Civilian behavior on social media during civil war

Author:

Gohdes Anita R.1ORCID,Steinert‐Threlkeld Zachary C.2ORCID

Affiliation:

1. Hertie School Friedrichstr. 180 Berlin Germany

2. UCLA Luskin School of Public Affairs, University of California, Los Angeles Los Angeles California USA

Abstract

AbstractRecent research emphasizes social media's potential for citizens to express shared grievances. In active conflict, however, social media posts indicating political loyalties can pose severe risks to civilians. We develop a theory that explains how civilians modify their online behavior as part of efforts to improve their security during conflict. After major changes in territorial control, civilians should be more likely to post positive content, and more content that supports the winning side. We study social media behavior during and after the siege of Aleppo in November 2016. We match Aleppo‐based Twitter users with users from other parts of Syria and use large language models to analyze changes in online behavior after the regime's retaking of the city. Results show that users in Aleppo post more positive and pro‐Assad content, but only when self‐disclosing their location. The findings have important implications for our understanding of digital communication in civil conflict.

Publisher

Wiley

Reference66 articles.

1. Abdul‐Mageed Muhammad Abdelrahim A.Elmadany andEl MoatezBill.2021. “ARBERT & MARBERT: Deep Bidirectional Transformers for Arabic.”59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 7088–7105.Association for Computational Linguistics.

2. Antoun Wissam FadyBaly andHazemHajj.2020. “AraBERT: Transformer‐Based Model for Arabic Language Understanding.”Proceedings of the 4th Workshop on Open‐Source Arabic Corpora and Processing Tools with a Shared Task on Offensive Language Detection. 9–15.

3. Baly Ramy AlaaKhaddaj HazemHajj WassimEl‐Hajj andKhaled BashirShaban.2019. “ArSentD‐LEV: A Multi‐Topic Corpus for Target‐Based Sentiment Analysis in Arabic Levantine Tweets.”http://arxiv.org/abs/1906.01830

4. Bassam Laila AngusMcDowall andStephanieNebehay.2016. “Battle of Aleppo Ends After Years of Bloodshed with Rebel Withdrawal.”https://www.reuters.com/article/us‐mideast‐crisis‐syria/battle‐of‐aleppo‐ends‐after‐years‐of‐bloodshed‐with‐rebel‐withdrawal‐idUSKBN1420H5

5. Can Hearts and Minds Be Bought? The Economics of Counterinsurgency in Iraq;Berman Eli;Journal of Political Economy,2011

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3