The automated parsing of 130,213 news articles about the 2012 US presidential elections produces a network formed by the key political actors and issues, which were linked by relations of support and opposition. The nodes are formed by noun phrases and links by verbs, directly expressing the action of one node upon the other. This network is studied by applying insights from several theories and techniques, and by combining existing tools in an innovative way, including: graph partitioning, centrality, assortativity, hierarchy and structural balance. The analysis yields various patterns. First, we observe that the fundamental split between the Republican and Democrat camps can be easily detected by network partitioning, which provides a strong validation check of the approach adopted, as well as a sound way to assign actors and topics to one of the two camps. Second, we identify the most central nodes of the political camps. We also learnt that Clinton played a more central role than Biden in the Democrat camp; the overall campaign was much focused on economy and rights; the Republican Party (Grand Old Party or GOP) is the most divisive subject in the campaign, and is portrayed more negatively than the Democrats; and, overall, the media reported positive statements more frequently for the Democrats than the Republicans. This is the first study in which political positions are automatically extracted and derived from a very large corpus of online news, generating a network that goes well beyond traditional word-association networks by means of richer linguistic analysis of texts. Big Datanetwork analysisstructural balancecomputational social sciencemediascapesubject-verb-object©

Automated analysis of the US presidential elections using Big Data and network analysis / Sudhahar, S.; Veltri, Giuseppe Alessandro; Cristianini, N.. - In: BIG DATA & SOCIETY. - ISSN 2053-9517. - 2:1(2015). [10.1177/2053951715572916]

Automated analysis of the US presidential elections using Big Data and network analysis

Veltri, Giuseppe Alessandro;
2015

Abstract

The automated parsing of 130,213 news articles about the 2012 US presidential elections produces a network formed by the key political actors and issues, which were linked by relations of support and opposition. The nodes are formed by noun phrases and links by verbs, directly expressing the action of one node upon the other. This network is studied by applying insights from several theories and techniques, and by combining existing tools in an innovative way, including: graph partitioning, centrality, assortativity, hierarchy and structural balance. The analysis yields various patterns. First, we observe that the fundamental split between the Republican and Democrat camps can be easily detected by network partitioning, which provides a strong validation check of the approach adopted, as well as a sound way to assign actors and topics to one of the two camps. Second, we identify the most central nodes of the political camps. We also learnt that Clinton played a more central role than Biden in the Democrat camp; the overall campaign was much focused on economy and rights; the Republican Party (Grand Old Party or GOP) is the most divisive subject in the campaign, and is portrayed more negatively than the Democrats; and, overall, the media reported positive statements more frequently for the Democrats than the Republicans. This is the first study in which political positions are automatically extracted and derived from a very large corpus of online news, generating a network that goes well beyond traditional word-association networks by means of richer linguistic analysis of texts. Big Datanetwork analysisstructural balancecomputational social sciencemediascapesubject-verb-object©
1
Sudhahar, S.; Veltri, Giuseppe Alessandro; Cristianini, N.
Automated analysis of the US presidential elections using Big Data and network analysis / Sudhahar, S.; Veltri, Giuseppe Alessandro; Cristianini, N.. - In: BIG DATA & SOCIETY. - ISSN 2053-9517. - 2:1(2015). [10.1177/2053951715572916]
File in questo prodotto:
File Dimensione Formato  
2053951715572916.pdf

accesso aperto

Tipologia: Versione editoriale (Publisher’s layout)
Licenza: Creative commons
Dimensione 4.62 MB
Formato Adobe PDF
4.62 MB Adobe PDF Visualizza/Apri

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: http://hdl.handle.net/11572/176265
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 32
  • ???jsp.display-item.citation.isi??? 21
social impact