No full-text available
To read the full-text of this research,
you can request a copy directly from the author.
Googling the present
Abstract
Google Trends data provides weekly reports on the number of search queries made by people in a geographical area and by category. As over three quarters of those who access the Internet regularly are looking for information on goods and services ‐ this information may be a useful indicator of economic activity. For example, the volume of queries may relate to future patterns of spending. This article investigates this use of Google Trends data for various search categories, looking at its correlation with official data on retail sales, property transactions, car registrations and foreign trips.
... It can be used to know, compare and predict the A systematic literature review behaviour and interests of the public on a certain subject, however, in existing papers the potentialities and limitations of the tool, as well as the purpose of the data and methodological choices of researchers, are still poorly understood and explored. Although there has been an increasing number of studies using this data in tourism and hospitality research (Chamberlin, 2010;Saidi et al., 2010;Gawlik et al., 2011;Artola and Galán, 2012;Artola et al., 2015), they are still relatively scarce, remaining largely unknown to practitioners and scholars. Therefore, this paper aims to systematically review the literature that used Google Insights for Search or Google Trends to identify the purpose and context of the data use, ascertaining the findings that are of particular relevance and reviewing the methodologic approaches. ...
... In only 33 per cent of the articles, the query category or subcategory was able to be identified: "travel" (Artola et al., 2015;Jackman and Naitram, 2015;Önder and Gunter, 2016;Rivera, 2016;Önder, 2017;Antolini and Grassini, 2018), Hong Kong (Choi and Varian, 2012), "hotels and accommodations" (Dinis et al., , 2017 and "food and drink" . One of the articles (Chamberlin, 2010) used more than one category ("travel", "vacation destinations", "hotels and accommodation", "air travel" and "cruises and charters"). ...
... Most studies select the search terms as the name of a country or city (Jackman and Naitram, 2015;Önder and Gunter, 2016;Önder, 2017), sometimes associated with accommodation (Dergiades et al., 2018) or the terms "tourism", "travel" or other elements of A systematic literature review the tourism supply, such as "restaurants" Artola et al., 2015;Kim and Malek, 2018). Choi and Varian (2012) and Chamberlin (2010) did not use any search term, considering only the category, while the rest chose only one service (e.g. hotel or restaurant). ...
Purpose
This paper aims to conduct a review of the literature published, between 2006 and 2018, that used search engine data on tourism and hospitality research, namely, Google Insights for Search and Google Trends. More specifically, it intends to identify the purpose and context of the data use, ascertaining the main findings and reviewing the methodological approaches.
Design/methodology/approach
A systematic literature review of Scopus indexed research has been carried out. Given the novelty of search engine data use in tourism and hospitality research and the relatively low number of search results in Scopus, other databases were used to broaden the scope of analysis, namely, EBSCO and Google Scholar. The papers selected were subjected to content and statistical analyses.
Findings
Google Trends data use in tourism and hospitality research has increased significantly from 2012 to 2017, mainly for tourism forecasting/nowcasting; knowing the interest of users’ searches for tourist attractions or destinations; showing the relationship between the official tourism statistics and the search volume index of Google Trends; and estimating the effect of one event on tourism demand. The categories and search terms used vary with the purpose of the study; however, they mostly focus on the travel category and use the country as the search term.
Originality/value
Google Trends has been increasingly used in research publications in tourism and hospitality, but the range of its applications and methods used has not yet been reviewed. Therefore, a systematic review of the existing literature increases awareness of its potential uses in tourism and hospitality research and facilitates a better understanding of its strengths and weaknesses as a research tool.
... 12. For example, see the comments of Chamberlin (2010), Schmidt & Vosen (2012) and Bortoli & Combes (2015). 13. ...
... 13. For example, see the comments of Artola & Galen (2012), Askitas & Zimmermann(2015), Chamberlin (2010) and Tkacz (2013). & Marcuccio (2009), Schmidt & Vosen (2011). ...
Abstract – This paper provides a discussion of the use of Big Data for economic forecasting and a critical review of recent empirical studies drawing on Big Data sources, including those using internet search, social media and financial transactions related data. A broad conclusion is that whilst Big Data sources may provide new and unique insights into high frequency macroeconomic activities, their uses for macroeconomic forecasting are relatively limited and have
met with varying degrees of success. Specific issues arise from the limitations of these data sets, the qualitative nature of the information they incorporate and the empirical testing frameworks used. The most successful applications appear to be those which seek to embed this class of information within a coherent economic framework, as opposed to a naïve black box statistical approach. This suggests that future work using Big Data should focus on improving the quality
and accessibility of the relevant data sets and in developing more appropriate economic modelling frameworks for their future use.
