ANALYSING PUBLIC PERCEPTIONS OF INTERNATIONAL EVENTS BY USING GEO-LOCATED TWITTER DATA

A. G. van der Vyver and Duncan Gillies
Additional contact information
A. G. van der Vyver: Monash, Johannesburg, South Africa
Duncan Gillies: Entelect, Johannesburg, South Africa

International Journal of Humanities, Arts and Social Sciences, 2017, vol. 3, issue 2, 64-70

Abstract: The growth in data generated by social media platforms like Twitter provides a wealth of potential information waiting to be extracted (or mined) - traditionally with a price tag. With the recent advancements in Open Source technologies, specifically Big Data, within the Information Technology world, businesses have started to gather as much information as possible about their customers and market space. The Big Data platform, Hadoop, has become extremely proficient at managing social media data ingestion, storage and processing, due to its ability to use both structured and unstructured data. The aim of this study is to demonstrate a Big Data environment running on Open Source technologies, in order to explore the possibilities of performing geo-located sentiment analytics on Twitter data. Subsequent to this, the link between events and changes in population sentiment was investigated. In this study, an average of 47% of the total tweets ingested were geo-locatable to a country. The Open Source Big Data software was able to demonstrate the reliability of the environment, as well as identify possible limitations to having an environment setup like the one used in this study. A number of research sub-questions were answered, one of which provided information suggesting causality between an event and the change in a populations sentiment when focusing on the events specific topic on Twitter. By performing sentiment analytics on the Twitter data, potential influential users were identifiable for each use case, while allowing additional analytics to be performed and so highlight themes and trends within the data. Three use cases will be concisely addressed in this paper. The first is the Oscar Pistorius Trial (legal), the second is the FIFA World Cup of 2014 (sport), and the last one, a movie titled Maze Runner.

Keywords: Public Percption; Social Media; Twitter; Big Data (search for similar items in EconPapers)
Date: 2017
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://kkgpublications.com/ijhss-v3-issue2-article-4/ (application/pdf)
https://kkgpublications.com/wp-content/uploads/2019/04/IJHSS.3.20004-2.pdf (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:apa:ijhass:2017:p:64-70

DOI: 10.20469/ijhss.3.20004-2

Access Statistics for this article

International Journal of Humanities, Arts and Social Sciences is currently edited by Dr. Mohammad Hamad Al-khresheh

More articles in International Journal of Humanities, Arts and Social Sciences from Dr. Mohammad Hamad Al-khresheh Calle Alarcon 66, Sant Adrian De Besos 08930, Barcelona Spain.
Bibliographic data for series maintained by Dr. Mohammad Hamad Al-khresheh ().