Mining for Signals of Future Consumer Expenditure on Twitter and Google Trends

Consumer expenditure constitutes the largest component of Gross Domestic Product in developed countries, and forecasts of consumer spending are therefore an important tool that governments and central bank use in their policy-making. In this paper we examine methods to forecast consumer spending from user-generated content, such as search engine queries and social media data, which hold the promise to produce forecasts much more efficiently than traditional surveys. Specifically, the aim of the paper is to study the relative utility of evidence about purchase intentions found in Google Trends versus those found in Twitter posts, for the problem of forecasting consumer expenditure. Our main findings are that, firstly, the Google Trends indicators and indicators extracted from Twitter are both beneficial for the forecasts: adding them as exogenous variables into regression model produces improvements on the pure AR baseline, consistently across all the forecast horizons. Secondly, we find that the Google Trends variables seem to be more useful predictors than the semantic variables extracted from Twitter posts, the differences in performance are significant, but not very large.

Google matrix analysis of worldwide football mercato

The worldwide football transfer market is analyzed as a directed complex network: the football clubs are the network nodes and the directed edges are weighted by the total amount of money transferred from a club to another. The Google matrix description allows to treat every club independently of their richness and allows to measure for a given club the efficiency of player sales and player acquisitions. The PageRank algorithm, developed initially for the World Wide Web, naturally characterizes the ability of a club to import players. The CheiRank algorithm, also developed to analyze large scale directed complex networks, characterizes the ability of a club to export players. The analysis in the two-dimensional PageRank-CheiRank plan permits to determine the transfer balance of the clubs in a more subtle manner than the traditional import-export scheme. We investigate the 2017-2018 mercato concerning 2296 clubs, 6698 player transfers, and 147 player nationalities. The transfer balance is determined globally for different types of player trades (defender, midfielder, forward, …) and for different national football leagues. Although, on average, the network transfer flows from and to clubs are balanced, the discrimination by player type draws a specific portrait of each football club.

How to sort out uncategorisable documents for interpretive social science? On limits of currently employed text mining techniques

Current text mining applications statistically work on the basis of linguistic models and theories and certain parameter settings. This enables researchers to classify, group and rank a large textual corpus – a useful feature for scholars who study all forms of written text. However, these underlying conditions differ in respect to the way how interpretively-oriented social scientists approach textual data. They aim to understand the meaning of text by heuristically using known categorisations, concepts and other formal methods. More importantly, they are primarily interested in documents that are incomprehensible with our current knowledge because these documents offer a chance to formulate new empirically-grounded typifications, hypotheses, and theories. In this paper, therefore, I propose for a text mining technique with different aims and procedures. It includes a shift away from methods of grouping and clustering the whole text corpus to a process that sorts out uncategorisable documents. Such an approach will be demonstrated using a simple example. While more elaborate text mining techniques might become tools for more complex tasks, the given example just presents the essence of a possible working principle. As such, it supports social inquiries that search for and examine unfamiliar patterns and regularities.

Do People Pay More Attention to Earthquakes in Western Countries?

This paper investigates whether people from Western countries pay more attention to earthquakes in Western countries than those in non-Western countries. Using Google Trends data, we examine the proportion of Google searches from the United States, the United Kingdom, Canada, Australia, and New Zealand for 610 earthquakes across the world over the period of 2006-2016. Our results suggest that people in these countries pay around 44 percent more attention to earthquakes in Western countries, holding constant earthquake magnitude and number of casualties. Our results remain significant and similar in magnitude after controlling for geographical and social characteristics, but reduce in magnitude to almost zero and become insignificant after controlling for GDP per capita of the countries where the earthquake struck. Our results suggest that there is a developed country bias, rather than a Western country bias, in people’s attention. This bias might lead to a lower flow of international relief to economically less developed countries, which are less able to deal with disasters.