JEL Classification: C53, E27, E37
Keywords: Big Data, internet search, short‑term, macroeconomic forecasting, models, nowcasting
... The GT data presents a great potential for tourism management in terms of supporting the decision making process as well as for tourism policy making, since the data is available almost in real time and several studies (see for example Choi & Varian, 2009;Chamberlin, 2010;Smith & White, 2011) concluded that the online pattern behaviour of the consumer is very much related with what happens in reality. GT data may reflect the interests and desires of the tourist consumer with the advantage of being available on time to all tourism agents. ...
... Most publications fall under the healthcare (see for example Ginsberg et al., 2009;Yang et al., 2011;Dehkordy et al., 2014) and economy (see for example Choi & Varian, 2009ª;Schmidt & Vosen, 2009;Baker & Fradkin, 2011;Bughin, 2015) fields, but work was also performed in finance (Smith, 2012), communication and marketing (Granka, 2010); religion (Scheitle, 2011); education (Vaughan-Frias et al., 2013), and cinema (Judge & Hand, 2010). The hospitality and tourism sector was analysed in the studies developed by Chamberlin, 2010;Choi and Varian, 2009b;Shimshoni et al., 2009;Suhoy, 2009;Smith and White, 2011;Artola and Galán, 2012;Gawlik et al., 2011;Saidi et al., 2010;Pan et al., 2012;Concha et al., 2015;Kallasidis, 2015;Bangwayo-Skeete and Skeete (2015); Dinis et al. 2013Dinis et al. , 2015; Jackman and Naitram, 2015); Yang et al. (2015); Rivera (2016); and Li et al., 2017). ...
Over the last years, we observed an exponential growth in the
number of tourism consumers that use the Internet as a source of
information during a destination selection process. Google Trends
is a tool that displays data, almost in real time, on the interest of
people in a particular topic based on search trends. This paper
demonstrates that Google Trends is a tool that can provide useful
and relevant information about the interests of individuals in
relation to domestic tourism destinations at national and regional
levels. Our findings indicate that overnights spent in hotel
establishments by the residents in Portugal are strongly correlated
with the Google index, mainly in mainland Portugal, Alentejo and
Algarve regions, and that the results improve when more
municipalities names and the national or the regional tourism
brands are included as search terms.
... developed a more revised and even shorter scale or instrument with a basic factor structure. They developed one of the latest instruments having four factors ATMI consisting of 40-items, a 5-points Likert scale ranging from 'strongly agree' to 'strongly disagree'(Chamberlin, 2010). Both positive and negative items were incorporated in the instrument. ...
The study entitled "Exploring Students’ Attitudes, Learning Behaviors, and their
effects on Mathematics Achievements" basically aims to analyse the grade X students' attitudes levels; attitudes influence on the creation of learning behaviors, and ultimate effects on students' achievements in mathematics and establish their relationships as one of the achievement models. Bandura's social cognitive theory and Bem's self-perception theory are major theoretical referents for this study. The study has employed a concurrent embedded mixed-method research design with a sample of 540 grade X students from 12 community schools in Nepal. The quantitative data were collected using attitude towards mathematics inventory, classroom learning behavior self-assessment inventory, and mathematics achievement test, and analyzed using statistical tools such as mean, standard deviation, correlation, and regression. The qualitative data related to learning behavior was collected through class observation and semi-structured interviews. The qualitative information was analysed thematically for drawing the categories and embedded with the results of the quantitative data iv while analyzing and interpreting. As results of the study, most of the students' levels of attitudes and learning behaviors were positive whereas the achievement level of the
students was found medium and differed between ecological regions and rural-urban backgrounds. The result refutes that rural student lagged behind their urban
counterparts in achievement, and genderwise achievement difference was statistically insignificant. The majority of the students preferred learning mathematics by using more behaviorist attributes and credited the teacher for their success. Overall, the effects of the students'attitudes and learning behaviors on achievements were found positive and statistically significant. The positive correlations between attitudes, learning behaviors, and achievements, suggest that a positive attitude towards mathematics causes positive learning behaviors leading to higher achievements and vice-versa.
... Third, and probably most importantly, they have been show to track well the variables of interest. In addition to the detection of influenza epidemics (Ginsberg et al., 2009), Google Trends data have been successfully used to predict (un)employment (Askitas and Zimmermann, 2009;Fondeur and Karam, 2013;D'Amuri and Marcucci, 2017;Naccarato et al., 2018;Niesert et al., 2020, Mulero andGarcía-Hiernaux, 2020;Borup and Schütte, Forthcoming), inflation (Guzman, 2011), consumer behaviour (Goel et al., 2010;Chamberlin, 2010), car sales (Du and Kamakura, 2012;Fantazzini and Toktamysova, 2015), tourism (Camacho and Pacce, 2018), oil consumption (Yu et al., 2019), warning signs of stock market moves (Preis et al., 2013) and more general macroeconomic aggregates (Koop and Onorante, 2019;Ferrara and Simoni, 2019). 9 Given their power, internet searches serve as a measure of economic sentiment. ...
