Search results

While relevant research has considered aggregated data from mobile devices and personal computers (PCs), tourists’ search patterns on mobile devices and PCs differ significantly. This study aims to explore whether decomposing aggregated search queries based on the terminals from which these queries are generated can enhance tourism demand forecasting.

Mount Siguniang, a national geopark in China, is taken as a case study in this paper; another case, Kulangsu in China, is used as the robustness check. The authors decomposed the total Baidu search volume into searches from mobile devices and PCs. Weekly rolling forecasts were used to test the roles of decomposed and aggregated search queries in tourism demand forecasting.

Search queries generated from PCs can greatly improve forecasting performance compared to those from mobile devices and to aggregate search volumes from both terminals. Models incorporating search queries generated via multiple terminals did not necessarily outperform those incorporating search queries generated via a single type of terminal.

Major players in the tourism industry, including hotels, tourist attractions and airlines, can benefit from identifying effective search terminals to forecast tourism demand. Industry managers can also leverage search indices generated through effective terminals for more accurate demand forecasting, which can in turn inform strategic decision-making and operations management.

This study represents one of the earliest attempts to apply decomposed search query data generated via different terminals in tourism demand forecasting. It also enriches the literature on tourism demand forecasting using search engine data.

The purpose of this paper is to utilize co-query volumes of brands as relatedness measurement to understand the market structure and demonstrate the usefulness of brand relatedness via a real-world case.

Using brand relatedness measurement obtained using data from Google Trends as data inputs into a multidimensional scaling method, the market structure of the automobile industry is presented to reveal its competitive landscape. The relatedness with brands involved in product-harm crisis is further incorporated in empirical models to estimate the influence of crisis on future sales performance of each brand. A representative incident of a product-harm crisis in the automobile industry, which is the 2009 Toyota recall, is investigated. A panel regression analysis is conducted using US and world sales data.

The use of co-query as brand relatedness measurement is validated. Results indicate that brand relatedness with a brand under crisis is positively associated with future sales for both US and global market. Potential presence of negative spillovers from an affected brand to innocent brands sharing common traits such as same country of origin is shown.

The brand relatedness measured from co-query volumes is considered as a broad concept, which encompasses all associative relationships between two brands perceived by the consumers. This study contributes to the literature by clarifying the concept of brand relatedness and proposing a measure with readily accessible data. Compared to previous studies relying on a vast amount of online data, the proposed measure is proven to be efficient and enhance predictions about the future performance of brands in a turbulent market.

The purpose of this paper is to examine the feasibility of discovering business information from search engine query data. Specifically the study tried to determine whether search volumes of company names are correlated with the companies’ business performance and position data.

The top 50 US companies in the 2012 Fortune 500 list were included in the study. The following business performance and position data were collected: revenues, profits, assets, stockholders’ equity, profits as a percentage of revenues, and profits as a percentage of assets. Data on the search volumes of the company names were collected from Google Trends, which is based on search queries users enter into Google. Google Trends data were collected in the two scenarios of worldwide searches and US searches.

The study found significant correlations between search volume data and business performance and position data, suggesting that search engine query data can be used to discover business information. Google Trends’ worldwide search data were better than the US domestic search data for this purpose.

The study is limited to only one country and to one year of data.

Publicly available search engine query data such as those from Google Trends can be used to estimate business performance and position data which are not always publicly available. Search engine query data are timelier than business data.

This is the first study to establish a relationship between search engine query data and business performance and position data.

The 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.

The 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.

All 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.

To 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.

Search 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.

The 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.

The purpose of this paper is to analyze the relationship between new product diffusion and consumer internet search patterns using big data and to investigate whether such data can be used in forecasting new product diffusion.

This research proposes a new product diffusion model based on the Bass diffusion model by incorporating consumer internet search behavior. Actual data from search engine queries and new vehicle sales for each vehicle class and region are used to estimate the proposed model. Statistical analyses are used to interpret the estimated results, and the prediction performance of the proposed method is compared with other methods to validate the usefulness of data for internet search engine queries in forecasting new product diffusion.

The estimated coefficients of the proposed model provide a clear interpretation of the relationship between new product diffusion and internet search volume. In 83.62 percent of 218 cases, analyzing the internet search pattern data are significant to explain new product diffusion and that internet search volume helps to predict new product diffusion. Therefore, marketing that seeks to increase internet search volume could positively affect vehicle sales. In addition, the demand forecasting performance of the proposed diffusion model is superior to those of other models for both long-term and short-term predictions.

As search queries have only been available since 2004, comparisons with data from earlier years are not possible. The proposed model can be extended using other big data from additional sources.

This research directly demonstrates the relationship between new product diffusion and consumer internet search pattern and investigates whether internet search queries can be used to forecast new product diffusion by product type and region. Based on the estimated results, increasing internet search volume could positively affect vehicle sales across product types and regions. Because the proposed model had the best prediction power compared with the other considered models for all cases with large margins, it can be successfully utilized in forecasting demand for new products.

