Social media analysis is a fast growing research area aimed at extracting useful information from social media. Several opinion mining techniques have been developed for capturing the mood of social media users related to a specific topic of interest. This paper shows how to use a cloud-based algorithm aimed at discovering the polarization of social media users in relation to political events characterized by the rivalry of different factions. The algorithm has been applied to a case study that analyzes the polarization of a large number of Twitter users during the 2016 Italian constitutional referendum. In particular, Twitter users have been classified and the results have been compared with the polls before voting and with the results obtained after the vote. The achieved results are very close to the real ones.

Developing a Cloud-Based Algorithm for Analyzing the Polarization of Social Media Users

Belcastro L.;Marozzo F.;Talia D.;Trunfio P.
2019

Abstract

Social media analysis is a fast growing research area aimed at extracting useful information from social media. Several opinion mining techniques have been developed for capturing the mood of social media users related to a specific topic of interest. This paper shows how to use a cloud-based algorithm aimed at discovering the polarization of social media users in relation to political events characterized by the rivalry of different factions. The algorithm has been applied to a case study that analyzes the polarization of a large number of Twitter users during the 2016 Italian constitutional referendum. In particular, Twitter users have been classified and the results have been compared with the polls before voting and with the results obtained after the vote. The achieved results are very close to the real ones.
978-3-030-58627-0
978-3-030-58628-7
Big Data
Cloud computing
Sentiment analysis
Social data analysis
User polarization
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.11770/328697
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? ND
social impact