Sentiment-based commercial real estate forecasting with Google search volume data

2014 ◽  
Vol 32 (6) ◽  
pp. 540-569 ◽  
Author(s):  
Marian Alexander Dietzel ◽  
Nicole Braun ◽  
Wolfgang Schäfers
Keyword(s):  
Real Estate ◽  
Commercial Real Estate ◽  
Google Trends ◽  
Internet Search ◽  
Price Indices ◽  
Search Query ◽  
Content Type ◽  
Forecasting Models ◽  
Search Data ◽  
Google Search

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 traces of ecotourism in a digital world: spatial and trend analysis of geotagged photographs on social media and Google search data for sustainable development

2020 ◽  
Vol 11 (2) ◽  
pp. 183-202
Author(s):  
Hanyoung Go ◽  
Myunghwa Kang ◽  
Yunwoo Nam
Keyword(s):  
Social Media ◽  
Sustainable Development ◽  
Spatial Analysis ◽  
Google Trends ◽  
Internet Search ◽  
Content Type ◽  
Digital World ◽  
Search Data ◽  
Google Search ◽  
Over Time

Purpose This paper aims to track how ecotourism has been presented in a digital world over time using geotagged photographs and internet search data. Ecotourism photographs and Google Trends search data are used to evaluate tourist perceptions of ecotourism by developing a categorization of essential attributes, examining the relation of ecotourism and sustainable development, and measuring the popularity of the ecotourism sites. Design/methodology/approach The researchers collected geotagged photographs from Flickr.com and downloaded Google search data from Google Trends. An integrative approach of content, trend and spatial analysis was applied to develop ecotourism categories and investigate tourist perceptions of ecotourism. First, the authors investigate ecotourism geotagged photographs on a social media to comprehend tourist perceptions of ecotourism by developing a categorization of key ecotourism attributes and measuring the popularity of the ecotourism sites. Second, they examined how ecotourism has been related with sustainable development using internet search data and investigate the trends in search data. Third, spatial analysis using GIS maps was used to visualize the spatial-temporal changes of photographs and tourist views throughout the world. Findings This study identified three primary themes of ecotourism perceptions and 13 categories of ecotourism attributes. Interest over time about ecotourism was mostly presented as its definitions in Google Trends. The result indicates that tracked ecotourism locations and tourist footprints are not congruent with the popular regions of ecotourism Google search. Originality/value This research follows the changing trends in ecotourism over a decade using geotagged photographs and internet search data. The evaluation of the global ecotourism trend provides important insights for global sustainable tourism development and actual tourist perception. Analyzing the trend of ecotourism is a strategic approach to assess the achievement of UN sustainable development goals. Factual perspectives and insights into how tourists are likely to seek and perceive natural attractions are valuable for a range of audiences, such as tourism industries and governments.

Using Twitter sentiment and emotions analysis of Google Trends for decisions making

2017 ◽  
Vol 51 (3) ◽  
pp. 322-350 ◽  
Author(s):  
Ernesto D’Avanzo ◽  
Giovanni Pilato ◽  
Miltiadis Lytras
Keyword(s):  
Web Service ◽  
Language Processing ◽  
Real World ◽  
Consumer Electronics ◽  
Google Trends ◽  
Search Query ◽  
Content Type ◽  
Monitoring Task ◽  
Twitter Users ◽  
Google Search

Purpose 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). Design/methodology/approach 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. Findings 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. Originality/value The proposed approach aims to bridge the gap among Google search query data and sentiments that emerge on Twitter about these trends.

scholarly journals Sentiment-based predictions of housing market turning points with Google trends

2016 ◽  
Vol 9 (1) ◽  
pp. 108-136 ◽  
Author(s):  
Marian Alexander Dietzel
Keyword(s):  
Real Estate ◽  
Housing Market ◽  
Turning Points ◽  
House Price ◽  
Data Set ◽  
Content Type ◽  
Forecasting Models ◽  
Search Volume ◽  
Out Of Sample ◽  
Google Search

