-19 incidence and Effective Reproductive Number (Reff) in the Greater Melbourne region. Five models were fitted to compare and validate predictive models using moving three-day ahead forecasts to test the predictive accuracy for both COVID-19 incidence and Reff over the Melbourne Delta outbreak. ResultsCase-only ARIMA model resulted in an R squared (R2) value of 0.942, Root Mean Square Error (RMSE) of 141.59, and Mean Absolute Percentage Error (MAPE) of 23.19. The model including transit station mobility (TSM) and maximum temperature (Tmax) had greater predictive accuracy with R2 0.948, RMSE 137.57, and MAPE 21.26. ConclusionMultivariable ARIMA modelling for COVID-19 cases and Reff was useful for predicting epidemic growth, with higher predictive accuracy for models including TSM and Tmax. These results suggest that TSM and Tmax would be useful for further exploration for developing weather-informed early warning models for future COVID-19 outbreaks with potential application for the inclusion of weather and Google data with disease surveillance in developing effective early warning systems for informing public health policy and epidemic response.

Google search trends and stock markets: Sentiment, attention or uncertainty?

Keyword-based measures purporting to reflect investor sentiment, attention or uncertainty have increasingly been used to model stock market behaviour. We investigate and shed light on the narrative reflected by Google search trends (GST) by constructing a neutral and general stock market-related GST index. To do so, we apply elastic net regression to select investor relevant search terms using a sample of 77 international stock markets. The index peaks around significant events that impacted global financial markets, moves closely with established measures of market uncertainty and it is predominantly correlated with uncertainty measures in differences, implying that GST reflect an uncertainty narrative. Returns and volatility for developed, emerging and frontier markets widely reflect changing Google search volumes and relationships conform to a priori expectations associated with uncertainty. Our index performs well relative to existing keyword-based uncertainty measures in its ability to approximate and predict systematic stock market drivers and factor dispersion underlying return volatility both in-sample and out-of-sample. Our study contributes to the understanding of the information reflected by GST, their relationship with stock markets and points towards generalisability, thus facilitating the development of further applications using internet search data.

Pandemic and precocious puberty - a Google trends study.

Recent publications from several countries have reported that more young people (mainly girls) are experiencing precocious puberty (PP)/menarche during the coronavirus disease 2019 pandemic compared to the past. This variation is attributed to the stress of confinement, lack of exercise, obesity and disturbed sleep patterns. A common feature of the relevant papers, however, is the small number of reported cases of PP. Studies have shown that searches for diseases on the internet also reflect to some extent the epidemiology of these diseases. To estimate, through internet searches for PP, any changes in the epidemiology of PP. We assessed in Google Trends searches for 21 PP-related terms in English internationally (which practically dwarf searches in other languages), in the years 2017-2021. Additionally, we assessed local searches for selected terms, in English and local languages, in countries where a rise in PP has been reported. Searches were collected in Relative Search Volumes format and analyzed using Kendall's Tau test, with a statistical significance threshold of P < 0.05. Internationally, searches for three PP-related terms showed no noticeable change over the study period, while searches for eight terms showed a decrease. An increase was found over time in searches for nine PP-related terms. Of the 17 searches in English and local languages, in countries where a rise in PP has been reported, 5 showed a significant increase over time. Over the study period, more than half of the search terms showed little change or declined. The discrepancy between internet searches for PP and the reported increase in the literature is striking. It would be expected that a true increase in the incidence of PP would also be aptly reflected in Google trends. If our findings are valid, the literature may have been biased. The known secular trend of decreasing age of puberty may also have played a role.

Real-Time Monitoring of Infectious Disease Outbreaks with a Combination of Google Trends Search Results and the Moving Epidemic Method: A Respiratory Syncytial Virus Case Study

The COVID-19 pandemic has disrupted the seasonal patterns of several infectious diseases. Understanding when and where an outbreak may occur is vital for public health planning and response. We usually rely on well-functioning surveillance systems to monitor epidemic outbreaks. However, not all countries have a well-functioning surveillance system in place, or at least not for the pathogen in question. We utilized Google Trends search results for RSV-related keywords to identify outbreaks. We evaluated the strength of the Pearson correlation coefficient between clinical surveillance data and online search data and applied the Moving Epidemic Method (MEM) to identify country-specific epidemic thresholds. Additionally, we established pseudo-RSV surveillance systems, enabling internal stakeholders to obtain insights on the speed and risk of any emerging RSV outbreaks in countries with imprecise disease surveillance systems but with Google Trends data. Strong correlations between RSV clinical surveillance data and Google Trends search results from several countries were observed. In monitoring an upcoming RSV outbreak with MEM, data collected from both systems yielded similar estimates of country-specific epidemic thresholds, starting time, and duration. We demonstrate in this study the potential of monitoring disease outbreaks in real time and complement classical disease surveillance systems by leveraging online search data.