The COVID-19 pandemic has inflicted an economic hardship unprecedented for the modern age. In this paper, we show that the health crisis and ensuing lockdown, came with an unseen shift in households’ economic sentiment. First, using a European dataset of country-level and regional internet searches, we document a substantial increase in people's business cycle related searches in the months following the coronavirus outbreak. People's unemployment concerns jumped to levels well-above those during the Great Recession. Second, we observe a significant, coinciding slowdown in labour markets and consumption. Third, our analysis shows that the ensuing shift in sentiment was significantly more outspoken in those EU countries hit hardest in economic terms. Finally, we show that unprecedented fiscal policy actions, such as the short-time work schemes implemented or reformed at the onset of the COVID-crisis, however, have not eased economic sentiment.
... Its accuracy and validity in forecastings [33][34][35][36][37], predictions [38,39], nowcasting [40], and in examining human behavior in general has been highlighted. Economics and finance are among the main fields where online search traffic data from Google have been employed to analyze and predict behavioral variations, mainly for examining behavioral changes in stock market related issues [15,[41][42][43][44][45][46][47], currencies [48,49], in general consumption [50] and sales [51][52][53], in general applications for advertising, marketing, and management [54,55], or even examining the effect of taxation in the public's view of the future [56]. ...
During the last decade, the use of online search traffic data is becoming popular in examining, analyzing, and predicting human behavior, with Google Trends being a popular tool in monitoring and analyzing the users’ online search patterns in several research areas, like health, medicine, politics, economics, and finance. Towards the direction of exploring the Sterling Pound’s predictability, we employ Google Trends data from the last 5 years (March 1st, 2015 to February 29th, 2020) and perform predict- ability analysis on the Pound’s exchange rates to Euro and Dollar. The period selected includes the 2016 UK referendum as well as the actual Brexit day (January 31st, 2020), with the analysis aiming at analyzing the Pound’s relationships with Google query data on Pound-related keywords and topics. A quantile dependence method is employed, i.e., cross-quantilograms, to test for directional predictability from Google Trends data to the Pound’s exchange rates for lags from zero to 30 (in weeks). The results indicate that statistically significant quantile dependencies exist between Google query data and the Pound’s exchange rates, which point to the direction of one of the main implications in this field, that is to examine whether the movements in one economic variable can cause reactions in other economic variables.
... In this study, the tourism arrival volume is collected monthly from reliable organizations (e.g., government agencies and departments). Various SII data are extracted through major search engine platforms, such as Google Trends and Baidu Index (Chamberlin 2010). Travelers often use search engines to obtain tourism-related information (Fesenmaier et al. 2011), such as weather, food, and transportation. ...
Tourism planners rely on accurate demand forecasting. However, despite numerous advancements, crucial methodological issues remain unaddressed. This study aims to further improve the modeling accuracy and advance the artificial intelligence (AI)-based tourism demand forecasting methods. Deep learning models that predict tourism demand are often highly complex and encounter overfitting, which is mainly caused by two underlying problems: (1) access to limited data volumes and (2) additional explanatory variable requirement. To address these issues, we use a decomposition method that achieves high accuracy in short- and long-term AI-based forecasting models. The proposed method effectively decomposes the data and increases accuracy without additional data requirement. In conclusion, this study alleviates the overfitting issue and provides a methodological contribution by proposing a highly accurate deep learning method for AI-based tourism demand modeling.
... The use of Google search data for the prediction of car sales or car registrations has raised significant attention in the literature. Chamberlin (2010), Seebach et al. (2011), Du and Kamakura (2012), and Choi and Varian (2012) were the first who examined the predictive power of Google search data in the context of car sales [35], [14], [36], [33]. They conclude that Google data reflect changes in the volume of car sales and appears to be an appropriate data source for prediction models. ...
... The data is offered on a weekly basis and has been aggregated to monthly for our analysis. For further discussion on the aggregation methodologies see Chamberlin (2010) and Xu & Reed (2017). ...
Although there exists sizeable literature studying the impact of tourists’ risk perceptions, less attention has been devoted to studying the difference between the impact of measured and perceived risks. We apply a panel vector autoregression (PVAR) to a dataset of inbound tourism in Shanghai, China to study the dynamic relationship between pollution and tourism. Particularly, we distinguish between measured pollution level and perceived pollution (measured by Google Trends search data) to test which one has the larger impact on tourists’ decisions. Our results show that pollution (measured or perceived) can be a powerful deterrent to potential international tourists.
Here is the link to the full-text: https://www.tandfonline.com/eprint/aiTJS5M7qhM2vKVT5qqb/full
... Choi and Varian (2012), for instance, show how Google Trends matches the survey-based Australian Consumer Confidence index and Scott and Varian (2015) reproduce the same results for the University of Michigan Consumer Confidence Index time series. Chamberlin (2010) explores Google trends correlations with U.K. Office of National Statistics official data on retail sales, property transactions, car registrations, and foreign trips. At the same time Google ...
