Projection of Socio-Linguistic markers in a semantic context and its application to online social networks
Projection of Socio-Linguistic markers in a semantic context and its application to online social networks
StatusVoR
Alternative title
Authors
Erseghe, Tomaso
Badia, Leonardo
Džanko, Lejla
Formanowicz, Magdalena
Nikadon, Jan
Suitner, Caterina
Monograph
Monograph (alternative title)
Date
2023-10-22
Publisher
Journal title
Online Social Networks and Media
Issue
Volume
37-38
Pages
Pages
1-12
ISSN
2468-6964
ISSN of series
Access date
2023-10-22
Abstract PL
Abstract EN
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.
Abstract other
Keywords PL
Keywords EN
Data analysis
Computational linguistics
Projection algorithms
Social networking
Sociology–Psychology
#FridaysForFuture
#MeToo
#Covid 19
Computational linguistics
Projection algorithms
Social networking
Sociology–Psychology
#FridaysForFuture
#MeToo
#Covid 19