Impact of Elon Musk’s Tweeting about Psychiatric Medication on the Internet, Media, and Purchasing: Observational Study

Background Public figures have an ability to shape public discourse, patterns of behaviors, and actions. Tech-billionaire Elon Musk, with nearly 100 million followers on Twitter, advocated for the decrease use of Wellbutrin with neutral-to-positive opinion of Ritalin. Objective We investigated Elon Musk’s Twitter posts, subsequent Google search trends, Amazon purchases, television airtime, and news articles on the terms Wellbutrin, bupropion, methylphenidate, Adderall, and Ritalin. Methods Twitter was indexed with Social Sprout, as well as to determine average analytics, impressions, and other necessary metrics. News and television airtime was catalogued in the United States’ 5 largest TV stations with the Global Database of Events, Language, and Tone. Google searches and shopping trends were analyzed with Google Trends. Amazon purchases were catalogued with Helium 10 software. Sentiment analysis was performed on Twitter hashtags using Sentiment Viz. Results From April 24 to May 14, 2022, EM made 3 tweets anecdotally about Wellbutrin and Ritalin, which resulted in a nearly 130% increase in retweets and 472% increase in comments compared to average. Sentiment on Twitter remained largely negative for Wellbutrin, compared to Ritalin. Wellbutrin was searched the most, along with its side effects and treatments, followed by Ritalin, then Adderall, Bupropion, and Methylphenidate. Bupropion and Methylphenidate had extended search periods, compared to Ritalin and Wellbutrin. Purchasing of all top Ritalin products increased on Amazon (18% increase compared to previous week), whereas Wellbutrin-like products decreased in purchasing by 11% on average. Conclusions Twitter has mass sway and influence on populations, including their purchasing power. Public health officials must work to combat medical misinformation on the platform.

The progression in employer branding and employee based brand equity: Scholar API based systematic literature review

Aim/purpose – This paper systematically reviews the literature of employer branding (EB) and employee-based brand equity (EBBE) using the Application Programming Interface (API) provided by Google Scholar. While combining EB and EBBE this paper considers both the perspective of current, as well as potential employees and provides a systematization of knowledge related to organizational attractiveness and the impact of employees on the organizational brand. Design/methodology/approach – This study reviews the progresses in employer brand- ing since 2009 to 2022, therefore ranging from the time that the concept of employee- -based brand equity was proposed by King and Grace (2009). A four-stage process em- powered by was used to review the existing literature: 1) to identify the current tenden- cies Google Trends search was applied; 2) to search the databases and to identify the most active contributors (publishers and authors) the scholar API was used; 3) PRISMA-S checklist was applied to ensure the rigorousness of systematic literature review; 4) to expose the interdependence of the concepts a bibliometric analysis was conducted using VOSviewer 1.6.18 software; 5) finally this study proposes a comprehensive framework of employer branding. Findings – The research on employer branding has grown substantially in the past de- cades and various conceptual and empirical studies have advanced the knowledge of both employer and internal branding. Still, the progression in the literature is narrow due to complexity of the field. This study identifies the main dimensions of employer brand- ing and offers a comprehensive framework to systematize the current state of art. Research implications/limitations – The multidisciplinary nature of employer branding has led to a dispersed understanding of constructs and applications in the academic stud- ies. This study focuses on the marketing/branding perspective and does not consider the studies grounded purely in human resource management. Originality/value/contribution – This study increases our understanding of the current literature and new research trends in employer branding and employee-based brand equity. Additionally, it explains the link between EB and EBBE. While applying the recently developed scholar API and artificial intelligence empowered software to conduct the systematic review, this study creates a procedure that can be used by researchers in an array of fields. Keywords: employer brand, employee-based brand equity, scholar API-based systematic literature review. JEL Classification: M51, M31.

What does Google Trends reveal about the proportion of waterpipe users in the Brazilian population?

To analyze the relationship between internet search volume and the prevalence of waterpipe use among young Brazilians in 2019. This was a descriptive study with data from Brazil in 2019, using the relative search volume on waterpipes extracted from Google Trends and the proportion of waterpipe users aged between 15 and 24 years, as measured by the National Health Survey (Pesquisa Nacional de Saúde - PNS), and aged between 13 and 17 years, as measured by the National Adolescent School-based Health Survey (Pesquisa Nacional de Saúde do Escolar - PeNSE). The relationship was assessed by means of Spearman's correlation. The point prevalence of waterpipe use across the Brazilian Federative Units (FUs) showed a moderate (r = 0.51; PNS) to strong correlation (r = 0.74 and r = 0.80; PeNSE) with the relative search volume (p-value < 0.05). Google Trends can support the monitoring system on waterpipe use in the FUs, providing additional information to existing population-based surveys. The search volume for waterpipes by states in Brazil, as measured by Google Trends, showed a moderate to high correlation with the respective proportions of current use and experimentation of waterpipe among the adolescent/young adult population. The use of Google Trends as a support to the monitoring system for waterpipe consumption in Brazil warrants further exploration in terms of the validity of additional information to existing population surveys. Expanding the use of Google Trends searches to assess its potential in monitoring other health risk products and detecting (or predicting) incidence or seasonality of health-related events.