Survey data have recently been compared and contrasted with so-called “Big Data” and some observers have speculated about how Big Data may eliminate the need for survey research. While both Big Data and survey research have a lot to offer, very little work has examined the ways that they may best be used together to provide richer datasets. This chapter offers a broad definition of Big Data and proposes a framework for understanding how the benefits and error properties of Big Data and surveys may be leveraged in ways that are complementary. This chapter presents several of the opportunities and challenges that may be faced by those attempting to bring these different sources of data together.
... Guzman, 2011) to more disaggregated variables such as retail sales, property transactions, car registrations, and foreign trips (e.g. Chamberlain, 2010), automobile purchases (Carriere-Swallow and Labbe, 2013), and cinema admissions (Hand and Judge, 2012). To our knowledge, our paper is the first to use web search data to construct an indicator of a change in law. ...
We investigate whether the February 2012 amendments to the Check Law in Turkey that replaced imprisonment with administrative fines for issuing bad checks were a driver of the surge in bad checks since late 2011. As the change in the law was foreseen, we argue that check issuance behavior was altered before the new law became official. To capture this, we use the cumulative volume of internet search queries related to the upcoming legal change. We find that, unlike the case during the global financial crisis of 2008–09, the surge in bad checks occurring in 2011–12 cannot be accounted for by the state of the economic environment unless the effects of the February 2012 law change are also controlled for. We also provide evidence that economic agents adjust fairly rapidly to the legal change, which reverses the surge in bad checks within a year. Overall, our findings suggest that sanctions need not be harsh to deter non-violent offenses provided that appropriate institutional structures are in place.
... To this end, many authors ( Varian, 2009a, 2009b; D'Amuri, 2009;, 2010; Goel et al., 2010) propose the use of online search data to improving the nowcasting and forecasting of official economic indicators, which are normally published a certain time after the period to which they refer. In particular, Choi and Varian (2009a) introduce the term " nowcasting " or " predicting the present " in suggesting the use of for which the gathering of data takes place all through the month in question. ...
... In an updated version of their first article, they demonstrate similar results for the prediction of vehicles and motor parts sales, initial claims for unemployment benefits, travel and consumer confidence (Choi and Varian, 2012). Chamberlin (2010) replicates Choi and Varian's research on UK data and confirms the leading characteristics and forecasting abilities of Google search indices. He points to the problem that the large overall rise in total searches over the last few years has led to a falling share of specific searches, which possibly stunts the upward growth of search indices, but reinforces downward movements. ...
Purpose
– The purpose of this paper is to examine internet search query data provided by “Google Trends”, with respect to its ability to serve as a sentiment indicator and improve commercial real estate forecasting models for transactions and price indices.
Design/methodology/approach
– This paper examines internet search query data provided by “Google Trends”, with respect to its ability to serve as a sentiment indicator and improve commercial real estate forecasting models for transactions and price indices.
Findings
– The empirical results show that all models augmented with Google data, combining both macro and search data, significantly outperform baseline models which abandon internet search data. Models based on Google data alone, outperform the baseline models in all cases. The models achieve a reduction over the baseline models of the mean squared forecasting error for transactions and prices of up to 35 and 54 per cent, respectively.
Practical implications
– The results suggest that Google data can serve as an early market indicator. The findings of this study suggest that the inclusion of Google search data in forecasting models can improve forecast accuracy significantly. This implies that commercial real estate forecasters should consider incorporating this free and timely data set into their market forecasts or when performing plausibility checks for future investment decisions.
Originality/value
– This is the first paper applying Google search query data to the commercial real estate sector.
The study sets out to make evident the existences of segmentation of the Islamic finance body of knowledge (BOK). The segmentation results from the combination of dependency of Islamic finance researchers on google and using Islamic finance terms (IFTs) as search keywords. The study defines Islamic finance terminology as the Arabic/Islamic terms unique to Islamic finance literature written in English, e.g. Shariah. A distinctive feature of Islamic finance terms is that a single term can have many spelling variations. Firstly, to validate the presence of BOK segmentation, we investigated spelling variation among IFTs through a variation analysis among a sample of chosen terms. Secondly, we established the dependency of producers and users of Islamic finance literature on online resources and especially Google and Google Scholar using a survey. Lastly, we observed segmentation in the BOK by examining the absence of search results that overlap for IFTs and their variations. The spelling variations among our samples ranged from zero to eight with an average of (4.8) spelling variations per IFT. The dependency rate on online resources among our respondents was (99%) on Google, while Google Scholar scored (98%). The search results’ analysis yielded zero overlaps between the search results confirming the actuality of segmentation. Keywords: Segmentation, Islamic Finance Terms, Google, Body of Knowledge, Spelling Variation.