Purpose – Recent research has found significant relationships between internet search volume and real estate markets. This paper aims to examine whether Google search volume data can serve as a leading sentiment indicator and are able to predict turning points in the US housing market. One of the main objectives is to find a model based on internet search interest that generates reliable real-time forecasts. Design/methodology/approach – Starting from seven individual real-estate-related Google search volume indices, a multivariate probit model is derived by following a selection procedure. The best model is then tested for its in- and out-of-sample forecasting ability. Findings – The results show that the model predicts the direction of monthly price changes correctly, with over 89 per cent in-sample and just above 88 per cent in one to four-month out-of-sample forecasts. The out-of-sample tests demonstrate that although the Google model is not always accurate in terms of timing, the signals are always correct when it comes to foreseeing an upcoming turning point. Thus, as signals are generated up to six months early, it functions as a satisfactory and timely indicator of future house price changes. Practical implications – The results suggest that Google data can serve as an early market indicator and that the application of this data set in binary forecasting models can produce useful predictions of changes in upward and downward movements of US house prices, as measured by the Case–Shiller 20-City House Price Index. This implies that real estate forecasters, economists and policymakers should consider incorporating this free and very current data set into their market forecasts or when performing plausibility checks for future investment decisions. Originality/value – This is the first paper to apply Google search query data as a sentiment indicator in binary forecasting models to predict turning points in the housing market.

scholarly journals Compilation of Commercial Property Price Indices for Germany Tailored for Policy Use

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Thomas A. Knetsch
Keyword(s):  
Time Series ◽  
Real Estate ◽  
Commercial Real Estate ◽  
German Population ◽  
Price Indices ◽  
Commercial Property ◽  
Price Increases ◽  
Comprehensive Data ◽  
Property Price ◽  
Existing Data

Abstract The compilation of commercial property price indices (CPPIs) is challenging. Policymakers urge for timely, reliable and comprehensive data. In Germany, lack of data prevents the calculation of official figures by the national statistical authority. Different applications of price indices need different definitions of commercial real estate. CPPIs according to these definitions are constructed on the basis of existing data for 127 German towns and cities (that cover about one-third of German population). The overall price developments revealed by the various indices are rather similar in terms of central time series characteristics, while differences in detail can be explained by their specific compositions. Price increases for all definitions have been strongest in the seven largest cities. The definitions tend to lead to more marked differences for medium-sized towns.

A post-global financial crisis (GFC) framework for strategic planning, assessment and management decision making for US sustainable commercial real estate

2017 ◽  
Vol 35 (6) ◽  
pp. 589-618 ◽  
Author(s):  
Pernille Hoy Christensen
Keyword(s):  
Decision Making ◽  
Financial Crisis ◽  
Real Estate ◽  
Performance Indicators ◽  
Institutional Investors ◽  
Global Financial Crisis ◽  
Real Estate Market ◽  
Commercial Real Estate ◽  
Content Type ◽  
Sustainability Initiatives

Purpose The purpose of this paper is to understand both the facts and the values associated with the breadth of issues, and the principles related to sustainable real estate for institutional investors. Sustainable real estate is a growing sector within the commercial real estate industry, and yet, the decision-making practices of institutional investors related to sustainability are still not well understood. In an effort to fill that gap, this research investigates the post-global financial crisis (GFC) motivations driving the implementation of sustainability initiatives, the implementation strategies used, and the predominant eco-indicators and measures used by institutional investors. Design/methodology/approach This paper presents the results of a three-round modified Delphi study conducted in the USA in 2011-2012 investigating the nature of performance measurements and reporting requirements in sustainable commercial real estate and their impact on the real estate decision-making process used by institutional investors. Two rounds of in-depth interviews were conducted with 14 expert panelists. An e-questionnaire was used in the third round to verify qualitative findings. Findings The key industry drivers and performance indicators influencing institutional investor decision making were associated with risk management of assets and whether initiatives can improve competitive market advantage. Industry leaders advocate for simple key performance indicators, which is in contrast to the literature which argues for the need to adopt common criteria and metrics. Key barriers to the adoption of sustainability initiatives are discussed and a decision framework is presented. Practical implications This research aims to help industry partners understand the drivers motivating institutional investors to uptake sustainability initiatives with the aim of improving decision making, assessment, and management of sustainable commercial office buildings. Originality/value Building on the four generations of the sustainability framework presented by Simons et al. (2001), this research argues that the US real estate market has yet again adjusted its relationship with sustainability and revises their framework to include a new, post-GFC generation for decision making, assessment, and management of sustainable real estate.