Фінансовий моніторинг сектору бухгалтерських послуг за міжнародними стандартами: новий виклик для професії бухгалтера

The growing risks of financing terrorism in the conditions of martial law necessitates the strengthening of financial monitoring. Accountants, business entities providing accounting services, and their related entities of audit activities are among the specially defined subjects of primary financial monitoring. Determining the level of riskiness of financial transactions is an essential function of an accountant. It, therefore, requires measures to increase the general and special competence of accounting specialists in financial monitoring. The article aims to determine the approaches and directions of regulatory and methodical support of financial monitoring of accountants as specially defined subjects following international standards. The requirements of FATF international standards and the national regulation system of specially defined professions regarding the fulfillment of financial monitoring requirements were analyzed. Special attention is paid to studying the risk-oriented approach in the financial monitoring system. A comparison was made of the results of sectoral risk assessments regarding the use by subjects of primary financial monitoring for money laundering according to the National risk assessments. The dynamics of the number of individual entrepreneurs who provide accounting services and are registered with the State Financial Monitoring Service of Ukraine were evaluated. With the help of the Google Trends search tool, the results of national risk assessments and the level of interest in financial monitoring carried out by accountants in different countries were evaluated. An example of a risk matrix of client-accounting service combinations was presented, which can be developed based on a risk analysis of the experience and activities of an individual accountant. It was noted that the dilemma of the choice of accountants between the interests of the client and the requirements of financial monitoring is related to the professional judgment of accounting specialists and their increased functional responsibility within the limits of current legislation and international standards.

Assessment of the relationship between Google Trends search data and national suicide rates in Turkey

Objective: The present study aimed to examine possible relationships between suicide-related terms obtained from Google Trends and actual suicide data and whether these relationships differ according to sex. Materials and Methods: The study period was from 2009 to 2019. In this study, suicide data were collected from the suicide statistics of the Turkish Statistical Institute (TUIK) for this timeframe. Google Trends was used to examine the search trends of suicide-related terms in Turkey. Pearson correlation analysis was used to find associations between the data obtained from TUIK and Google Trends. Finally, linear regression analysis was performed to identify predictors of monthly completed suicide rates in the general population. Results: In our study, 105 search terms obtained from Google Trends were examined to find associations with suicide rates in a specific timeframe. Among them, 31 terms had positive correlations, and nine had significant negative correlations. The terms "allergy" and "pain" were the most closely related to the overall suicide rates. Other significantly correlated terms were "how to commit suicide," "to commit suicide," "depression," and "hallucination." In addition, significantly different results were found for men and women. Conclusion: The present study showed that suicide-related terms obtained from Google Trends may predict actual suicide rates and may be an easy way to monitor suicide trends in Turkey. Future studies should use a more comprehensive internet network, including social media and other search engines, and consider other variables related to suicide to better understand this relationship.

Behaviour of Face Masks Search for Covid-19 Prevention in Indonesia: Trend and Policy Analysis

The studies on the Google searching behavior of face masks can be counted as evidence of how far the netizens’ enthusiasm for increasing their knowledge of the proper use of face masks. This current study aimed to analyze the trends in online searching behavior for face masks to prevent Covid-19 in Indonesia. This was conducted quantitatively utilizing Google search trends regarding the comparison between face mask types, including cloth masks, medical masks, and N95 masks in Indonesia after the first case of Covid-19. The mapping of sub-regions with the largest Google Trends filter category was also illustrated in this study. A time-trend analysis was conducted from Google data by describing several policy implementations, including social distancing and transition periods. A correlation analysis was performed by comparing the number of searches for face masks and the total number of Covid-19 cases. It was found that searching for all types of face masks increased in the early stage of the pandemic in Indonesia, while the trend later decreased. After implementing the social distancing policy, the results suggest that searches for cloth masks ranked highest. The increasing number of Covid-19 confirmed cases reduced the tendency of searching behavior for face masks in the category of cloth masks (r2 = -0.1730), medical masks (r2 = -0.1736), and N95 masks (r2 = -0.4329) at p-value &lt;0.05. This study illustrates that the existence of a mandatory policy to use masks will increase mask-seeking behavior in Indonesia.