Tourism data is one of the strategic data in Indonesia. In addition, tourism is one of the ten priority programs of national development planning in Indonesia. BPS-Statistics Indonesia has collected data related to tourism demand in Indonesia, but these data have different time period. Several data can be provided monthly, while the other data can be provided annually. However, accurate and real time tourism data are needed for effective policy making. In this era, all of information about tourism destination or accommodation can be gotten easily through internet, especially information from Google search engine, such as information about tourism places, flights, hotels, and ticket for tourism attractions. Since 2004, Google has provided the information of user behavior through Google Trends tool. This paper aims to analyze and compare the patterns of tourism demand in Indonesia from Google Trends data with tourism statistics from BPS-Statistics Indonesia. In order to understand tourism demand in Indonesia, we used Google Trends data on a set of queries related to tourism. This paper shows that the search intensity of related queries provides the pattern of predicted tourism demand in Indonesia. We evaluated the prediction result by comparing several time series models. Furthermore, we compared and correlated the Google Trends data with official data. The result shows that Google Trends data and tourism statistics have similar pattern when there were disasters. The result also shows that Google Trends data has correlation with official data and produced accurate prediction of tourism demand in Indonesia. Therefore, Google Trends data can be used to predict and understand the pattern of tourism demand in Indonesia.
Purpose
This study aims to explore when and for what purpose is social media used by tourists in their decision-making; and to further interpret the nature of such usage.
Design/methodology/approach
An online questionnaire was administered to 530 Indians who qualified as recent tourists and social media users. Partial least square structural equation modeling (PLS-SEM) is used to analyse hypothesised relationships; the results helped us to unveil the tourist social media cycle which is a conceptual model of the results obtained.
Findings
PLS-SEM results indicate that social media is predominantly used in the pre-travel stage for evaluation purposes, during travel stage for purchase purposes and post-travel stage for post-purchase behaviour. Also, it is noted that social media use by a tourist is an ongoing process, and thus, a conceptual model in the form of tourist social media cycle is unveiled.
Practical implications
This study reveals the unique behaviour of Indian tourists with respect to using social media for travel decision-making, which establishes a different perspective of understanding and further strategizing social media’s use in tourism for a developing nation. Also, the tourist social media cycle stresses on the importance of social media as a digital repository where continuously the user-generated content is used by self (existing) or “others” (potential tourists).
Originality/value
To the best of the author’s knowledge, this is the first study that addresses the population and knowledge gap of understanding social media–based tourist behaviour providing a perspective of a developing nation, specifically India. Further, it unveils the nature of social media use by tourist in the form of a first ever tourist social media cycle.
Dynamic model averaging (DMA) has become a widely used estimation technique in macroeconomic applications. Since its introduction in econom(etr)ics by Gary Koop and Dimitris Korobilis in 2009, applications of DMA have increased in unimaginable ways. Besides applying the original (univariate) framework suggested by Koop and Korobilis on the data of interest, for example, the inflation rate of the country of choice or return on the rate of equity, practitioners have been able to use DMA‐based techniques to extend current models, thereby further improving out‐of‐sample forecast accuracy, overcome computational bottlenecks, and even help improve our understanding of economic phenomena by introducing new models. These include using Google search data in combination with the predictive likelihood to govern switching between different predictive regressions in the model set or specifying large time‐varying parameter vector autoregressions that can be estimated without resorting to simulation‐based techniques. This study provides an overview of DMA techniques and the ways in which they have evolved since the contribution of Koop and Korobilis.
The impact of social media on the travel industry is predicted to be tremendous, especially on its holiday travel segment. Although there is a plethora of studies concentrating on the role and impact of social media in travel related decisions, most of them are medium and community specific, or focus on a specific stage of the decision making or the travel planning process. This paper presents a comprehensive view of the role and impact of social media on the travel planning process: before, during and after the trip, providing insights on usage levels, scope of use, level of influence, and trust. The study was conducted through an online structured questionnaire on a sample of 346 members of an online panel of internet users from Russia and the other Former Soviet Union (FSU) Republics who had been on holidays in the previous 12 months. Findings reveal that social media are predominantly used after holidays for experience sharing. It is also shown that there is a strong correlation between level of influence from social media and changes made to holiday plans. Moreover, it is revealed that user-generated content is more trusted than official tourism websites, travel agents, and mass media advertising.