scholarly journals Interest in COVID-19 in Latin America and the Caribbean: an infodemiological study using Google Trends

2021 ◽  
Vol 37 (10) ◽  
Author(s):  
Carlos Jesús Aragón-Ayala ◽  
Julissa Copa-Uscamayta ◽  
Luis Herrera ◽  
Frank Zela-Coila ◽  
Cender Udai Quispe-Juli
Keyword(s):  
Latin America ◽  
Response Time ◽  
Latin American ◽  
Google Trends ◽  
Public Attention ◽  
Search Data ◽  
The Caribbean ◽  
Global And Local ◽  
Google Search ◽  
Latin American And Caribbean

Infodemiology has been widely used to assess epidemics. In light of the recent pandemic, we use Google Search data to explore online interest about COVID-19 and related topics in 20 countries of Latin America and the Caribbean. Data from Google Trends from December 12, 2019, to April 25, 2020, regarding COVID-19 and other related topics were retrieved and correlated with official data on COVID-19 cases and with national epidemiological indicators. The Latin American and Caribbean countries with the most interest for COVID-19 were Peru (100%) and Panama (98.39%). No correlation was found between this interest and national epidemiological indicators. The global and local response time were 20.2 ± 1.2 days and 16.7 ± 15 days, respectively. The duration of public attention was 64.8 ± 12.5 days. The most popular topics related to COVID-19 were: the country’s situation (100 ± 0) and coronavirus symptoms (36.82 ± 16.16). Most countries showed a strong or moderated (r = 0.72) significant correlation between searches related to COVID-19 and daily new cases. In addition, the highest significant lag correlation was found on day 13.35 ± 5.76 (r = 0.79). Interest shown by Latin American and Caribbean countries for COVID-19 was high. The degree of online interest in a country does not clearly reflect the magnitude of their epidemiological indicators. The response time and the lag correlation were greater than in European and Asian countries. Less interest was found for preventive measures. Strong correlation between searches for COVID-19 and daily new cases suggests a predictive utility.

scholarly journals What sells in a crisis? Determinants of sale probability over a cycle and through a crash

2017 ◽  
Vol 35 (6) ◽  
pp. 619-637 ◽  
Author(s):  
David Scofield ◽  
Steven Devaney
Keyword(s):  
Real Estate ◽  
Sample Selection ◽  
Sampling Technique ◽  
Real Estate Market ◽  
Commercial Real Estate ◽  
Content Type ◽  
Asset Selection ◽  
The Uk ◽  
Real Estate Cycle ◽  
Over Time

Purpose The purpose of this paper is to understand what affects the liquidity of individual commercial real estate assets over the course of the economic cycle by exploring a range of variables and a number of time periods to identify key determinants of sale probability. Design/methodology/approach Analyzing 12,000 UK commercial real estate transactions (2003 to 2013) the authors use an innovative sampling technique akin to a perpetual inventory approach to generate a sample of held assets for each 12 month interval. Next, the authors use probit models to test how market, owner and property factors affect sale probability in different market environments. Findings The types of properties that are most likely to sell changes between strong and weak markets. Office and retail assets were more likely to sell than industrial both overall and in better market conditions, but were less likely to sell than industrial properties during the downturn from mid-2007 to mid-2009. Assets located in the City of London more likely to sell in both strong and weak markets. The behavior of different groups of owners changed over time, and this indicates that the type of owner might have implications for the liquidity of individual assets over and above their physical and locational attributes. Practical implications Variation in sale probability over time and across assets has implications for real estate investment management both in terms of asset selection and the ability to rebalance portfolios over the course of the cycle. Results also suggest that sample selection may be an issue for commercial real estate price indices around the globe and imply that indices based on a limited group of owners/sellers might be susceptible to further biases when tracking market performance through time. Originality/value The study differs from the existing literature on sale probability as the authors analyzed samples of transactions drawn from all investor types, a significant advantage over studies based on data restricted to samples of domestic institutional investors. As well, information on country of origin for buyers and sellers allows us to explore the influence of foreign ownership on the probability of sale. Finally, the authors not only analyze all transactions together, but the authors also look at transactions in five distinct periods that correspond with different phases of the UK commercial real estate cycle. This paper considers the UK real estate market, but it is likely that many of the findings hold for other major commercial real estate markets.

