Who Leads? Who Follows? Measuring Issue Attention and Agenda Setting by Legislators and the Mass Public Using Social Media Data

Abstract

Are legislators responsive to the priorities of the public? Research demonstrates a strong correspondence between the issues about which the public cares and the issues addressed by politicians, but conclusive evidence about who leads whom in setting the political agenda has yet to be uncovered. We answer this question with fine-grained temporal analyses of Twitter messages by legislators and the public during the 113th US Congress. After employing an unsupervised method that classifies tweets sent by legislators and citizens into topics, we use vector autoregression models to explore whose priorities more strongly predict the relationship between citizens and politicians. We find that legislators are more likely to follow, than to lead, discussion of public issues, results that hold even after controlling for the agenda-setting effects of the media. We also find, however, that legislators are more likely to be responsive to their supporters than to the general public.

Americans preferred Syrian refugees who are female, English-speaking, and Christian on the eve of Donald Trump’s election

“…Public attitudes toward refugees, and particularly partisan attitudes, likely shape the behavior of policymakers [16], with potentially dire consequences for those seeking refuge. Recent research has shown that anti-Muslim discrimination and divisive campaigns can cause Muslims in the U.S. to reduce their online visibility and retreat from public life [33]; additionally, anti-Muslim animosity contributes to online radicalization among Muslims in Western Europe [34].…”

“…The number of refugees resettled annually in the U.S. has been dramatically decreased since the survey was fielded, and resettlement of Syrians and Muslims in particular has dropped precipitously, both in absolute and percentage terms, despite the large number of refugees fleeing Syria and Muslim-majority countries. Public attitudes—and especially partisan attitudes—toward refugees may play an important role in shaping legislators’ behavior [16], with implications for thousands of those seeking refuge from conflict. This paper contributes to a recent but vibrant literature that examines attitudes and behavior toward refugees and asylum seekers around the world, as well as anti-Muslim sentiment among the American public [2, 3, 14, 17–20].…”

Content-based features predict social media influence operations

“…This results in varying class imbalance in the test set, with an average ratio of 1 to 5 between positive and negative class. While most similar methods only include users whose time zones or self-reported locations reside in the United States, our data contain a variety of American users by including those users who have not declared their location, but whose location can be estimated through a network of their friends and followers of their friends [details in (28)].…”

A Weakly Supervised and Deep Learning Method for an Additive Topic Analysis of Large Corpora

“…Usually, weakly supervised learning models are evaluated by comparing their results with a benchmark dataset containing similar categories. As the discipline currently does not possess such a dataset, and our label definitions may differ from those of other researchers, we followed some of the validation steps used when validating topic models (e.g., Barberá et al 2018). We provide two datasets that may reassure researchers that the model's assumptions and predictions match its theoretical premises.…”