Us Vs. Them – Understanding the Impact of Homophily in Political Discussions on Twitter - Inria - Institut national de recherche en sciences et technologies du numérique
Communication Dans Un Congrès Année : 2021

Us Vs. Them – Understanding the Impact of Homophily in Political Discussions on Twitter

Danula Hettiachchi
  • Fonction : Auteur
  • PersonId : 1286538

Résumé

Analysing homophily, i.e. people’s tendency to associate with others with similar social attributes, can help us unravel and better understand user behaviour in social media. In our work, we analyse the impact of homophily in discussions regarding the Citizenship Amendment Act (CAA) on Twitter. The Indian Government enacted CAA to provide relaxation in the citizenship process to religious minorities in three neighbouring countries. While it was lauded by many, it also fuelled backlash amongst some Indian citizens, resulting in the emergence of two distinctive political dispositions regarding this matter. We collected 78,004 Tweets, including 11,794 original Tweets during a period of two weeks shortly after the ruling, and examined ways of potentially reducing homophily and therefore minimise the presence of echo chambers. In particular, we investigated users’ political dispositions and expressed sentiment, and how these two social attributes influence homophilic social ties and interactions. Further, we discuss how our findings can be used in social networks to allow people with diverse viewpoints and emotional attitudes to interact with each other in a positive and constructive manner.
Fichier principal
Vignette du fichier
520518_1_En_27_Chapter.pdf (1.2 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04215496 , version 1 (22-09-2023)

Licence

Identifiants

Citer

Danula Hettiachchi, Tanay Arora, Jorge Goncalves. Us Vs. Them – Understanding the Impact of Homophily in Political Discussions on Twitter. 18th IFIP Conference on Human-Computer Interaction (INTERACT), Aug 2021, Bari, Italy. pp.476-497, ⟨10.1007/978-3-030-85610-6_27⟩. ⟨hal-04215496⟩
24 Consultations
49 Téléchargements

Altmetric

Partager

More