Social Media Analysis of User’s Responses to Terrorism Using Sentiment Analysis and Text Mining

Autor: Samah Mansour
Rok vydání: 2018
Předmět:
Zdroj: Procedia Computer Science. 140:95-103
ISSN: 1877-0509
DOI: 10.1016/j.procs.2018.10.297
Popis: The Islamic State of Iraq and Syria (ISIS) has attracted the world’s attention because of its spread in Iraq and Syria and its brutal treatment of people. At this point, there is no enough research about if people in both the Western and Eastern countries view ISIS as a terrorist organization and a source of fear or they view it differently. Recently, social media has become important for social networking and content sharing. Twitter is a microblogging website that allows users to share short text messages, also known as tweets, with up to 140 characters. This research uses twitter to conduct text mining and sentiment analysis to examine if there is a difference between people from the Western countries and the Eastern countries on how they view ISIS. To accomplish this goal, Twitter’s API was used to search and collect tweets about ISIS from eight different countries. Moreover, term frequency- inverse document frequency (TF-IDF) technique was used to conduct the text sentiment analysis using R. The results of the sentiment analysis of the tweets indicated that: (1) the people used almost the same words when they are tweeting about ISIS, (2) sharing the same positive and negative words reflects how people think about this organization as a group of terrorists regardless the country they are from and (3) most users view ISIS as a source of threat and fear regardless where they are from.
Databáze: OpenAIRE