An ever-growing body of knowledge demonstrates the correlation among real-world phenomena and search query data issued on Google, as showed in the literature survey introduced in the following. The purpose of this paper is to introduce a pipeline, implemented as a web service, which, starting with recent Google Trends, allows a decision maker to monitor Twitter’s sentiment regarding these trends, enabling users to choose geographic areas for their monitors. In addition to the positive/negative sentiments about Google Trends, the pipeline offers the ability to view, on the same dashboard, the emotions that Google Trends triggers in the Twitter population. Such a set of tools, allows, as a whole, monitoring real-time on Twitter the feelings about Google Trends that would otherwise only fall into search statistics, even if useful. As a whole, the pipeline has no claim of prediction over the trends it tracks. Instead, it aims to provide a user with guidance about Google Trends, which, as the scientific literature demonstrates, is related to many real-world phenomena (e.g. epidemiology, economy, political science).

The proposed experimental framework allows the integration of Google search query data and Twitter social data. As new trends emerge in Google searches, the pipeline interrogates Twitter to track, also geographically, the feelings and emotions of Twitter users about new trends. The core of the pipeline is represented by a sentiment analysis framework that make use of a Bayesian machine learning device exploiting deep natural language processing modules to assign emotions and sentiment orientations to a collection of tweets geolocalized on the microblogging platform. The pipeline is accessible as a web service for any user authorized with credentials.

The employment of the pipeline for three different monitoring task (i.e. consumer electronics, healthcare, and politics) shows the plausibility of the proposed approach in order to measure social media sentiments and emotions concerning the trends emerged on Google searches.

The proposed approach aims to bridge the gap among Google search query data and sentiments that emerge on Twitter about these trends.

The purpose of this paper is to analyze the effect of investor sentiment, measured with Google internet search data, on volatility forecasts of the US REIT market.

The author uses the S&P US REIT index and collects search volume data from Google Trends for all US REIT. Two different Generalized Autoregressive Conditional Heteroskedastic models are then estimated, namely, the baseline model and the Google augmented model. Using these models, one-step-ahead forecasts are conducted and the forecast accuracies of both models are subsequently compared.

The empirical results reveal that search volume data can be used to predict volatility on the REIT market. Especially in periods of high volatility, Google augmented models outperform the baseline model.

The results imply that Google data can be used on the REIT market as a market indicator. Investors could use Google as an early warning system, especially in periods of high volatility.

This is the first paper to use Google search query data for volatility forecasts of the REIT market.

The purpose of this paper is to investigate whether there is a relationship between asset-specific online search interest and movements in the US REIT market.

The authors collect search volume (SV) data from “Google Trends” for a set of keywords representing the information demand of real estate (equity) investors. On this basis, the authors test hypothetical investment strategies based on changes in internet SV, to anticipate REIT market movements.

The results reveal that people’s information demand can indeed serve as a successful predictor for the US REIT market. Among other findings, evidence is provided that there is a significant relationship between asset-specific keywords and the US REIT market. Specifically, investment strategies based on weekly changes in Google SV would have outperformed a buy-and-hold strategy (0.1 percent p.a.) for the Morgan Stanley Capital International US REIT Index by a remarkable 15.4 percent p.a. between 2006 and 2013. Furthermore, the authors find that real-estate-related terms are more suitable than rather general, finance-related terms for predicting REIT market movements.

The findings should be of particular interest for REIT market investors, as the established relationships can potentially be utilized to anticipate short-term REIT market movements.

This is the first paper which applies Google search query data to the REIT market.

The purpose of the current study is to theorize and apply a socio-technological model – the powerful influence of social determinants in conditioning the effects of information attention on social outcomes. Fundamentally, this study is motivated by the idea that the social determinants of information flow can be used as a predictive tool to inform public socio-policy decisions.

This study draws upon digital disparity literature and uses publicly available Google search queries in exploring online information attention and its relationships to the HIV/AIDS diffusion in US cities. This study’s secondary data collected from extant sources is used to draw attention to a holistic urban ecology under which online search attention represents the variation of information access at the aggregate level.

The main finding shows that online information attention, as indicated by search trend, is far from being a simple predictor, but operates in complex interactions with existing social environments. A bivariate correlation between AIDS information search and AIDS diffusion rate was found to be significant. However, predictive multivariate models displayed robust effects of social contextual variables, such as income level and racial composition of cities, in moderating the effect of online search information flow.

The importance of these insights is discussed for reducing socio-health disparities at the macro-social level, and policymakers and health administrators are recommended to incubate supportive online infrastructure as an effective preventive measure at the time of a crisis.

The unique contribution of this study is the premise that looks at the aggregate-ecological contour of cities within which the potential benefits of information occur, instead of examining the isolated function of mediated information per se. In this vein, online information search, in lieu of the exposure to mass media message that is often measured via self-reported items, is a particularly unique and fruitful area of future inquiry that this study promotes.

The purpose of this paper is to propose a novel collaborative trend prediction method to estimate the status of trending topics by crowdsourcing the wisdom in web search engines. Government officials and decision makers can take advantage of the proposed method to effectively analyze various trending topics and make appropriate decisions in response to fast-changing national and international situations or popular opinions.

In this study, a crowdsourced-wisdom-based feature selection method was designed to select representative indicators showing trending topics and concerns of the general public. The authors also designed a novel prediction method to estimate the trending topic statuses by crowdsourcing public opinion in web search engines.

The authors’ proposed method achieved better results than traditional trend prediction methods and successfully predict trending topic statuses by using the crowdsourced wisdom of web search engines.

This paper proposes a novel collaborative trend prediction method and applied it to various trending topics. The experimental results show that the authors’ method can successfully estimate the trending topic statuses and outperform other baseline methods. To the best of the authors’ knowledge, this is the first such attempt to predict trending topic statuses by using the crowdsourced wisdom of web search engines.