Public Riots in Twitter: Domain-Based Event Filtering During Civil Unrest

Arturo Oncevay, Marco Sobrevilla, Hugo Alatrista-Salas, Andrés Melgar

Research output: Chapter in Book/Report/Conference proceedingChapter

1 Scopus citations

Abstract

Civil unrest is public manifestations, where people demonstrate their position for different causes. Sometimes, violent events or riots are unleashed in this kind of events, and these can be revealed from tweets posted by involved people. This study describes a methodology to detect riots within the time of a protest to identify potential adverse developments from tweets. Using two own datasets related to a violent and non-violent protest in Peru, we applied temporal clustering to obtain events and identify a tweet headline per cluster. We then extracted relevant terms for the scoring and ranking process using a different domain and contrast corpus built from different sources. Finally, we filtered the relevant events for the violence domain by using a contrast evaluation between the two datasets. The obtained results highlight the adequacy of the proposed approach.
Original languageEnglish
Title of host publicationADBIS, TPDL and EDA 2020 Common Workshops and Doctoral Consortium - International Workshops
Subtitle of host publicationDOING, MADEISD, SKG, BBIGAP, SIMPDA, AIMinScience 2020 and Doctoral Consortium, Proceedings
EditorsLadjel Bellatreche, Mária Bieliková, Omar Boussaïd, Jérôme Darmont, Barbara Catania, Elena Demidova, Fabien Duchateau, Mark Hall, Tanja Mercun, Maja Žumer, Boris Novikov, Christos Papatheodorou, Thomas Risse, Oscar Romero, Lucile Sautot, Guilaine Talens, Robert Wrembel
Pages49-59
Number of pages11
ISBN (Electronic)9783030558130
DOIs
StatePublished - 1 Jan 2020
EventCommunications in Computer and Information Science -
Duration: 1 Jan 2020 → …

Publication series

NameCommunications in Computer and Information Science
Volume1260 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

ConferenceCommunications in Computer and Information Science
Period1/01/20 → …

Bibliographical note

Publisher Copyright:
© 2020, Springer Nature Switzerland AG.

Keywords

  • Clustering
  • Event detection
  • Riot
  • Social media analysis

Fingerprint

Dive into the research topics of 'Public Riots in Twitter: Domain-Based Event Filtering During Civil Unrest'. Together they form a unique fingerprint.

Cite this