State-Level COVID-19 Symptom Searches and Case Data: a Quantitative Analysis of Political Affiliation as a Predictor for Lag Time Using Google Trends and CDC Data.

Across each state. the emergence of the COVID-19 pandemic in the United States was marked by policies and rhetoric that often correspond to the political party in power. These diverging responses have sparked broad ongoing discussion about how the political leadership of a state may affect not only the COVID-19 case numbers in a given state, but also the subjective individual experience of the pandemic. This study leverages state-level data from Google Search Trends and CDC daily case data in order to investigate the temporal relationship between increases in relative search volume for COVID-19 symptoms and corresponding increases in case data. I aimed to identify whether there are state-level differences in patterns of lag time across each of the four spikes in the data (RQ1) and whether the political climate in a given state is associated with these differences (RQ2). Using publicly available data from Google Trends and the Centers for Disease Control and Prevention, linear mixed modeling was utilized to account for random state-level intercepts. Lag time was operationalized as number of days between a peak (a sustained increase before a sustained decline) in symptom search data and a corresponding spike in case data and was calculated manually for each of the four spikes in individual states. Google offers a dataset that tracks the relative search incidence of more than 400 potential COVID-19 symptoms, which is normalized on a 0-100 scale. I used the CDC's definition of the eleven most common COVID-19 symptoms and created a single construct variable that operationalizes symptom searches. To measure political climate, I considered the proportion of 2020 Trump popular votes in a state as well as a dummy variable for the political party that controls the governorship and a continuous variable measuring proportional party control of federal Congressional representatives. The strongest overall fit was for a linear mixed model that included proportion of 2020 Trump votes as the predictive variable of interest and included controls for mean daily cases and deaths as well as population. Additional political climate variables were discarded for lack of model fit. Findings indicated evidence that there are statistically-significant differences in lag time by state but that no individual variable measuring political climate was a statistically-significant predictor of these differences. Given that there will likely be future pandemics within this political climate, it is important to understand how political leadership affects perceptions of and corresponding responses to public health crises. Although this study did not fully model this relationship, I believe that future research can build on the state-level differences that I identified by approaching the analysis with a different theoretical model, method for calculating lag time, and/or level of geographic modeling.

Stock Movement Prediction Using Machine Learning Based on Technical Indicators and Google Trend Searches in Thailand

Machine learning for stock market prediction has recently been popular for identifying stock selection strategies and providing market insights. In this study, we adopted machine learning algorithms to analyze technical indicators, and Google Trends search terms based on the Thai stock market. This study uses three datasets, which are technical indicators, Google Trends search terms, and a combination of the two. The objectives were to study and identify the factors in stock selection, develop and evaluate portfolio selection models using keyword proxies from the three datasets mentioned, and compare the performance of the selected algorithms. In the prediction process, we discovered that the combination of technical indicators and Google Trends search terms while applying Logistic Regression, Random Forest, and Extreme Gradient Boosting (XGBoost) exhibited the highest ROC curves. For success prediction rate and annualized return, Random Forest and XGBoost were almost similar but still different. While XGBoost performs well during a period of market critical conditions (COVID-19), Random Forest performs marginally better than XGBoost during normal market conditions in terms of average success rate.

Depression and Anxiety on Twitter During the COVID-19 Stay-At-Home Period in 7 Major U.S. Cities

Although surveys are a well-established instrument to capture the population prevalence of mental health at a moment in time, public Twitter is a continuously available data source that can provide a broader window into population mental health. We characterized the relationship between COVID-19 case counts, stay-at-home orders because of COVID-19, and anxiety and depression in 7 major U.S. cities utilizing Twitter data. We collected 18 million Tweets from January to September 2019 (baseline) and 2020 from 7 U.S. cities with large populations and varied COVID-19 response protocols: Atlanta, Chicago, Houston, Los Angeles, Miami, New York, and Phoenix. We applied machine learning‒based language prediction models for depression and anxiety validated in previous work with Twitter data. As an alternative public big data source, we explored Google Trends data using search query frequencies. A qualitative evaluation of trends is presented. Twitter depression and anxiety scores were consistently elevated above their 2019 baselines across all the 7 locations. Twitter depression scores increased during the early phase of the pandemic, with a peak in early summer and a subsequent decline in late summer. The pattern of depression trends was aligned with national COVID-19 case trends rather than with trends in individual states. Anxiety was consistently and steadily elevated throughout the pandemic. Google search trends data showed noisy and inconsistent results. Our study shows the feasibility of using Twitter to capture trends of depression and anxiety during the COVID-19 public health crisis and suggests that social media data can supplement survey data to monitor long-term mental health trends.