Introduction: Breast milk is planned for nursing young ones and therefore considered as nature’s most precious gift to humankind. However, despite strong evidences in support of breastfeeding, its prevalence has remained low worldwide. Objective: The objective of this study is to explore the knowledge, attitude, and perception toward breastfeeding among primigravida mothers and factors determining them. Materials and Methods: The study was conducted over 18 months on primigravida mothers admitted in postnatal care ward of tertiary care center of a medical college. Questionnaires were filled by mothers of newborns about various domains such as initiation of feeding, latching, maternal position during breastfeeding, prelacteal, colostrum, exclusive breastfeeding (EBF), and feeding at public places. Results: A total of 260 women aged 21–25 years were included in the study. Most of them were the housewives (81.5%), Hindu (95.4%), living in joint family (55.8%), and living in urban area (73.8%). About 90.4% initiated breastfeeding immediately after delivery and mothers have good knowledge on breastfeeding (81.1%). Mothers living in joint family had significantly more knowledge about the EBF and importance of colostrum. The source of their knowledge regarding breastfeeding was mostly medical staff (95.4%). Conclusion: The present study found that mothers had satisfactory knowledge regarding breastfeeding. Proper counseling and all level of support should be given to primigravida mothers, and breastfeeding practices can be increased by strengthening the existing program through media support and by removing social taboo regarding breastfeeding.
This chapter presents a methodology for building composite indicators to measure the public online search interest by tourist destinations. As an example, we have applied it to measure the online search interest of foreign markets, namely Spain, the UK and Germany by Portugal as a tourist destination. In order to build the composite indicators we extracted weekly and during one year, data from the Google Trends (GT) tool, based on the set of search terms chosen to define the destination Portugal. The composite indicators proposed are based on the Tourism Satellite Accounts (TSA) conceptual framework and weighted by the arithmetic mean of seven primary indicators composed by fifteen sub-indicators. The results indicate the interest and popularity of Spanish, British and German foreigners by tourism in Portugal and country specific touristic products. The obtained results contribute definitively to support and help Destination Management Organizations (DMO) enabling timely decisions.
This study aims to examine whether decomposed search engine data can be used to improve the forecasting accuracy of tourism demand. The methodology was applied to predict monthly tourist arrivals from nine countries to Hong Kong. Search engine data from Google Trends were first decomposed into different components using an ensemble empirical mode decomposition method and then the cyclical components were examined through statistical analysis. Forecasting models with rolling window estimation were implemented to predict the tourist arrivals to Hong Kong. Results indicate the proposed methodology can outperform the benchmark model in the out-of-sample forecasting evaluation of Choi and Varian (2012). The findings also demonstrate that our proposed methodology is superior in forecasting turning points. This study proposes a unique decomposition-based perspective on tourism forecasting using online search engine data.
Purpose
The purpose of this paper is to use data mined from Google Trends, in order to predict the unemployment rate prevailing among Canadians between 25 and 44 years of age.
Design/methodology/approach
Based on a theoretical framework, this study argues that the intensity of online leisure activities is likely to improve the predictive power of unemployment forecasting models.
Findings
Mining the corresponding data from Google Trends, the analysis indicates that prediction models including variables which reflect online leisure activities outperform those solely based on the intensity of online job search. The paper also outlines the most propitious ways of mining data from Google Trends. The implications for research and policy are discussed.
Originality/value
This paper, for the first time, augments the forecasting models with data on the intensity of online leisure activities, in order to predict the Canadian unemployment rate.
The increased availability of online information in recent years has aroused interest in the possibility of deriving indications for many kinds of phenomena. In the more specific economic and statistical context, numerous studies suggest the use of online search data to improve the forecasting and nowcasting of official economic indicators with a view to increasing the promptness of their circulation. The purpose of this work is to investigate if the use of big data can improve the forecasting of the youth unemployment rate - estimated in Italy on a monthly basis by the Italian National Institute of Statistics - by means of time series models. The time series used are those of the Google Trends query share for the keyword offerte di lavoro (job offers) and the official labour force survey data for the Italian youth unemployment rate since 2004. Two different models are estimated: an ARIMA model using only the official youth unemployment rate series and a VAR model combining the former series with the Google Trends query share. The results show that the use of Google Trends information leads to an average decrease in the forecast error.
The demand and interest in big data analytics are increasing rapidly. The concepts around big data include not only existing structured data, but also various kinds of unstructured data such as text, images, videos, and logs. Among the various types of unstructured data, text data have gained particular attention because it is the most representative method to describe and deliver information. Text analysis is generally performed in the following order: document collection, parsing and filtering, structuring, frequency analysis, and similarity analysis. The results of the analysis can be displayed through word cloud, word network, topic modeling, document classification, and semantic analysis. Notably, there is an increasing demand to identify trending topics from the rapidly increasing text data generated through various social media. Thus, research on and applications of topic modeling have been actively carried out in various fields since topic modeling is able to extract the core topics from a huge amount of unstructured text documents and provide the document groups for each different topic. In this paper, we review the major techniques and research trends of text analysis. Further, we also introduce some cases of applications that solve the problems in various fields by using topic modeling.
