Skip to main content
Top

18-11-2024 | Research

Fake News Detection in Large-Scale Social Network with Generalized Bayesian Classification

Authors: Wei Zhang, Ahmed Ibrahim Alzahrani, Mi Young Lee

Published in: Mobile Networks and Applications

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

Fake news in large-scale social networks is relatively rare, resulting in poor detection performance of deep learning method without sufficient samples. Meantime, false information comes from various sources and forms in large-scale social networks, which increases the difficulty of detection by simple Bayesian decision. Therefore, a method for detecting fake news in large-scale social networks based on a generalized Bayesian classifier is proposed. By using web crawlers to collect news in social network from multiple platforms such as entertainment, education, and medical diseases, and employing the HITS (Hyperlink-Induced Topic Search) algorithm to analyze webpage links, the accuracy of webpage target data retrieval is improved. A network data cleaning function is utilized to remove redundant and cluttered data from social network. A multi-modal Transformer model is employed to extract fusion features of text and image from large-scale social network data. By optimizing the Bayesian classifier using a greedy selection algorithm, a generalized Bayesian classifier is obtained. The extracted features of fake news from social networks are used as inputs to the generalized Bayesian classifier to obtain the prior probability of fake news in social networks. Based on this prior probability, evidence factors that meet the conditions of fake news in large-scale social networks are obtained. By evaluating the numerical values of these evidence factors, the classification and detection of fake news in large-scale social networks are achieved. Experimental results show that the maximum KL divergence value of the proposed method is 0.01, and the maximum Gini coefficient value is 0.1, indicating excellent performance in information cleaning and feature extraction. The maximum number of false positive results is only one sample, demonstrating its ability to accurately detect Fake News in social networks.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Show more products
Literature
1.
go back to reference Bhattacharjee S, Das SK (2023) Building a unified data falsification threat landscape for internet of things/cyberphysical systems applications. Computer 56(3):20–31CrossRef Bhattacharjee S, Das SK (2023) Building a unified data falsification threat landscape for internet of things/cyberphysical systems applications. Computer 56(3):20–31CrossRef
2.
go back to reference Alghamdi J, Lin Y, Luo S (2023) Towards COVID-19 fake news detection using transformer-based models. Knowl-Based Syst 274:110642CrossRef Alghamdi J, Lin Y, Luo S (2023) Towards COVID-19 fake news detection using transformer-based models. Knowl-Based Syst 274:110642CrossRef
3.
go back to reference James S (2021) How to Quarantine Fake News: What the U.S. Government May Do as Fake News Spread on Social Media during a Public Health Crisis Becomes a Biosecurity Threat. Journal of Biosecurity, Biosafety, and Biodefense Law 12(1):93–114CrossRef James S (2021) How to Quarantine Fake News: What the U.S. Government May Do as Fake News Spread on Social Media during a Public Health Crisis Becomes a Biosecurity Threat. Journal of Biosecurity, Biosafety, and Biodefense Law 12(1):93–114CrossRef
4.
go back to reference Khan A, Brohman K, Addas S (2022) The anatomy of ‘fake news’: Studying false messages as digital objects. J Inf Technol 37(2):122–143CrossRef Khan A, Brohman K, Addas S (2022) The anatomy of ‘fake news’: Studying false messages as digital objects. J Inf Technol 37(2):122–143CrossRef
5.
go back to reference Sepúlveda-Torres R, Vicente M, Saquete E, Lloret E, Palomar M (2023) “Leveraging relevant summarized information and multi-layer classification to generalize the detection of misleading headlines. Data Knowl Eng 145:102176CrossRef Sepúlveda-Torres R, Vicente M, Saquete E, Lloret E, Palomar M (2023) “Leveraging relevant summarized information and multi-layer classification to generalize the detection of misleading headlines. Data Knowl Eng 145:102176CrossRef
7.
go back to reference Qureshi KA, Malick RAS, Sabih M, Cherifi H (2022) Deception detection on social media: a source-based perspective. Knowl-Based Syst 256:109649CrossRef Qureshi KA, Malick RAS, Sabih M, Cherifi H (2022) Deception detection on social media: a source-based perspective. Knowl-Based Syst 256:109649CrossRef
8.
go back to reference Yasir Babiker Hamdan & Sathish (2021) Faultless decision making for fake news in online: a systematic approach. Journal of Soft Computing Paradigm 2(4):226–235CrossRef Yasir Babiker Hamdan & Sathish (2021) Faultless decision making for fake news in online: a systematic approach. Journal of Soft Computing Paradigm 2(4):226–235CrossRef
9.
go back to reference Thaher T, Saheb M, Turabieh H, Chantar H (2021) Intelligent detection of fake news in arabic tweets utilizing hybrid harris hawks based feature selection and machine learning models. Symmetry 13(4):556CrossRef Thaher T, Saheb M, Turabieh H, Chantar H (2021) Intelligent detection of fake news in arabic tweets utilizing hybrid harris hawks based feature selection and machine learning models. Symmetry 13(4):556CrossRef
10.
go back to reference Weiss AP, Alwan A, Garcia EP, Kirakosian AT (2021) Toward a comprehensive model of fake news: a new approach to examine the creation and sharing of fake news. Societies 11(3):82CrossRef Weiss AP, Alwan A, Garcia EP, Kirakosian AT (2021) Toward a comprehensive model of fake news: a new approach to examine the creation and sharing of fake news. Societies 11(3):82CrossRef
