Cookies?
Library Header Image
LSE Research Online LSE Library Services

Big data methods, social media, and the psychology of entrepreneurial regions: capturing cross-county personality traits and their impact on entrepreneurship in the USA

Obschonka, Martin, Lee, Neil, Rodríguez-Pose, Andrés, Eichstaedt, Johannes C. and Ebert, Tobias (2019) Big data methods, social media, and the psychology of entrepreneurial regions: capturing cross-county personality traits and their impact on entrepreneurship in the USA. Small Business Economics. pp. 1-22. ISSN 0921-898X

[img] Text - Accepted Version
Repository staff only until 28 June 2020.

Download (2MB) | Request a copy

Identification Number: 10.1007/s11187-019-00204-2

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. But can artificial intelligence models based on publicly available Big Data identify geographical differences in entrepreneurial personality or culture? We use a machine learning model based on 1.5 billion tweets by 5.25 million users to estimate the Big Five personality traits and an entrepreneurial personality profile for 1,772 U.S. counties. The Twitter-based personality estimates show substantial relationships to county-level entrepreneurship activity, accounting for 20% (entrepreneurial personality profile) and 32% (Big Five traits) of the variance in local entrepreneurship, even when controlling for other factors that affect entrepreneurship. Whereas more research is clearly needed, our findings have initial implications for research and practice concerned with entrepreneurial regions and eco-systems, and regional economic outcomes interacting with local culture. The results suggest, for example, that social media datasets and artificial intelligence methods have the potential to deliver comparable information on the personality and culture of regions than studies based on millions of questionnaire-based personality tests.

Item Type: Article
Official URL: https://link.springer.com/journal/11187
Additional Information: © 2019 Springer Science+Business Media, LLC, part of Springer Nature
Divisions: Geography & Environment
Subjects: T Technology > T Technology (General)
Sets: Departments > Geography and Environment
Date Deposited: 20 Dec 2018 16:39
Last Modified: 20 Nov 2019 05:51
URI: http://eprints.lse.ac.uk/id/eprint/91410

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics