Identification of Fake News using Fetch.ai Agent Technology
Keywords:
ASI, One, LLM, Fetch.ai, Travily agentAbstract
The proliferation of fake news across digital platforms poses a significant threat to informed public discourse, societal trust, and democratic processes. Traditional centralized approaches to fake news detection often face limitations in scalability, transparency, and susceptibility to bias or censorship. This paper presents a novel decentralized approach for the identification of fake news, leveraging the capabilities of Fetch.ai agent technology and the ASI:One (Artificial Superintelligence) Web3 Large Language Model (LLM) . We propose a multi-agent system architecture deployed on the Fetch.ai blockchain, where autonomous agents collaborate to verify the veracity of news headlines. The core methodology involves a Fake News Detector Agent orchestrating a workflow that includes: receiving user requests, tasking a specialized Travily agent for autonomous web information retrieval from credible sources and fact-checking databases, and integrating with the ASI:One LLM for advanced, verifiable natural language processing tasks such as semantic analysis, claim extraction, and contradiction detection. All verification steps, agent interactions, and the final veracity assessment are immutably recorded on the Fetch.ai blockchain using Almanac smart contracts, ensuring end-to-end transparency and providing a verifiable audit trail. This decentralized framework enhances resistance to manipulation and preserves user privacy. Preliminary evaluations suggest the potential for high accuracy in distinguishing fake news from legitimate reporting, while the system’s inherent transparency offers significant advantages over opaque, centralized models. This research contributes a robust, scalable, and trustworthy technological solution to combat the spread of misinformation in the digital age, demonstrating the power of combining decentralized autonomous agents with verifiable Web3 AI
Downloads
Metrics
References
D. Chia, S. Lyu, and T. Lo, “Decision Tree for Fake News Detection,” in Proc. 2020 IEEE SoutheastCon, 2020.
Akhil, Agarwal, and Arush, “Fake News Detection: An Ensemble Learning Approach,” in Proc. 2020 IEEE 4th Int. Conf. Intell. Comput. Control Syst., 2020.
M. Mahir, S. Akhter, M. R. Huq, and A. A. Tanvir, “Detecting Fake News Using Machine Learning and Deep Learning Algorithms,” in Proc. 7th Int. Conf. Smart Comput. Commun. (ICSCC), 2019.
R. Asthana, R. Upadhyay, S. One, N. Upreti, and M. Akbar, “Deep learning models for fake news detection: A novel approach,” Trans. Emerging Telecommun. Technol., 2019. doi: 10.1002/ett.3767.
S. A. Yousif and Reham, “Fake News Classification Using Decision Tree and Random Forest (J48),” Al-Nahrain J. Sci., vol. 23, no. 4, pp. 49–55, Dec. 2020.
R. Varma, S. Pawar, S. Patil, T. Yesugade, and S. Kokate, “LSTM for Fake News Detection,” Int. J. Eng. Res. Technol., vol. 8, no. 4, Apr. 2021.
B. R. and S. A. N., “Performance Comparison of Machine Learning Classifiers for Fake News Detection,” in Proc. 2nd Int. Conf. Inventive Res. Comput. Appl. (ICIRCA), IEEE, 2020, pp. 696–700.
M. Granik and V. Mesyura, “Detecting fake news with a naïve Bayes classifier,” in Proc. 2017 IEEE 1st Ukraine Conf. Elect. Comput. Eng. (UKRCON), pp. 900–903, IEEE, 2017.
A. Sriniranjani and M. Rajeswari, “Logistic Regression Algorithm with Machine Learning for Fake News Detection,” JETIR, vol. 9, no. 6, Jun. 2022.
P. Bhattacharyya, A. Ekbal, A. Roy, and K. Basak, “A Deep Ensemble Framework for Fake News Detection and Classification,” arXiv preprint, arXiv:1811.04670, 2018.
W. Mahoney, R. Zhao, C. Purevdagva, and P.-C. Huang, “A Methodology for Detecting Fraudulent Political Communication that is Based on Machine Learning,” in Proc. 2020 IEEE 14th Int. Conf. Big Data Sci. Eng. (BigDataSE), pp. 80–87.
S. Hangloo and B. Arora, “Combating Multimodal Fake News on Social Media: Methods, Datasets, and Future Perspective,” Multimedia Systems, vol. 28, no. 6, pp. 2391–2422, Jul. 2022. doi: 10.1007/s00530-022-00966-y.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
You are free to:
- Share — copy and redistribute the material in any medium or format
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
Terms:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
