More Tweets, More Votes: Social Media as a Quantitative Indicator of Political Behavior

Abstract

Is social media a valid indicator of political behavior? There is considerable debate about the validity of data extracted from social media for studying offline behavior. To address this issue, we show that there is a statistically significant association between tweets that mention a candidate for the U.S. House of Representatives and his or her subsequent electoral performance. We demonstrate this result with an analysis of 542,969 tweets mentioning candidates selected from a random sample of 3,570,054,618, as well as Federal Election Commission data from 795 competitive races in the 2010 and 2012 U.S. congressional elections. This finding persists even when controlling for incumbency, district partisanship, media coverage of the race, time, and demographic variables such as the district's racial and gender composition. Our findings show that reliable data about political behavior can be extracted from social media.

‘This loopy idea’ an analysis of UKIP’s social media discourse in relation to rurality and climate change

“…DiGrazia and colleagues have also used Twitter to discern voting intentions; their findings confirm those of Connover about the practical organisation of conservatives through social media in the US (Chew & Eysenbach, 2010;DiGrazia, McKelvey, Bollen, & Rojas, 2013). They point to the limitations of earlier studies but through an analysis of over ½ million tweets posted during 795 competitive election races in the US between 2010-12 found that social media has a role in indicating political behaviour.…”

High-resolution Temporal Representations of Alcohol and Tobacco Behaviors from Social Media Data

“…This is a fundamental limitation of this study in terms of the content of the data; we have not linked the Tweets to who people are or what people do in the offline world, thus all findings are based on how these behaviors are communicated online. Initial work assessing online and offline behavior has shown that reliable data about political behavior (candidates supported online and voting behavior) [32], and weight loss [65] are also validated in the offline world. As we discuss below, a comprehensive study that links the social media communications to offline behaviors should be performed.…”

The empiricist’s challenge: Asking meaningful questions in political science in the age of big data

“…In the other group, we find studies using digital trace data as predictors of political events and phenomena or proxies for other more traditional measurement approaches in the social sciences, such as surveys (Barberá, 2015;DiGrazia, McKelvey, Bollen, & Rojas, 2013;Steinert-Threlkeld, Mocanu, Vespignani, & Fowler, 2015;Tumasjan, Sprenger, Sandner, & Welpe, 2010). Here, we find a strong prominence of studies concentrating on statistical predictions of various political outcomes based on signals found in digital trace data (see Hofman, Sharma, & Watts, 2017;Schoen et al, 2013).…”