Social network behavior and public opinion manipulation

2022 ◽  
Vol 64 ◽  
pp. 103060
Author(s):  
Long Chen ◽  
Jianguo Chen ◽  
Chunhe Xia
Comunicar ◽  
2018 ◽  
Vol 26 (55) ◽  
pp. 39-48 ◽  
Author(s):  
María-Elena Meneses ◽  
Alejandro Martín-del-Campo ◽  
Héctor Rueda-Zárate

This article aims to identify how digital public opinion was articulated on Twitter during the visit of the Republican presidential candidate Donald Trump to Mexico City in 2016 by invitation from the Mexican government, which was preceded by the threat to construct a border wall that Mexico would pay for. Using a mixed methodology made up of computational methods such as data mining and social network analysis combined with content analysis, the authors identify conversational patterns and the structures of the net-works formed, beginning with this event involving the foreign policy of both countries that share a long border. The authors study the digital media practices and emotional frameworks these social network users employed to involve themselves in the controversial visit, marked by complex political, cultural and historical relations. The analysis of 352,203 tweets in two languages (English and Spanish), those most used in the conversations, opened the door to an understanding as to how transnational public opinion is articulated in connective actions detonated by newsworthy events in distinct cultural contexts, as well as the emotional frameworks that permeated the conversation, whose palpable differences show that Twitter is not a homogeneous universe, but rather a set of universes co-determined by sociocultural context. El presente artículo busca identificar cómo se articuló la opinión pública digital en la red social Twitter durante la visita del entonces candidato republicano Donald Trump a la Ciudad de México en el año 2016 por invitación del gobierno mexicano que fue precedida de la amenaza de construir un muro fronterizo que pagaría México. Mediante una metodología mixta compuesta por métodos computacionales tales como minería de datos y análisis de redes sociales combinado con análisis de contenido se identifican los patrones de la conversación y las estructuras de redes que se conformaron a partir de este acontecimiento de la política exterior de ambas naciones que comparten una extensa frontera. Se estudiaron las prácticas mediáticas digitales y los encuadres emocionales con los cuales los usuarios de esta red social se involucraron en la controversial visita marcada por una compleja relación política, cultural e histórica. El análisis de 352.203 tuits en dos idiomas (inglés y español), los más utilizados en las conversaciones, permitió comprender cómo se articula la opinión pública transnacional en acciones conectivas detonadas por eventos noticiosos en contextos culturales distintos, así como los encuadres emocionales que permearon la conversación, cuyas diferencias palpables demuestran que cuando se habla de Twitter no se trata de un universo homogéneo, sino de un conjunto de universos codeterminados por el contexto sociocultural.


2014 ◽  
Vol 513-517 ◽  
pp. 2394-2397
Author(s):  
Hong Biao Xie ◽  
Hong Jun Qiu

Public opinion refers to the certain social groups subjective reflection of certain social phenomena and reality within a period of time. The important measures to maintain social stability and the ruling party's ruling safety are to instantly master the dynamic public opinion and to actively guide social public opinion. In this paper, the author found the model of social network public opinion hotspot issues. The SVM algorithm is adopted to improve the information processing and analysis testing, effectively resolving the text classification problem. It verifies that this method plays an important role in the hot issues analyses of the network link.


2020 ◽  
Vol 93 ◽  
pp. 103690 ◽  
Author(s):  
Cheng Gong ◽  
Yajun Du ◽  
Xianyong Li ◽  
Xiaoliang Chen ◽  
Xiaoying Li ◽  
...  

Author(s):  
Anaëlle Wilczynski

This article deals with strategic voting under incomplete information. We propose a descriptive model, inspired by political elections, where the information about the vote intentions of the electorate comes from public opinion polls and a social network, modeled as a graph over the voters. The voters are assumed to be confident in the poll and they update the communicated results with the information they get from their relatives in the social network. We consider an iterative voting model based on this behavior and study the associated “poll-confident” dynamics. In this context, we ask the question of manipulation by the polling institute.


2020 ◽  
Vol 3 (2) ◽  
pp. 12
Author(s):  
Miguel Martín Cárdaba ◽  
Rafael Carrasco Polaino ◽  
Ubaldo Cuesta Cambra

The popularization of Internet and the rise of social networks have offered an unbeatable opportunity for anti-vaccines, especially active communicators, to spread their message more effectively causing a significant impact on public opinion. A great amount of research has been carried out to understand the behavior that anti-vaccine communities show on social networks. However, it seems equally relevant to study the behavior that communities and communicators “pro vaccines” perform in these networks. Therefore, the objective of this research has been to study how members of the Spanish Association of Health Journalist (ANIS) communicate and use the social network Twitter. More specifically, the different interactions made by ANIS partners were analyzed through the so-called “centrality measures of social network analysis” (SNA), to check the configuration of the user network and detect those most relevant by their indexes of centrality, intermediation or mentions received. The research monitored 142 twitter accounts for one year analyzing 254 twits and their 2.671 interactions. The research concluded that the network of ANIS partners on Twitter regarding vaccines has little cohesion and has several components not connected to each other, in addition to the fact that there are users outside the association that show greater relevance than the partners themselves. We also concluded that there are an important lack of planning and direction in the communication strategy of ANIS on Twitter, which limits the dissemination of important content.


2019 ◽  
Vol 60 (3) ◽  
pp. 1015-1027 ◽  
Author(s):  
Gengxin Sun ◽  
Sheng Bin ◽  
Meng Jiang ◽  
Ning Cao ◽  
Zhiyong Zheng ◽  
...  

2021 ◽  
Author(s):  
Muhammad Luqman Jamil ◽  
Sebastião Pais ◽  
João Cordeiro ◽  
Gaël Dias

Abstract Online social networking platforms allow people to freely express their ideas, opinions, and emotions negatively or positively. Previous studies have examined user’s sentiments on these platforms to study their behaviour in different contexts and purposes. The mechanism of collecting public opinion information has attracted researchers to automatically classify the polarity of public opinions based on the use of concise language in messages, such as tweets, by analyzing social media data. In this paper, we extend the preceding work [1], by proposing an unsupervised approach to automatically detect extreme opinions/posts in social networks. We have evaluated our performance on five different social network and media datasets. In this work, we use the semi-supervised approach BERT to check the accuracy of our classified dataset. The latter task shows that, in these datasets, posts that were previously classified as negative or positive are, in fact, extremely negative or positive in many cases.


Sign in / Sign up

Export Citation Format

Share Document