Show/Hide Menu
Hide/Show Apps
Logout
Türkçe
Türkçe
Search
Search
Login
Login
OpenMETU
OpenMETU
About
About
Open Science Policy
Open Science Policy
Open Access Guideline
Open Access Guideline
Postgraduate Thesis Guideline
Postgraduate Thesis Guideline
Communities & Collections
Communities & Collections
Help
Help
Frequently Asked Questions
Frequently Asked Questions
Guides
Guides
Thesis submission
Thesis submission
MS without thesis term project submission
MS without thesis term project submission
Publication submission with DOI
Publication submission with DOI
Publication submission
Publication submission
Supporting Information
Supporting Information
General Information
General Information
Copyright, Embargo and License
Copyright, Embargo and License
Contact us
Contact us
Activism via attention: interpretable spatiotemporal learning to forecast protest activities
Download
index.pdf
Date
2019-02-14
Author
Ertuğrul, Ali Mert
Lin, Yu-Ru
Chung, Wen-Ting
Yan, Muheng
Li, Ang
Metadata
Show full item record
This work is licensed under a
Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License
.
Item Usage Stats
145
views
72
downloads
Cite This
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.
Subject Keywords
Interpretable spatiotemporal learning
,
Event forecasting
,
Civil unrest
,
Protest activities
URI
https://hdl.handle.net/11511/62956
Journal
EPJ DATA SCIENCE
DOI
https://doi.org/10.1140/epjds/s13688-019-0183-y
Collections
Graduate School of Informatics, Article
Suggestions
OpenMETU
Core
Social determination of reputation: a research in Turkish context
Çalışkan, Mehmet Ali; Yeğen, Mesut; Department of Sociology (2010)
Today, the proliferation of social communication channels and the rapidization of communication cause fast dispersion of information and interpretation of social, cultural and economic developments. Therefore, societies interact with organizations not only through products and services, but also through image, visibility, perceptions, rumors, etc. Organizations have to develop reputation policies; they have to measure, track and manage their reputation. The most important element of an organization’s reputa...
Place and protest: the “occupy gezi movement” in Ankara
Şensönmez, Gökhan; Bodirsky, Katharina; Department of Sociology (2016)
This thesis analyzes the occupy movement within the example of Gezi in terms of place and protest. The term occupy movement indicats a contradictory couple of static and dynamic strategies. While the literature attends this new wave of mobilizations through the lens of 'occupy' alone, the essential component 'movement' is neglected. Accordingly, the existing works on Gezi mainly study Gezi Park that overshadows the experiences of a movement spread to nation-scale. To be able to shed light to these experienc...
Rights-based civil society organizations and democratization in Turkey
Tanca, Dersu Ekim; Alpan, Başak Zeynep; Department of European Studies (2019)
This thesis investigates the role of the rights-based civil society organizations in promoting democratization in Turkey. I consider rights-based civil society organizations as focal actors for democratization because they initiate, secure and advance democratic rule by upholding liberties and freedoms. From the late Ottoman period to the 198ights-based civil society organizations were absent. However, after the 1980s, they emerged to represent different right themes. By employing the existing literature on...
Resisting English medium instruction through digital grassroots activism
Selvi, Ali Fuad (Informa UK Limited, 2020-02-07)
Recently, we have been witnessing the emergence of digital grassroots activism in social networking sites (e.g. Facebook) - affording discursive tools and spaces to engage in normative approaches to preserve Turkish(ness) and raise ideological oppositions against English medium instruction (EMI). By linking Critical Discourse Analysis (Fairclough, N. 2013. Critical Discourse Analysis: The Critical Study of Language. London, UK: Routledge.) with the principles of visual semiotics (Kress, G., and T. van Leeuw...
Interpretable spatio-temporal networks for modeling and forecasting societal events
Ertuğrul, Ali Mert; Taşkaya Temizel, Tuğba; Department of Information Systems (2019)
The relationships between individual activities and societal events (e.g. migrations, social movements) are complex due to the various social, temporal and spatial factors. Understanding such relationships in the context of various societal events such as street protests and opioid crisis, and forecasting these events are important as they have great impacts on public policies and supporting decision making of authorities. In this thesis, novel, spatio-temporal, deep neural networks are proposed (i) to fore...
Citation Formats
IEEE
ACM
APA
CHICAGO
MLA
BibTeX
A. M. Ertuğrul, Y.-R. Lin, W.-T. Chung, M. Yan, and A. Li, “Activism via attention: interpretable spatiotemporal learning to forecast protest activities,”
EPJ DATA SCIENCE
, pp. 0–0, 2019, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/62956.