Purpose—The purpose of this paper is to explore the Google Trends (GT) data in order to understand the behavior and interests of British tourists in Portugal as a tourist destination and to verify if the GT data correlates with the tourism official data of Portugal. Furthermore, it will investigate if GT data can improve forecasts on the arrival of British tourists to Portugal. Design/methodology/approach—We used GT data on a set of search terms to predict the demand for hotel establishments by UK residents in Portugal and employed the Autoregressive Integrated Moving Average (ARIMA) model and Transfer Function (TF) to evaluate the usefulness of this data. Furthermore, we correlated the GT data with official tourism data of Portugal. Findings—The TF models outperformed their ARIMA counterparts, meaning that the TF models which considered the GT index produced more accurate forecasts. Practical implications—The paper contributes to increase the knowledge on the potential of Google-based search data in order to understand the behaviour patterns of predicted British travelers to Portugal and help to predict the British tourist inflows to Portugal. Originality/value—The paper is novel because it is the first in the field of hospitality and tourism to predict British tourists inflows to Portugal and it is a unique paper in this area that used several keywords in order to define a tourist destination.
Nos últimos anos os agentes de turismo têm manifestado necessidade de informação atualizada, pertinente e atempada que os auxilie no processo de tomada de decisão. Uma das áreas onde se verifica maiores lacunas de informação é sobre o comportamento do consumidor em turismo e os hábitos de consumo das viagens turísticas que se tem vindo a alterar significativamente nos últimos tempos. A adoção e crescente utilização da Internet tem contribuído em parte para essas alterações. Nos dias de hoje, o consumidor antes de decidir adquirir determinado serviço ou produto turístico pesquisa informação na Internet recorrendo para tal aos motores de busca. O Google é o motor de busca que lidera o mercado das pesquisas a nível mundial e o Google Trends (GT) é uma ferramenta disponibilizada gratuitamente pela mesma empresa que fornece dados, quase em tempo real, sobre o interesse ao longo do tempo do público que procura informação no Google. O objetivo deste artigo é mostrar que os dados do GT podem ser de grande utilidade para os agentes de turismo pois fornecem informação comparativa sobre o interesse dos indivíduos por determinadas locais, recursos ou eventos turísticos e seus concorrentes. Os resultados obtidos mostram que o interesse e comportamento dos consumidores de turismo apresenta padrões semelhantes aos verificados na realidade, e que o GT fornece informação comparativa quase em tempo real relevante para os agentes de turismo.
This study follows the stream of research identifying sentiment trends by using online search query data. The potential of the Google data series for the U.K. housing market on a disaggregated level is analyzed in a panel VAR framework. Our findings confirm research based on U.S. samples that Google subcategories, especially "Real Estate Agency," serve as an indicator of transaction volume. Our main contribution is the detection of contrary dynamics within the Google "Home Financing" subcategory, which to date yields empirically mixed evidence (Hohenstatt, Kaesbauer, and Schaefers, 2011). Sensitivity analysis yields that transaction volume responds twice as sensitively as house prices due to a standard deviation increase of the stress indicator. Most importantly, the derived stress indicator of housing market (un-)soundness works at least as well as in downturns, as opposed to "Real Estate Agency," which is primarily a suitable indicator during upturns.
Internet search data could be a useful source of information for policymakers when formulating decisions based on their understanding of the current economic environment. This paper builds on earlier literature via a structured value assessment of the data provided by Google Trends. This is done through two empirical exercises related to the forecasting of changes in UK unemployment. Firstly, economic intuition provides the basis for search term selection, with a resulting Google indicator tested alongside survey-based variables in a traditional forecasting environment. Secondly, this environment is expanded into a pseudo-time nowcasting framework which provides the backdrop for assessing the timing advantage that Google data have over surveys. The framework is underpinned by a MIDAS regression which allows, for the first time, the easy incorporation of Internet search data at its true sampling rate into a nowcast model for predicting unemployment. Copyright
In a sector strongly dependent on information as is the case of tourism, the timely knowledge of
consumer behaviour enables making well-considered decisions and less uncertainty. Nowadays, the
act of searching on the Internet about a particular subject before decision-making is part of the
individuals’ daily lives. The Google Trends tool provides real time aggregated data on the online
individuals’ interest based on the carried out search queries on Google. The objective of this paper is
to show that Google Trends can provide comparative information about the individuals’ interest in
relation to Portugal tourism regional areas and in particular, on the tourist destination "Algarve", and
also between its competing tourist destinations. The results show that the tool can contribute to the
knowledge of the individuals’ interests in relation to regional tourist destinations, information
considered of great interest for Destination Management Organizations.