scholarly journals Cap rates and risk: a spatial analysis of commercial real estate

2018 ◽  
Vol 35 (1) ◽  
pp. 25-43
Author(s):  
Florian Unbehaun ◽  
Franz Fuerst
Keyword(s):  
Real Estate ◽  
Risk Perceptions ◽  
Large Scale ◽  
Risk Premia ◽  
Real Estate Market ◽  
Commercial Real Estate ◽  
Data Series ◽  
Large Set ◽  
Content Type ◽  
The Impact

Purpose This study aims to assess the impact of location on capitalization rates and risk premia. Design/methodology/approach Using a transaction-based data series for the five largest office markets in Germany from 2005 to 2015, regression analysis is performed to account for a large set of asset-level drivers such as location, age and size and time-varying macro-level drivers. Findings Location is found to be a key determinant of cap rates and risk premia. CBD locations are found to attract lower cap rates and lower risk premia in three of the five largest markets in Germany. Interestingly, this effect is not found in the non-CBD locations of these markets, suggesting that the lower perceived risk associated with these large markets is restricted to a relatively small area within these markets that are reputed to be safe investments. Research limitations/implications The findings imply that investors view properties in peripheral urban locations as imperfect substitutes for CBD properties. Further analysis also shows that these risk premia are not uniformly applied across real estate asset types. The CBD risk effect is particularly pronounced for office and retail assets, apparently considered “prime” investments within the central locations. Originality/value This is one of the first empirical studies of the risk implications of peripheral commercial real estate locations. It is also one of the first large-scale cap rate analyses of the German commercial real estate market. The results demonstrate that risk perceptions of investors have a distinct spatial dimension.

Assessing E-Government Success Strategies using Internet Search Data

2013 ◽  
pp. 289-307
Author(s):  
Katherine M. Boland ◽  
John G. McNutt
Keyword(s):  
Longitudinal Data ◽  
Google Trends ◽  
Success Strategies ◽  
Internet Search ◽  
Dynamic Nature ◽  
Government Programs ◽  
Search Data ◽  
Research Questions ◽  
Internet Searches ◽  
Citizen Response

Evaluating e-government programs can be a challenging task. While determining program features and capacity are relatively straightforward processes, exploring the more dynamic nature of citizen response to e-government is difficult. Fortunately, recent advances in Internet search technology offer researchers new opportunities to address these research questions. Innovations, such as Google Trends and Google Insights for Search, have made longitudinal data on Internet searches accessible to scholars. The availability of this data opens a number of possible research avenues regarding e-government.

scholarly journals Blockchain technology in commercial real estate transactions

2019 ◽  
Vol 37 (6) ◽  
pp. 570-579 ◽  
Author(s):  
Hugo Pieter Wouda ◽  
Raymond Opdenakker
Keyword(s):  
Real Estate ◽  
Design Science ◽  
Science Research ◽  
Commercial Real Estate ◽  
Office Building ◽  
Content Type ◽  
Blockchain Technology ◽  
Transaction Process ◽  
Current Transaction ◽  
Pain Points

Purpose The transaction process of an office building is known to be time consuming and inefficient, in part due to the lack of market transparency. The purpose of this paper is to focus on the development of a blockchain application that can improve the transaction process of office buildings in the Netherlands. Design/methodology/approach Conducting design science research, the current transaction process of an office building and status quo of blockchain technology in real estate is investigated. Subsequently, multiple parties are interviewed to define major pain points within the process. The interview findings are used to design a blockchain solution which overcomes the aforementioned pain points. After designing, the interviewees are asked again to pragmatically validate the proposed model. Findings One of the major pain points identified concerning the transaction process of an office building is that it is difficult to define the characteristics of a property, due to lack of data structure and quality. The proposed application improves the way specific assets are understood by structuring physical and contractual information in one place and guarantees the quality of the data by using the blockchain mechanisms. Practical implications A blockchain application is proposed, which can improve the transaction process of an office building. Originality/value Recent studies indicate that blockchain technology could lead to improvements in efficiency, transparency and therefore trust within the transaction process. Therefore, the proposed application is of value for the future of real estate data management and the transaction process.

Sign in / Sign up

Export Citation Format

Share Document