Measuring employment demand using internet search data

Stevie Chancellor, Scott Counts

Research output: Chapter in Book/Report/Conference proceedingConference contribution

15 Scopus citations

Abstract

We are in a transitional economic period emphasizing automation of physical jobs and the shift towards intellectual labor. How can we measure and understand human behaviors of job search, and how communities are adapting to these changes? We use internet search data to estimate employment demand in the United States. Starting with 225 million raw job search queries in 2015 and 2016 from a popular search engine, we classify queries into one of 15 fields of employment with accuracy and F-1 of 97%, and use the resulting query volumes to estimate per-sector employment demand. We validate against Bureau of Labor Statistics measures, and then demonstrate benefits for communities, showing significant differences in the types of jobs searched for across socio-economic dimensions like poverty and education level. We discuss implications for macroeconomic measurement, as well as how community leaders, policy makers, and the field of HCI benefit from this information.

Original languageEnglish (US)
Title of host publicationCHI 2018 - Extended Abstracts of the 2018 CHI Conference on Human Factors in Computing Systems
Subtitle of host publicationEngage with CHI
PublisherAssociation for Computing Machinery
ISBN (Electronic)9781450356206, 9781450356213
DOIs
StatePublished - Apr 20 2018
Externally publishedYes
Event2018 CHI Conference on Human Factors in Computing Systems, CHI 2018 - Montreal, Canada
Duration: Apr 21 2018Apr 26 2018

Publication series

NameConference on Human Factors in Computing Systems - Proceedings
Volume2018-April

Other

Other2018 CHI Conference on Human Factors in Computing Systems, CHI 2018
Country/TerritoryCanada
CityMontreal
Period4/21/184/26/18

Bibliographical note

Publisher Copyright:
© 2018 ACM.

Keywords

  • Big data
  • Employment
  • Internet search
  • Job search

Fingerprint

Dive into the research topics of 'Measuring employment demand using internet search data'. Together they form a unique fingerprint.

Cite this