The web currently carries vast amounts of information as to what consumers search for, comment on, and purchase in the real economy. This paper leverages a mash-up of online Google search queries and of social media comments (from Twitter, Facebook and other blogs) to “nowcast” the product sales evolution of the major telecom companies in Belgium. A few findings stand out. With an Error Correction Mechanism (ECM) model of sales dynamics, a co-integration relationship prevails between social media valence (respectively, between search query) and telecom operators’ sales for both internet and digital television access provision (respectively, for fixed telephony provision). Elasticity estimates on sales are relatively larger for valence than for search queries. The ECM model with nowcasting variables improves telecom sales forecasts by about 25 % versus a naïve autoregressive sales model.
The impact of social media on the travel industry is predicted to be tremendous, especially on its holiday travel segment. Although there is a plethora of studies concentrating on the role and impact of social media in travel related decisions, most of them are medium and community specific, or focus on a specific stage of the decision making or the travel planning process. This paper presents a comprehensive view of the role and impact of social media on the travel planning process: before, during and after the trip, providing insights on usage levels, scope of use, level of influence, and trust. The study was conducted through an online structured questionnaire on a sample of 346 members of an online panel of internet users from Russia and the other Former Soviet Union (FSU) Republics who had been on holidays in the previous 12 months. Findings reveal that social media are predominantly used after holidays for experience sharing. It is also shown that there is a strong correlation between level of influence from social media and changes made to holiday plans. Moreover, it is revealed that user-generated content is more trusted than official tourism websites, travel agents, and mass media advertising.
As more and more daily activities take place online, data on internet behaviour is becoming a key information source. In this sense, several papers have explored the usefulness of internet search data in order to improve the nowcasting and forecasting of economic indicators. Special attention has been paid to predicting unemployment. Nonetheless, most of the empirical evidence on this field has focused in countries with low/moderate rates of unemployment.
This paper follows this line of research and explores the use of Google Trends data in order to improve the forecasting of the figures of unemployment in Spain. This country reveals as a very interesting case due to the sharp increases in unemployment caused by the economic crisis.
With the aim of providing an extensive approach on the Spanish unemployment, we use ARIMA models, also introducing as explanatory variables the Google searches for “job offers” and a business confidence indicator referred to employment perspectives. In this way we combine the time series perspective with qualitative indicators from the supply and the demand sides, leading to a more comprehensive description and also improving forecasting performance.
This paper reviews some of the applications that use the vast swathes of information provided by Internet user searches for economic analysis and forecasting. This enormous volume of information, available in real time, can be handled by analysts thanks to statistical tools such as “Google Insights for Search”, which allow trends in different areas of interest to be classified and evaluated. Previous work focused predominantly on the labour market, on the housing market, on retail sales and on consumer confidence. This paper presents a very specific application for the Spanish economy: British tourist inflows to Spain (the Spanish tourist industry's main customers). The improvement in the forecasting provided by the short-term models that include the G-indicator depends on the benchmark model. This does, however, allow an adjusted indicator of the inflow of British tourists to be obtained with a lead of almost one month. This is but an initial step in the use of on-line searches for constructing leading indicators of economic activity. Other applications to be explored are car sales, consumer confidence and house purchases. The chief characteristic of these procedures is that, with time and the continuous growth of Internet use, results can only improve in the future. It should nonetheless be recalled that the construction of these G-indicators requires caution so as to avoid mistakes arising, inter alia, from the different use of language in different countries. Not taking due caution and blindly confiding in these indicators may lead to erroneous results being obtained.
Can Google queries help predict economic activity?The answer depends on what you mean by "predict." Google Trends and Google Insights for Search provide a real time report on query volume, while economic data is typically released several days after the close of the month. Given this time lag, it is not implausible that Google queries in a category like "Automotive/Vehicle Shopping" during the first few weeks of March may help predict what actual March automotive sales will be like when the official data is released halfway through April.That famous economist Yogi Berra once said "It's tough to make predictions, especially about the future." This inspired our approach: let us lower the bar and just try to predict the present. Our work to date is summarized in a paper called Predicting the Present with Google Trends. We find that Google Trends data can help improve forecasts of the current level of activity for a number of different economic time series, including automobile sales, home sales, retail sales, and travel behavior. Even predicting the present is useful, since it may help identify "turning points" in economic time series. If people start doing significantly more searches for "Real Estate Agents" in a certain location, it is tempting to think that house sales might increase in that area in the near future.Our paper outlines one approach to short-term economic prediction, but we expect that there are several other interesting ideas out there. So we suggest that forecasting wannabes download some Google Trends data and try to relate it to other economic time series. If you find an interesting pattern, post your findings on a website and send a link to econ-forecast@google.com. We'll report on the most interesting results in a later blog post.It has been said that if you put a million monkeys in front of a million computers, you would eventually produce an accurate economic forecast. Let's see how well that theory works.
An experimental measure of Internet retail sales: changes to methods
- C Mclaren
McLaren C (2009) 'An experimental measure of Internet retail sales: changes to methods',
available at www.statistics.gov.uk/cci/article.asp?ID=2358