11.
go back to reference Liang Y, Turdi T, Askar H (2023) Multi-modal false information detection via multi-layer CNN-based feature fusion and multi-classifier hybrid prediction. Computer Engineering & Science 45(06):1087–1096 Liang Y, Turdi T, Askar H (2023) Multi-modal false information detection via multi-layer CNN-based feature fusion and multi-classifier hybrid prediction. Computer Engineering & Science 45(06):1087–1096
12.
go back to reference Sharma U, Singh J (2024) A comprehensive overview of fake news detection on social networks. Soc Netw Anal Min 14(1):1–25CrossRef Sharma U, Singh J (2024) A comprehensive overview of fake news detection on social networks. Soc Netw Anal Min 14(1):1–25CrossRef
13.
go back to reference Sridhar A, Poor HV (2023) Quickest inference of network cascades with noisy information. IEEE Trans Inf Theory 69(4):2494–2522MathSciNetCrossRef Sridhar A, Poor HV (2023) Quickest inference of network cascades with noisy information. IEEE Trans Inf Theory 69(4):2494–2522MathSciNetCrossRef
14.
go back to reference Wei W, Liu S, Li W, Atiquzzaman M, Li S, Du D (2018) Fractal intelligent privacy protection in online social network using attribute-based encryption schemes. IEEE Trans Comput Social Syst 5(3):736–747CrossRef Wei W, Liu S, Li W, Atiquzzaman M, Li S, Du D (2018) Fractal intelligent privacy protection in online social network using attribute-based encryption schemes. IEEE Trans Comput Social Syst 5(3):736–747CrossRef
15.
go back to reference Hossain NUI, Sakib N, Govindan K (2022) Assessing the performance of unmanned aerial vehicle for logistics and transportation leveraging the Bayesian network approach. Expert Syst Appl 209:118301CrossRef Hossain NUI, Sakib N, Govindan K (2022) Assessing the performance of unmanned aerial vehicle for logistics and transportation leveraging the Bayesian network approach. Expert Syst Appl 209:118301CrossRef
16.
go back to reference Amezaga HA, Shafiq MO (2022) A modified attention mechanism powered by Bayesian Network for user activity analysis and prediction. Data Knowl Eng 140:102034CrossRef Amezaga HA, Shafiq MO (2022) A modified attention mechanism powered by Bayesian Network for user activity analysis and prediction. Data Knowl Eng 140:102034CrossRef
17.
go back to reference Asadayoobi N, Taghipour S, Jaber MY (2022) Predicting human reliability based on probabilistic mission completion time using Bayesian Network. Reliab Eng Syst Saf 221:108324CrossRef Asadayoobi N, Taghipour S, Jaber MY (2022) Predicting human reliability based on probabilistic mission completion time using Bayesian Network. Reliab Eng Syst Saf 221:108324CrossRef
18.
go back to reference Lu X, Piao C, Yang X, Bai Y (2024) Research on differential privacy high dimensional data publishing technology based on Bayesian networks. Comput Eng 50(5):167–181 Lu X, Piao C, Yang X, Bai Y (2024) Research on differential privacy high dimensional data publishing technology based on Bayesian networks. Comput Eng 50(5):167–181
19.
go back to reference Ozaydin E, Fiskin R, Ugurlu O, Wang J (2022) A hybrid model for marine accident analysis based on bayesian network (BN) and association rule mining (arm). Ocean Eng 247(Mar.1):110705CrossRef Ozaydin E, Fiskin R, Ugurlu O, Wang J (2022) A hybrid model for marine accident analysis based on bayesian network (BN) and association rule mining (arm). Ocean Eng 247(Mar.1):110705CrossRef
20.
go back to reference Ehsani MR, Shafieefar M, Akbari H (2022) A probabilistic approach to predict wave force on a caisson breakwater based on Bayesian regression and experimental data. Ocean Eng 249:110945CrossRef Ehsani MR, Shafieefar M, Akbari H (2022) A probabilistic approach to predict wave force on a caisson breakwater based on Bayesian regression and experimental data. Ocean Eng 249:110945CrossRef
21.
go back to reference Ling TF, Kang YK (2022) Secure transmission of network classified information based on extended Bayes classification. Comp Simul 9(8):377–382 Ling TF, Kang YK (2022) Secure transmission of network classified information based on extended Bayes classification. Comp Simul 9(8):377–382
22.
go back to reference Moral-García S, Castellano JG, Mantas CJ, Abellán J (2022) Using extreme prior probabilities on the Naive Credal Classifier. Knowledge-Based Syst 237:107707CrossRef Moral-García S, Castellano JG, Mantas CJ, Abellán J (2022) Using extreme prior probabilities on the Naive Credal Classifier. Knowledge-Based Syst 237:107707CrossRef
23.
go back to reference Alotaibi A, Hamdaoui R (2021) Improvement of semi-supervised document classification based on fine tuning Naive Bayesian classifier. Eur J Sci Res 158(3):181–190 Alotaibi A, Hamdaoui R (2021) Improvement of semi-supervised document classification based on fine tuning Naive Bayesian classifier. Eur J Sci Res 158(3):181–190
24.
go back to reference Zhou C, Liu Y, Meng X (2024) Social network user influence evaluation model based on Bayesian derived classifier. Comput Eng 50(6):394–400 Zhou C, Liu Y, Meng X (2024) Social network user influence evaluation model based on Bayesian derived classifier. Comput Eng 50(6):394–400
Metadata
Title
Fake News Detection in Large-Scale Social Network with Generalized Bayesian Classification
Authors
Wei Zhang
Ahmed Ibrahim Alzahrani
Mi Young Lee
Publication date
18-11-2024
Publisher
Springer US
Published in
Mobile Networks and Applications
Print ISSN: 1383-469X
Electronic ISSN: 1572-8153
DOI
https://doi.org/10.1007/s11036-024-02436-3