Fake Media Detection Using Natural Language Processing and Blockchain Approaches

References

[1] Augenstein, T. Rocktäschel, A. Vlachos, and K. Bontcheva investigated posture identification using bidirectional conditional encoding in a 2020 study published on arXiv:1606.05464.

[2] In tweets regarding Catalan independence, M. Taulé, M. A. Martí, F. M. Rangel, P. Rosso, C. Bosco, and V. Patti provided an overview of the gender and stance recognition work at IberEval 2017. This work was published as one of the proceedings of the 2017 2nd Workshop on Evaluating Human Language Technologies for Iberian Languages (CEUR-WS), volume 1881.

[3] M. Lai, A. T. Cignarella, D. I. Hernández Farías, C. Bosco, V. Patti, and P. Rosso conducted a study on multilingual stance recognition in political discussions on social media. Their research was published in the journal Computational Speech and Language in September 2020 with publication number 101075.

[4] For the Fake News test posture identification test, B. Riedel, I. Augenstein, G. P. Spithourakis, and S. Riedel proposed a baseline approach. Their research, which was released in May 2018, provided a simple yet effective technique.

[5] In a 2019 study, C. Dulhanty, J. L. Deglint, I. B. Daya, and A. Wong examined the use of deep bidirectional transformer language models for posture recognition in automatic misinformation assessment.

[6] S. Ochoa, G. D. Mello, L. A. Silva, A. J. Gomes, A. M. R. Fernandes, and V. R. Q. Leithardt published "FakeChain: A blockchain architecture to ensure trust in social media networks" in Proc. Int. Conf. Qual. Inf. Commun. Technol. Algarve, Portugal: Springer, 2019, pp. 105–118.

[7] Y. Wang, W. Yang, F. Ma, J. Xu, B. Zhong, Q. Deng, and J. Gao published Weak supervision for false news detection via reinforcement learning in Proc. AAAI Conf. Artif. Intell., vol. 34, 2020, pp. 516–523.

[8] Chokshi and R. Mathew's research paper, "Deep learning and natural language processing for fake news detection: A research." January 2021, SSRN Electronic Journal. [Online]. accessible at papers.ssrn.com/sol3/papers.cfm with abstract id=3769884.

[9] J. A. Vijay, H. A. Basha, and J. A. Nehru, "A Dynamic Technique for Identifying the False News Using Random Forest Classifier and NLP," Computational Methods and Data Engineering, 2021, Springer, pp. 331-341.

[10] A corresponding textual input structure in "Deep learning for fake news identification," 10. Computation, vol. 9, no. 2, p. 20, February 2021, article by D. Mouratidis, M. Nikiforos, and K. L. Kermanidis.

@article{1707724,
      author = {Nithish Kumar A R, Prem Kumar S, Mukilan M},
      title = {Fake Media Detection Using Natural Language Processing and Blockchain Approaches},
      journal = {Iconic Research And Engineering Journals},
      year = {2025},
      volume = {8},
      number = {10},
      pages = {55-60},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1707724.pdf},
      abstract = {The suggested method for identifying bogus news combines blockchain technology, reinforcement learning (RL), and natural language processing (NLP) approaches. A large dataset of news stories and the metadata that goes with them is first gathered, and then the text is cleaned and tokenized using NLP-based pre-processing. An RL agent is then trained using pertinent features that have been extracted, such as word frequencies and readability. A system of rewards and penalties is used to teach the agent to differentiate between news that is true and that is not. After training, the RL agent can use the features it has retrieved to determine whether new articles are true or fake. Although blockchain technology's potential importance is mentioned, more details are needed. The goal of this creative strategy is to stop the spread of inaccurate and misleading information in digital news.},
      keywords = {Natural Language Processing (NLP), Block chain, Fake News},
      month = {April},
  }