Please use this identifier to cite or link to this item: http://hdl.handle.net/10125/59667

Gradients of Fear and Anger in the Social Media Response to Terrorism

File Size Format  
0227.pdf 571.89 kB Adobe PDF View/Open

Item Summary

Title:Gradients of Fear and Anger in the Social Media Response to Terrorism
Authors:Baucum, Matthew
John, Richard
Keywords:Data Analytics, Data Mining and Machine Learning for Social Media
Digital and Social Media
emotion, social media, terrorism, text mining
Date Issued:08 Jan 2019
Abstract:Research suggests that public fear and anger in wake of a terror attack can each uniquely contribute to policy attitudes and risk-avoidance behaviors. Given the importance of these negative-valanced emotions, there is value in studying how terror events can incite fear and anger at various times and locations relative to an attack. We analyze 36,259 Twitter posts authored in response to the 2016 Orlando nightclub shooting and examined how fear- and anger-related language varied with time and distance from the attack. Fear-related words sharply decreased over time, though the trend was strongest at locations near the attack, while anger-related words slightly decreased over time and increased with distance from Orlando. Comparing these results to users’ pre-attack emotional language suggested that distant users remained both angry and fearful after the shooting, while users close to the attack remained angry but quickly reduced expressions of fear to pre-attack levels.
Pages/Duration:10 pages
URI:http://hdl.handle.net/10125/59667
ISBN:978-0-9981331-2-6
DOI:10.24251/HICSS.2019.276
Rights:Attribution-NonCommercial-NoDerivatives 4.0 International
https://creativecommons.org/licenses/by-nc-nd/4.0/
Appears in Collections: Data Analytics, Data Mining and Machine Learning for Social Media


Please email libraryada-l@lists.hawaii.edu if you need this content in ADA-compliant format.

This item is licensed under a Creative Commons License Creative Commons