Big Data, artificial intelligence and the geography of entrepreneurship in the United States

Abstract

There is increasing interest in the potential of artificial intelligence and Big Data (e.g., generated via social media) to help understand economic outcomes and processes. But can artificial intelligence models, solely based on publicly available Big Data (e.g., language patterns left on social media), reliably identify geographical differences in entrepreneurial personality/culture that are associated with entrepreneurial activity? Using a machine learning model processing 1.5 billion tweets by 5.25 million users, we estimate the Big Five personality traits and an entrepreneurial personality profile for 1,772 U.S. counties. We find that these Twitter-based personality estimates show substantial relationships to county-level entrepreneurship activity, accounting for 20% (entrepreneurial personality profile) and 32% (all Big Five trait as separate predictors in one model) of the variance in local entrepreneurship and are robust to the introduction in the model of conventional economic factors that affect entrepreneurship. We conclude that artificial intelligence methods, analysing publically available social media data, are indeed able to detect entrepreneurial patterns, by measuring territorial differences in entrepreneurial personality/culture that are valid markers of actual entrepreneurial behaviour. More importantly, such social media datasets and artificial intelligence methods are able to deliver similar (or even better) results than studies based on millions of personality tests (self-report studies). Our findings have a wide range of implications for research and practice concerned with entrepreneurial regions and eco-systems, and regional economic outcomes interacting with local culture.

Nice guys finish last: When and why agreeableness is associated with economic hardship.

“…Given that a number of counties were missing, and spatial lag models cannot operate with missing data, it was not possible to define neighbouring counties by shared borders, as we did in Study 6. Instead, we followed an approach suggested by Obschonka and colleagues (Obschonka, Lee, Rodríguez-Pose, Eichstaedt & Ebert, 2018), which defined neighbouring counties as those for which the county centroids are less than 100km apart. For the 59 counties (mostly islands) that were more than 100km away from the next county centroid, we used the closest county as the nearest neighbour.…”

Entrepreneurship education of college students and entrepreneurial psychology of new entrepreneurs under causal attribution theory

“…Entrepreneurial psychology studies the psychological influence factors of entrepreneurs. Research on entrepreneurial psychology helps entrepreneurs adjust their management methods and business models promptly (Obschonka et al, 2020;Su et al, 2020;Wiklund et al, 2020). As an important field of entrepreneurial psychology research, entrepreneurial psychological capital is a specific positive psychological state exhibited by individuals that can affect entrepreneurial-related activities (Chavoushi et al, 2021;Newman et al, 2021;Haddoud et al, 2022).…”

Automatic Quality Control of Crowdsourced Rainfall Data With Multiple Noises: A Machine Learning Approach

“…

In recent years, crowdsourcing, an alternative data acquisition approach that involves the collection of data from individual citizens through the internet, social media, and smartphones, has been increasingly investigated, especially in the field of geophysics (Ebert et al, 2018;Wu & Wang, 2019). Compared to traditional geophysical data collection approaches (which largely rely on expensive professional instruments; de Vos, Droste, et al, 2019), the crowdsourced approach uses human judgments or the low-cost sensors of common citizens as its data source (Zhang et al, 2021).

…”