A scalable machine learning approach for measuring violent and peaceful forms of political protest participation with social media data.

Jake Ryland Williams,Lefteris Jason Anastasopoulos,Lazaros K Gallos

doi:10.1371/journal.pone.0212834

Jake Ryland Williams, Lefteris Jason Anastasopoulos + Show 1 more

Open Access

https://doi.org/10.1371/journal.pone.0212834

Copy DOI

Journal: PloS one	Publication Date: Mar 19, 2019
Citations: 10	License type: CC BY 4.0

Affiliation: Drexel University

Abstract

In this paper, we introduce a scalable machine learning approach accompanied by open-source software for identifying violent and peaceful forms of political protest participation using social media data. While violent political protests are statistically rare events, they often shape public perceptions of political and social movements. This is, in part, due to the extensive and disproportionate media coverage which violent protest participation receives relative to peaceful protest participation. In the past, when a small number of media conglomerates served as the primary information source for learning about political and social movements, viewership and advertiser demands encouraged news organizations to focus on violent forms of political protest participation. Consequently, much of our knowledge about political protest participation is derived from data collected about violent protests, while less is known about peaceful forms of protest. Since the early 2000s, the digital revolution shifted attention away from traditional news sources toward social media as a primary source of information about current events. This, along with developments in machine learning which allow us to collect and analyze data relevant to political participation, present us with unique opportunities to expand our knowledge of peaceful and violent forms of political protest participation through social media data.

Highlights

While violent protests are statistically rare events, they tend to shape how political and social movements are perceived by the public [1, 2]
As a result of the focus on violent protests, much of our prior knowledge about political protest participation is based on data collected about violent protest activity while less is known about participation in peaceful protest [5]
As political protest participation in the digital age becomes increasingly represented on social media, a theory which is able to map textual data and metadata onto events occurring on the ground provides a means by which these data can be harnessed to better understand the evolution of modern political protest participation in its peaceful and violent manifestations

Summary

Introduction

While violent protests are statistically rare events, they tend to shape how political and social movements are perceived by the public [1, 2]. We seek to develop a practical methodology, accompanied by open—source software, which allows researchers and the public to build databases that can identify and measure participation in peaceful and violent political protest events from social media data. A method which can distinguish between data relevant to political participation must first determine how activities related to these phenomena manifest within social media data, for example, as tweets on Twitter discussing participation in a citizen demonstration or expressing a political viewpoint about an issue This knowledge can be utilized to develop a classification scheme can be used to assign labels to individual pieces of social media data such as tweets. These rules are summarized as answers to the following 7 questions: 1. Are we dealing with behavior?

Is the activity used to express political aims and intentions of participants?

Discussion

Findings

Myers Daniel J The diffusion of collective violence