On the dynamics of political discussions on Instagram: A network perspective

Abstract

Instagram has been increasingly used as a source of information especially among the youth. As a result, political figures now leverage the platform to spread opinions and political agenda. We here analyze online discussions on Instagram, notably in political topics, from a network perspective. Specifically, we investigate the emergence of communities of co-commenters, that is, groups of users who often interact by commenting on the same posts and may be driving the ongoing online discussions. In particular, we are interested in salient co-interactions, i.e., interactions of co-commenters that occur more often than expected by chance and under independent behavior. Unlike casual and accidental co-interactions which normally happen in large volumes, salient co-interactions are key elements driving the online discussions and, ultimately, the information dissemination. We base our study on the analysis of 10 weeks of data centered around major elections in Brazil and Italy, following both politicians and other celebrities. We extract and characterize the communities of co-commenters in terms of topological structure, properties of the discussions carried out by community members, and how some community properties, notably community membership and topics, evolve over time. We show that communities discussing political topics tend to be more engaged in the debate by writing longer comments, using more emojis, hashtags and negative words than in other subjects. Also, communities built around political discussions tend to be more dynamic, although top commenters remain active and preserve community membership over time. Moreover, we observe a great diversity in discussed topics over time: whereas some topics attract attention only momentarily, others, centered around more fundamental political discussions, remain consistently active over time.

Mining and modelling temporal dynamics of followers’ engagement on online social networks

“…Our previous studies (Ferreira et al 2020 ; Ferreira et al. 2021 ) focus on the peculiarity of user interactions with political profiles on IG during the 2018 European and Brazilian elections, with the goal of identifying the structure emerging from the co-interactions. We studied the appearance and evolution of communities of users, obtained through a probabilistic model that extracts the backbone of the interaction networks.…”

Análise da Percepção das Pessoas no Twitter Sobre Ações Policiais

“…Assim, o crescente uso dessas plataformas tem chamado a atenc ¸ão de vários pesquisadores que visam modelar e analisar o comportamento dos usuários em face de fenômenos reais. Em particular, análises utilizando ferramentas de processamento natural de linguagem tem auxiliado na compreensão de diversos aspectos, por exemplo, relacionados a política [Ferreira et al 2021, Nobre et al 2022, pandemia [Malagoli et al 2021] e percepc ¸ão da seguranc ¸a urbana [Hand andChing 2020, Oglesby-Neal et al 2019]. Nesta sec ¸ão nós discutimos alguns destes esforc ¸os mais próximos deste trabalho.…”

Caracterização das publicações e relações entre mídias alternativas polarizadas no Facebook

“…No Whatsapp, [Nobre et al 2020] realizou a identificac ¸ão de comunidades a partir de semelhanc ¸as dos conteúdos de mensagens. [Ferreira et al 2021] modelou uma rede baseada na interac ¸ão entre usuários em publicac ¸ões no Instagram e realizou a identificac ¸ão de comunidades. Parte fundamental dos trabalhos mencionados é a extrac ¸ão de backbone, que é explorada em detalhes por [Coscia andNeffke 2017, Serrano et al 2009].…”

“…Para a formac ¸ão das arestas, foram desconsiderados pares de publicac ¸ões em que uma das postagens possuía menos de 180 caracteres. Ressalta-se que o coeficiente e o threshold utilizados bem como a desconsiderac ¸ão de postagens com textos curtos foram empregados em outras abordagens similares [Nobre et al 2022, Ferreira et al 2021, Nobre et al 2020].…”