Link to the University of Pittsburgh Homepage
Link to the University Library System Homepage Link to the Contact Us Form

Activism via attention: interpretable spatiotemporal learning to forecast protest activities

Ertugrul, Ali Mert and Lin, Yu-Ru and Chung, Wen-Ting and Yan, Muheng and Li, Ang (2019) Activism via attention: interpretable spatiotemporal learning to forecast protest activities. EPJ Data Science, 8 (5). pp. 1-26. ISSN 2193-1127

[img] PDF
Published Version

Download (320kB)


The diffusion of new information and communication technologies—social media in particular—has played a key role in social and political activism in recent decades. In this paper, we propose a theory-motivated, spatiotemporal learning approach, ActAttn, that leverages social movement theories and a deep learning framework to examine the relationship between protest events and their social and geographical contexts as reflected in social media discussions. To do so, we introduce a novel predictive framework that incorporates a new design of attentional networks, and which effectively learns the spatiotemporal structure of features. Our approach is not only capable of forecasting the occurrence of future protests, but also provides theory-relevant interpretations—it allows for interpreting what features, from which places, have significant contributions on the protest forecasting model, as well as how they make those contributions. Our experiment results from three movement events indicate that ActAttn achieves superior forecasting performance, with interesting comparisons across the three events that provide insights into these recent movements.


Social Networking:
Share |


Item Type: Article
Status: Published
CreatorsEmailPitt UsernameORCID
Ertugrul, Ali Mert
Lin, Yu-Ruyurulin@pitt.eduyurulin
Chung, Wen-Tingwtchung@pitt.eduwtchung
Yan, Muheng
Li, Ang
Date: 2019
Date Type: Publication
Journal or Publication Title: EPJ Data Science
Volume: 8
Number: 5
Publisher: SpringerOpen
Page Range: pp. 1-26
DOI or Unique Handle: 10.1140/epjds/s13688-019-0183-y
Schools and Programs: School of Computing and Information > Information Science
Refereed: Yes
Uncontrolled Keywords: Interpretable spatiotemporal learning; Event forecasting; Civil unrest; Protest activities
ISSN: 2193-1127
Official URL:
Date Deposited: 04 May 2020 17:12
Last Modified: 04 May 2020 17:13


Monthly Views for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item