Relevant socio-psychological processes can be detected in social networks thanks to an analysis of linguistic markers that sheds light on the characteristics and dynamics of the social discourse. Usually, linguistic markers comprise a list of words representative of a given construct; however, this approach does not account for contextual interdependencies of words, which can amplify or diminish the relevance of a particular word. In this paper, we present and leverage a scalable method called PageRank-like marker projection (PLMP) that addresses this problem. Its rationale, inspired by PageRank, is meant to fully exploit the interdependencies in a semantic network to project markers from a social discourse level (tweets) to its semantic elements (words). We show how PLMP is able to associate markers with specific words from their semantic context, which allows for an even richer interpretation of the online sentiment. We demonstrate the effectiveness of PLMP in practice by considering specific instances of social discourse on Twitter for three exemplary calls to collective action.

Projection of Socio-Linguistic markers in a semantic context and its application to online social networks

Erseghe T.;Badia L.;Suitner C.
2023

Abstract

Relevant socio-psychological processes can be detected in social networks thanks to an analysis of linguistic markers that sheds light on the characteristics and dynamics of the social discourse. Usually, linguistic markers comprise a list of words representative of a given construct; however, this approach does not account for contextual interdependencies of words, which can amplify or diminish the relevance of a particular word. In this paper, we present and leverage a scalable method called PageRank-like marker projection (PLMP) that addresses this problem. Its rationale, inspired by PageRank, is meant to fully exploit the interdependencies in a semantic network to project markers from a social discourse level (tweets) to its semantic elements (words). We show how PLMP is able to associate markers with specific words from their semantic context, which allows for an even richer interpretation of the online sentiment. We demonstrate the effectiveness of PLMP in practice by considering specific instances of social discourse on Twitter for three exemplary calls to collective action.
File in questo prodotto:
File Dimensione Formato  
2023_OSNAM.pdf

accesso aperto

Tipologia: Published (publisher's version)
Licenza: Creative commons
Dimensione 3.97 MB
Formato Adobe PDF
3.97 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

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/11577/3500460
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? 0
  • OpenAlex ND
social impact