MODIFIED METHOD FOR DETECTING FAKE NEWS BASED ON MACHINE LEARNING ALGORITHMS

Authors

DOI:

https://doi.org/10.24025/2306-4412.2.2023.279984

Keywords:

algorithmic-software method, machine learning algorithms, methods of fake detection and recognition, BERT, LSTM, Passive-Aggressive Classifier

Abstract

The object of research is the process of analyzing information in social media to identify fake news. The subject of the research is the development of algorithmic-software method software for detecting fake news. The aim of the work is to increase the average accuracy of the process of detecting fake news in social media by developing and implementing an algorithmic-software method for detecting fake news based on machine learning algorithms. Various methods of scientific research were used: analysis to find out the advantages and disadvantages of existing methods for detecting fake news; comparison – when choosing the most optimal programming language and programming environment for developing software to detect fake news; a method of reviewing existing literature to detect fake news, including academic publications, technical reports, and online resources; peer review method, which obtained information on the effectiveness of various methods for detecting fake news. Using these methods, a comprehensive understanding of the problem of detecting fake news was obtained and effective software for detecting fake news was developed. The scientific novelty of the work lies in the fact that a modified algorithmic-software method for detecting fake news based on machine learning algorithms was proposed, which differs from the existing methods using an ensemble of three algorithms, the results of each of which are used to select more compact specialized models for subsequent algorithms, which ultimately allows speeding up the process of detecting fake news in the text by 30% compared to analogs, and reduce the average falsehood by 25%. The practical value of the results obtained in the work lies in the fact that the developed software of the algorithmic-software method for detecting fake news will help reduce the spread of fakes and help their detection.

Author Biographies

Anatolii Sanzharovskyi, National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute"

Master

Vasyl Yurchyshyn, National Technical University of Ukraine "Igor Sikorsky Kyiv Polytechnic Institute"

Cand. Tech. Sc., Associate Professor

References

А. Санжаровський, та В. Юрчишин, "Алгоритмічно-програмний метод для виявлення фейкових новин на основі алгоритмів машинного навчання", на П’ятнадцятій наук. конф. магістрантів та аспірантів Прикладна математика та комп’ютинг (ПМК-2022), Київ, 16-18 листоп. 2022, с. 499-504.

Study: On Twitter, false news travels faster than true stories. [Online]. Available: https://news.mit.edu/2018/study-twitter-false-news-travels-faster-true-stories-0308. Accessed on: Jan. 20, 2023.

Disinformation risk assessment: The online news market in the United States. [Online]. Available: https://www.disinformationindex.org/country-studies/2022-12-16-disinformation-risk-assessment-the-online-news-market-in-the-united-states/. Accessed on: Jan. 20, 2023.

H. Alcott, and M. Gentzkow, "Social media and fake news in the 2016 election", Journal of Economic Perspectives, vol. 31 (2), pp. 211-236. doi: 10.1257/jep.31.2.211.

K. Shu, A. Sliva, S. Wang, J. Tang, and H. Liu, "Fake news detection on social media: A data mining perspective", ACM SIGKDD Explorations Newsletter, vol. 19, iss. 101, pp. 22-36, Sept. 2017. doi: 10.1145/3137597.3137600.

K. Sharma, F. Qian, H. Jiang, and N. Ruchansky, "Combating fake news: A survey on identification and mitigation techniques", ACM Transactions on Intelligent Systems and Technology, vol. 10 (3), pp. 1-42, Apr. 2019. [Online]. Available: https://www.researchgate.net/publication/332434399_Combating_Fake_News_A_Survey_on_Identification_and_Mitigation_Techniques. Accessed on: Jan. 20, 2023. doi: 10.1145/3305260.

B. D. Horne, and S. Adali, "This just in: Fake news packs a lot in title, uses simpler, repetitive content in text body, more similar to satire than real news", ArXiv abs/1703.09398, 2017. [Online]. Available: https://www.semanticscholar.org/paper/This-Just-In%3A-Fake-News-Packs-a-Lot-in-Title%2C-Uses-Horne-Adali/f8366afaf58bbb9db151a1168bb6f14b618955b4. Accessed on: Jan. 20, 2023.

