This report assesses empirical applications of web search data and discusses the prospective value such data can offer Army recruiting efforts. The authors examine three different tools — Google Trends, Google AdWords, and Google Correlate — that can be used to access and analyze readily available, anonymous data from Internet searches related to the Army and to Army service.

Searching for Information Online

Using Big Data to Identify the Concerns of Potential Army Recruits

Salar Jahedi, Jennie W. Wenger, Douglas Yeung

ResearchPublished Mar 9, 2016

Cover: Searching for Information Online
Download PDF
Additional Downloads

Includes Research Synopsis

This report assesses empirical applications of web search data and discusses the prospective value such data can offer Army recruiting efforts. The authors examine three different tools — Google Trends, Google AdWords, and Google Correlate — that can be used to access and analyze readily available, anonymous data from Internet searches related to the Army and to Army service. They found that Google search queries can inform how interest in military careers has evolved over time and by geographic location and can identify the foremost Army-related concerns that potential recruits have. Moreover, by analyzing how search terms correlate across time, it is possible to predict with reasonable accuracy what non-Army related terms people are searching for in the months before or after an Army query. These queries serve as leading and lagging indicators of army-related searches and can offer a glimpse into the concerns of individuals near the time period when they are considering joining. The results suggest that search terms can serve as an indicator of propensity and can be incorporated into models to predict highly qualified Army accessions.

Key Takeaways

  • Google search queries can be used to better understand how interest in military careers has evolved over time and geographic location.
  • It is possible to use these tools to identify the chief Army-related concerns that potential recruits have, including the qualifications for, procedures for, or benefits of enlisting.
  • It is possible to predict with reasonable accuracy what individuals were searching for months before or after searching for Army-related terms.
  • Including Google Trends terms in a model of factors influencing the number of Army accessions increases the predictive power of the model.

Recommendations

  • Further research is required to better understand ways of using Internet search data to inform Army recruiting initiatives, with the eventual goal of drawing causal inferences and making accurate predictions.
  • One promising path involves combining the Google search data with a secondary data source, such as the U.S. Census Bureau, which has information about the percentage of the military-aged population within a geographic region.
  • In the same way that companies such as Amazon and Netflix recommend products or movies to individuals based on the behavior of similar shoppers, it is possible for the Army to share queried information with individuals based on what other similar individuals find most useful.

Topics

Document Details

Citation

Chicago Manual of Style

Jahedi, Salar, Jennie W. Wenger, and Douglas Yeung, Searching for Information Online: Using Big Data to Identify the Concerns of Potential Army Recruits. Santa Monica, CA: RAND Corporation, 2016. https://www.rand.org/pubs/research_reports/RR1197.html.
BibTeX RIS

Research conducted by

The work presented in this report was sponsored by the U.S. Army and was conducted within the Personnel, Training, and Health Program, part of the RAND Arroyo Center.

This publication is part of the RAND research report series. Research reports present research findings and objective analysis that address the challenges facing the public and private sectors. All RAND research reports undergo rigorous peer review to ensure high standards for research quality and objectivity.

This document and trademark(s) contained herein are protected by law. This representation of RAND intellectual property is provided for noncommercial use only. Unauthorized posting of this publication online is prohibited; linking directly to this product page is encouraged. Permission is required from RAND to reproduce, or reuse in another form, any of its research documents for commercial purposes. For information on reprint and reuse permissions, please visit www.rand.org/pubs/permissions.

RAND is a nonprofit institution that helps improve policy and decisionmaking through research and analysis. RAND's publications do not necessarily reflect the opinions of its research clients and sponsors.