A Social Network Analysis–based approach to investigate user behaviour during a cryptocurrency speculative bubble

Bonifazi, Gianluca; Corradini, Enrico; Ursino, Domenico; Virgili, Luca

doi:10.1177/01655515211047428

Cited by 15 publications

(6 citation statements)

References 42 publications

(55 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…− the emergence of an information "bubble" from user preferences that distorts the perception of the real information panorama, e.g. revealed in the research of Bonifazi et al (2023); − low protection of personal information and privacy of the social networks use; especially vulnerable groups of users being younger children and teenagers, e.g. found in research by Chou and Chou (2023); − a surge in polarization and the emergence of conflicts based on multifarious factors such as political beliefs, race, gender, ethnicity, and social class among its users, e.g.…”

Section: Literature Reviewmentioning

confidence: 99%

La evolución prospectiva de las redes sociales desde la perspectiva de la neurofenomenología

Sharypin,

Galushko,

Stavroiani

et al. 2024

Telos

View full text Add to dashboard Cite

The purpose of the present article is to identify neurophenomenological aspects that influence the future development of social networks and to develop a corresponding concept of regulatory policy. The following methods are used in the article: collection and analysis of information, modeling of a conditional social network, systematization and separation of neurophenomenological factors, determination of functional dependencies, development of analytical conclusions and proposals. It was established that instigators and a favorable environment of social networks form prerequisites for the spread of negative information campaigns (conditional attacks). At the same time, it is mathematically proven that with minimal development of resistance to information attacks among users of social media platforms, the potential for stabilizing the information environment of social networks and promoting sustainable advancement of natural society was determined. Based on the research results, it was determined that fostering critical thinking skills, maintaining information stability, and practicing sound personal digital hygiene among users are key factors in upholding the overall stability of social networks. Additionally, these practices promote sustainable development of a psychologically healthy community. Additional investigations are focused on elaborating the notion of regulatory policy to facilitate the prospective advancement of social networks.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

La evolución prospectiva de las redes sociales desde la perspectiva de la neurofenomenología

Sharypin,

Galushko,

Stavroiani

et al. 2024

Telos

View full text Add to dashboard Cite

show abstract

“…Because it avoids the use of scaling functions, this result is different from those of other studies. In a recent paper [13], it proposed a general method of user behavior analysis and knowledge pattern extraction based on social network analysis. This method extracts relevant information from the blockchain transaction data in a specified period, carries out statistics and builds an ego network, and extracts important information such as active transaction addresses and different user groups.…”

Section: Related Workmentioning

confidence: 99%

A Stacking Ensemble Deep Learning Model for Bitcoin Price Prediction Using Twitter Comments on Bitcoin

Chen

et al. 2022

Mathematics

View full text Add to dashboard Cite

Cryptocurrencies can be considered as mathematical money. As the most famous cryptocurrency, the Bitcoin price forecasting model is one of the popular mathematical models in financial technology because of its large price fluctuations and complexity. This paper proposes a novel ensemble deep learning model to predict Bitcoin’s next 30 min prices by using price data, technical indicators and sentiment indexes, which integrates two kinds of neural networks, long short-term memory (LSTM) and gate recurrent unit (GRU), with stacking ensemble technique to improve the accuracy of decision. Because of the real-time updates of comments on social media, this paper uses social media texts instead of news websites as the source data of public opinion. It is processed by linguistic statistical method to form the sentiment indexes. Meanwhile, as a financial market forecasting model, the model selects the technical indicators as input as well. Real data from September 2017 to January 2021 is used to train and evaluate the model. The experimental results show that the near-real time prediction has a better performance, with a mean absolute error (MAE) 88.74% better than the daily prediction. The purpose of this work is to explain our solution and show that the ensemble method has better performance and can better help investors in making the right investment decision than other traditional models.

show abstract

“…Social network analysis is a quantitative analysis method developed by sociologists utilising mathematical methods and graph theory to study the relationship between social actors. In the network community, the social network analysis method explores the topological structure characteristics of user networks and analyzes the impact of knowledge sharing and information dissemination [40][41][42]. Its core indicators include degree centrality, betweenness centrality and average clustering coefficient.…”

Section: Social Network Analysis Of Blockchain Information Disseminat...mentioning

confidence: 99%

Research on information dissemination of blockchain network community under the action of negative incentive mechanism

Xie

Zhang

2022

Journal of Information Science

View full text Add to dashboard Cite

Traditional online communities suffer from false, repetitive or low-level content, with blockchain technology able to solve these problems. Specifically, the incentive mechanism is the blockchain’s core value, including positive and negative incentive mechanisms. The former strengthens people’s behaviour positively, while the latter, on the contrary, adopts mandatory methods such as punishment to eliminate the occurrence of certain types of behaviour. The negative incentive mechanism is the key factor to solve the problems presented above that traditional online communities face. Specifically, this article develops a solution that utilises the negative incentive mechanism, based on the classic infectious disease model (SIR model), introduces smart nodes, puts forward the SSIR model of information dissemination in the blockchain network community, and establishes a set of differential equations reflecting the information dissemination rules. Based on the parameter assumption and solving the equations with MATLAB, this article compares and reveals the changes of different user types on the SIR and SSIR models. Furthermore, we utilise the data collected from the Steemit blockchain community and Sina Weibo platform and apply the Social Network Analysis method to compare and analyse the information dissemination between the blockchain and the traditional network community. The research results highlight that the negative incentive mechanism in the blockchain network community affords a more rational behaviour of user information dissemination, a simpler interaction between users, and reducing to a certain extent the dissemination of ‘distorted’ or ‘uncertain’ information.

show abstract

A Social Network Analysis–based approach to investigate user behaviour during a cryptocurrency speculative bubble

Cited by 15 publications

References 42 publications

La evolución prospectiva de las redes sociales desde la perspectiva de la neurofenomenología

La evolución prospectiva de las redes sociales desde la perspectiva de la neurofenomenología

A Stacking Ensemble Deep Learning Model for Bitcoin Price Prediction Using Twitter Comments on Bitcoin

Research on information dissemination of blockchain network community under the action of negative incentive mechanism

Contact Info

Product

Resources

About