Celebrity profiling through linguistic analysis of digital social networks

Abstract

Digital social networks have become an essential source of information because celebrities use them to share their opinions, ideas, thoughts, and feelings. This makes digital social networks one of the preferred means for celebrities to promote themselves and attract new followers. This paper proposes a model of feature selection for the classification of celebrities profiles based on their use of a digital social network Twitter. The model includes the analysis of lexical, syntactic, symbolic, participation, and complementary information features of the posts of celebrities to estimate, based on these, their demographic and influence characteristics. The classification with these new features has an F1-score of 0.65 in Fame, 0.88 in Gender, 0.37 in Birth year, and 0.57 in Occupation. With these new features, the average accuracy improve up to 0.14 more. As a result, extracted features from linguistic cues improved the performance of predictive models of Fame and Gender and facilitate explanations of the model results. Particularly, the use of the third person singular was highly predictive in the model of Fame.

A sustainability maturity model for micro, small and medium-sized enterprises (MSMEs) based on a data analytics evaluation approach

“…Once the iterations have been completed, the accuracy and error values of each model are calculated. Additional accuracy and final error values are obtained by calculating the corresponding averages of the k trained models (Fushiki, 2011;Klyueva, 2019;Moreno-Sandoval et al, 2019).…”

Hybrid Onion Layered System for the Analysis of Collective Subjectivity in Social Networks

“…Among them are the texts called publications, which form a corpus from which it is possible to extract highvalue information. [10] relate a group of linguistic features (lexical, syntactic, symbolic, participation, and complementary information) by analyzing the digital identity of the network actor from the collected corpus with the sociographic, demographic and psychographic characteristics of his real identity. In this way, the users' digital identities generate a research space that simultaneously studies the structure of the communities generated based on the interaction of the symbolic, participation, and complementary information features and the sentimental charges of the linguistic expressions in the lexical and syntactic features.…”

El análisis de subjetividad colectiva en redes sociales

“…En este sentido, COSSOL permite evaluar el comportamiento de los usuarios representado en lo que Moreno Sandoval et al (2021) denominan como rasgos de la identidad digital del usuario existentes en la red social tales como: publicaciones, hashtags, menciones, emojis, URLs y comentarios. De este modo, la evaluación realizada por el sistema COSSOL reconoce los vínculos estructurales en los que se comparten masivamente modos comunes de Pensar, Actuar y Sentir (PAS), denominados Subjetividad Colectiva.…”

“…3.2 Ingesta de datos y comentarios en redes sociales digitales 77 A continuación se examina un modelo tal como el propuesto por Moreno Sandoval et al (2021), el cual relaciona las características del actor de la red o usuario real con un grupo de rasgos lingüísticos que se pueden encontrar en las publicaciones disponibles en las redes sociales digitales. Las características de los usuarios reales son divididas en las categorías de demografía, sociografía y psicografía.…”