Modeling Influence with Semantics in Social Networks

Razis, Gerasimos; Anagnostopoulos, Ioannis; Zeadally, Sherali

doi:10.1145/3369780

Cited by 17 publications

(8 citation statements)

References 120 publications

(245 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Numerous studies have focused on identifying indicators to measure influence on Twitter (Riquelme & González-Cantergiani, 2016;Razis, Anagnostopoulos & Zeadally, 2018). However, there is a lack of research on the application of these indicators to the media system.…”

Section: Discussionmentioning

confidence: 99%

“…Within the social media framework, this influence can be understood as the ability to control the information flow (Cha et al, 2010;Azaza et al, 2016), and influence the interactions that occur among the actors that make up a network (Leavitt et al, 2009) Despite the vast amount of data produced by digital platforms, digital influence is a difficult concept to measure since it is complex and multidimensional and does not consist of a single variable. Therefore, the indicators and formulas proposed for their detection and measurement are diverse (Riquelme & González-Cantergiani, 2016;Razis, Anagnostopoulos & Zeadally, 2018) which allow, in addition, to identify the most relevant and influential users in a social network. The literature has identified three major types of indicators that can be useful in determining the influence of the actors present in social media, specifically on Twitter: activity, popularity, and authority (Riquelme & González-Cantergiani, 2016).…”

Section: Social Influence In the Era Of Social Media: Activity Populmentioning

confidence: 99%

See 1 more Smart Citation

Influencia de los medios de comunicación en la conversación política en Twitter

Casero-Ripollés

2020

icono14

View full text Add to dashboard Cite

Tradicionalmente, los medios de comunicación (periódicos, cadenas de televisión, radio y agencias de noticias) han tenido una gran influencia en la sociedad, pero su papel está cambiando ante la aparición del entorno digital. Aunque sabemos mucho sobre cómo medir la influencia digital, todavía tenemos poca evidencia de cómo se ejerce en los medios sociales. Para revertir este déficit, se utilizan grandes técnicas de datos en una muestra de 127,3 millones de tweets para conocer cuáles fueron los más influyentes en el debate político sobre Twitter en España. A través de una metodología basada en el aprendizaje automático y el análisis de redes sociales, se identifican los medios de comunicación más influyentes en función de su naturaleza, tipo, posición ideológica percibida y cobertura territorial. Para ello se utilizan tres indicadores de influencia digital: actividad, popularidad y autoridad. Los resultados indican que el ejercicio de influencia sobre Twitter dentro del sistema de medios se está reconfigurando en profundidad. Asimismo, los datos revelan la incidencia de la posición ideológica percibida de los medios de comunicación, cuando se trata de tener más o menos centralidad en la red y poder influir en las interacciones en Twitter. Finalmente, aunque los medios de comunicación registran altos valores de inactividad y popularidad, generalmente obtienen valores intermedios o bajos de autoridad. Esta falta de autoridad cuestiona el poder de los medios de comunicación para influir efectivamente en el debate político en Twitter.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Social Influence In the Era Of Social Media: Activity Populmentioning

confidence: 99%

Influencia de los medios de comunicación en la conversación política en Twitter

Casero-Ripollés

2020

icono14

View full text Add to dashboard Cite

show abstract

“…A hierarchical classification scheme is proposed in a survey paper which depicts that quantitative assessment methods-influence metrics, information flow and influence model (including machine learning models), network/ graph properties exist in literature to model social influence. Even, qualitative assessment is also possible using social modelling, social matching, and community detection (Razis, Anagnostopoulos, & Zeadally, 2018).…”

Section: Regression Modellingmentioning

confidence: 99%

Measuring social media influencer index- insights from facebook, Twitter and Instagram

Arora

Bansal²,

Kandpal³

et al. 2019

Journal of Retailing and Consumer Services

429

198

View full text Add to dashboard Cite

The growth of social media has completely revamped the way people interact, communicate and engage. These platforms play a key role in facilitating greater outreach and influence. This study proposes a mechanism for measuring the influencer index across popular social media platforms including Facebook, Twitter, and Instagram. A set of features that determine the impact on the consumers are modelled using a regression approach. The underlying machine learning algorithms including Ordinary Least Squares (OLS), K-NN Regression (KNN), Support Vector Regression (SVR), and Lasso Regression models are adapted to compute a cumulative score in terms of influencer index. Findings indicate that engagement, outreach, sentiment, and growth play a key role in determining the influencers. Further, the ensemble of the four models resulted in the highest accuracy of 93.7% followed by the KNN regression with 93.6%. The study has implications across various domains of e-commerce, viral marketing, social media marketing and brand management wherein identification of key information propagators is essential. These influencer indices may further be utilized by e-commerce portals and brands for the purpose of social media promotion and engagement for larger outreach.

show abstract

“…The vast data associated with SNS makes isolating influence difficult, however, there is evidence of not only state sponsored influence, but individuals determined on shaping the nature of SNS and the populations that engage with SNS [7]. Extensive research has already surveyed and defined the hierarchical schema of SNS [8] which have been used in various research studies, for example, text mining research to explore the trending or popular actions [9]. Studies have also defined areas for potential future research [10], while others have applied semantic analysis of SNS to track and assess the influence of content shared across these platforms [11].…”

Section: Background and Related Workmentioning

confidence: 99%