Using Google Search Data for State Politics Research: An Empirical Validity Test Using Roll-Off Data

Abstract

Google Insights for Search provides a new and rich data source for political scientists, which may be particularly useful for state politics scholars. We outline the prior uses of Google Insights for Search in social and health sciences, explain the data-generating process, and test for the first time the validity of this data for state politics research. Our empirical test of validity shows that Google searches for ballot measures' names and topics in state one week before the 2008 Presidential election correlate with actual participation on those ballot measures. This demonstrates that the more Internet searches there were for a ballot measure, the less likely voters were to rolloff (not answering the question), and establishes the construct validity for this data for one important topic in state politics research. We also outline the limitations to this data source.

Public interest in climate change over the past decade and the effects of the ‘climategate’ media event

“…Google Trends is one of the few open sources of high resolution search query data and Google accounts for >80% of global search engine use (Net Market Share 2013). Increasingly utilized for applications in public health (Ginsberg et al 2009), political science (Koehler-Derrick 2013), and economics (Goel et al 2010), Google Trends is considered a robust and valid indicator for tracking interest, attention, and public opinion over time (Ortiz et al 2011, Reilly et al 2012, Zhu et al 2012, Mellon 2013b) and has previously been used to quantify trends in public interest in environmental key words (McCallum andBury 2013, Proulx et al 2013). Importantly, Google Trends data have been validated for the term 'global warming' relative to independent longitudinal polling data (Mellon 2013a).…”

The effect of a terrorist attack on emergency department inflow: an observation study using difference-in-differences methodology

“…Figure 2 shows the volume of Google searches on the keywords “terror” or “terroriste” in conjunction with four recent terrorist attacks in Europe, generated by Google Trends [34]. In previous research, similar searches have been shown to consistently produce more statistically accurate data than other survey- based indicators of public attention and opinion [35–38]. In this case, it is clear that public attention, as measured by the volume of searches, follows the same two-week pattern as the inflow reduction.…”

X Views and Counting

“…Although a new data source, validation of Internet search queries exists across multiple disciplines, including political science (Bélanger & Meguid, 2008; Reilly, Richey, & Taylor, 2012; Ripberger, 2011; Scharkow & Vogelgesang, 2011; Weeks & Southwell, 2010), epidemiology (see Althouse, Ng, & Cummings, 2011; Ginsberg et al, 2009), health care (Reis & Brownstein, 2010), consumer behavior (Goel, Hofman, Lahaie, Pennock, & Watts, 2010), suicide studies (Marhan, Săucan, Popa, & Danciu, 2012; McCarthy, 2010), and efficacy-based studies within the social sciences (Scheitle, 2011). The rising popularity of this data source exceeds just its relative “newness” and claimed efficacy.…”