D. Rothman, "Transformers for natural language processing: Build innovative deep neural network architectures for NLP with Python, PyTorch, TensorFlow, BERT, RoBERTa, and more"; Birmingham, UK: Packt Publishing Ltd. Birmingham Mumbai, 2021.

P. Bahad, P. Saxena, and R. Kamal, "Fake news detection using bi-directional LSTMrecurrent neural network", Procedia Comput. Sci., vol. 165, pp. 74-82, 2019. [Online]. Available: https://doi.org/10.1016/j.procs.2020.01.072. Accessed on: Jan. 20,

S. M. Padnekar, G. S. Kumar, and P. Deepak, "Bilstm-autoencoder architecture for stance prediction", in Proc. 2020 Int. Conf. on Data Science and Engineering (ICDSE), Kochi, India, pp. 1-5, Dec. 3-5, 2020.

E. Amer, K.-S. Kwak, and S. El-Sappagh, "Context-based fake news detection model relying on deep learning models". Electronics, vol. 11 (8), p. 1255, 2022. [Online]. Available: https://doi.org/10.3390/electronics11081255. Accessed on: Jan. 20, 2023

A. Malakhov, A. Patruno, and S. Bocconi, "Fake news classification with BERT". [Online]. Available: http://ceur-ws.org/Vol-2882/paper38.pdf. Accessed on: Jan. 20, 2023.

D. Jacob, C. Ming-Wei, L. Kenton, and T. Kristina, "BERT: Pre-training of deep bidirectional transformers for language understanding". [Online]. Available: https://arxiv.org/pdf/1810.04805.pdf. Accessed on: Jan. 20, 2023.

Fake News Detection Using Passive-Aggressive Classifier. [Online]. Available: https://link.springer.com/chapter/10.1007/978-981-15-7345-3_13. Accessed on: Jan. 20, 2023.

D. Arthur, and S. Vassilvitskii, "k-means++: The advantages of careful seeding". [Online]. Available: https://theory.stanford.edu/~sergei/papers/kMeansPP-soda.pdf. Accessed on: Jan. 20, 2023.

D. P. Kingma, and J. L. Ba, "Adam: A method for stochastic optimization". [Online]. Available: https://arxiv.org/abs/1412.6980. Accessed on: Jan. 20, 2023.

Downloads

Published

2023-06-02

How to Cite

Sanzharovskyi, A., & Yurchyshyn, V. (2023). MODIFIED METHOD FOR DETECTING FAKE NEWS BASED ON MACHINE LEARNING ALGORITHMS. Bulletin of Cherkasy State Technological University, (2), 58–70. https://doi.org/10.24025/2306-4412.2.2023.279984

Issue

No. 2 (2023): Bulletin of Cherkasy State Technological University

Section

Information Technologies

URN

http://vtn.chdtu.edu.uaurn:2306:44552.2023.279984

License

Copyright (c) 2023 Anatolii Sanzharovskyi, Vasyl Yurchyshyn

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

The authors who publish in this journal agree to the following terms:

The authors reserve the right to authorship of their work and give the journal the right to first publish this work under the terms of the Creative Commons Attribution License CC BY-NC, which allows other persons to freely distribute published work with a mandatory reference to authors of the original work and the first publication of the work in this journal.

Authors have the right to conclude separate additional agreements for the non-exclusive distribution of the paper in the form in which it was published by this journal (for example, posting work in electronic repository or publishing as part of a monograph), provided that the link to the first publication in this journal is maintained.

The journal policy allows and encourages authors to post on the Internet (for example, in repositories of institutions or on personal websites) the manuscript of work, both before the submission of this manuscript to the editorial staff, and during its editorial work, as it contributes to the emergence of productive scientific discussion and positively affects the efficiency and dynamics of published work citation (see The Effect of Open Access).