A New Framework for Decentralized Social Networks: Harnessing Blockchain, Deep Learning, and NLP

An Erratum to this article was published on June 30, 2026. https://dergipark.org.tr/en/pub/hjse/article/1982751

Abstract

This paper presents a novel framework for a decentralized social network that integrates blockchain technology, natural language processing (NLP), and deep learning (DL) to address critical vulnerabilities in traditional centralized online social networks (OSNs). Blockchain ensures data integrity, transparency, and decentralized governance, mitigating risks associated with data manipulation and privacy breaches. Deep learning algorithms, including Bidirectional LSTM for post-category prediction and LSTM for suicide detection, enhance content management by capturing nuanced language cues and identifying distress signals. NLP techniques, such as TF-IDF vectorization and cosine similarity, further improve content originality and moderation by detecting duplicates, preventing plagiarism, and fostering diverse content. This paper also elaborates on the implementation of these technologies, demonstrating how blockchain-based smart contracts manage secure interactions, deep learning models categorize content, and NLP techniques ensure content authenticity. This comprehensive integration of blockchain, deep learning, and NLP offers a transformative approach to social networking, promoting transparency, security, and ethical standards, while creating a safer, more trustworthy digital environment.

Keywords

• Blockchain
• Decentralized Social Networks
• Deep Learning
• Natural language processing.

References

1. 1. Chen N, Cho DS-Y. A Blockchain based autonomous decentralized online social network. In: 2021 IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE); 2021; Guangzhou, China. p. 186-90. doi:10.1109/ICCECE51280.2021.9342564.
2. 2. Zeng S, Yuan Y, Wang F-Y. A decentralized social networking architecture enhanced by blockchain. In: 2019 IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI); 2019; Zhengzhou, China. p. 269-73. doi:10.1109/SOLI48380.2019.8955104.
3. 3. Bharambe A, Chandorkar AA, Kalbande D. A deep learning approach for dengue tweet classification. In: 2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA); 2021; Coimbatore, India. p. 1043-7. doi:10.1109/ICIRCA51532.2021.9544862.
4. 4. Oliveira N, Pisa P, Andreoni M, Medeiros D, Menezes D. Identifying fake news on social networks based on natural language processing: trends and challenges. Information. 2021;12(1):38. doi:10.3390/info12010038.
5. 5. Abbas A. Social network analysis using deep learning: applications and schemes. Springer. 2021;21. doi:10.1007/s13278-021-00799-z.
6. 6. Saputhanthri A, De Alwis C, Liyanage M. Survey on blockchain-based IoT payment and marketplaces. IEEE Access. 2022;27. doi:10.1109/ACCESS.2022.3208688.
7. 7. Quach S, Thaichon P, Martin KD, Weaven S, Palmatier RW. Digital technologies: tensions in privacy and data. J Acad Mark Sci. 2022;50:25. doi:10.1007/s11747-022-00845-y.
8. 8. Jiang L, Zhang X. BCOSN: a blockchain-based decentralized online social network. IEEE Trans Comput Soc Syst. 2019;1-13. doi:10.1109/TCSS.2019.2941650.

9. 9. Bhusare P, Mannem B, A K. Decentralised social media. IEEE. 2023;6. doi:10.1109/ViTECoN58111.2023.10157136.
10. 10. Peng L, Feng W, Yang L. Social-Chain: decentralized trust evaluation based on blockchain in pervasive social networking. IEEE. 2021;1-28. doi:10.1145/3419102.
11. 11. Chen Y, Li Q, Wang H. Towards trusted social networks with blockchain technology. arXiv. 2018;6.
12. 12. Guidi B, Michienzi A, Ricci L. A graph-based socioeconomic analysis of Steemit. IEEE Trans Comput Soc Syst. 2021;8(2):365-76. doi:10.1109/TCSS.2020.3042745.
13. 13. Guidi B, Michienzi A. The side effect of ERC-20 standard in social media platforms. In: Lecture Notes in Computer Science. 2022. p. 114-27.
14. 14. Hisseine MA, Chen D, Yang X. The application of blockchain in social media: a systematic literature review. Appl Sci. 2022;12(13):6567. doi:10.3390/app12136567.
15. 15. Guidi B, Michienzi A. How to reward the web: the social dApp Yup. Online Soc Netw Media. 2022;31:100229. doi:10.1016/j. osnem.2022.100229.
16. 16. Tsai S-L, Cheng LC. Deep learning for automated sentiment analysis of social media. IEEE. 2019;1001-4. doi:10.1145/3341161.3344821.
17. 17. Monti F, Frasca F, Eynard D, Mannion D, Bronstein M. Fake news detection on social media using geometric deep learning. arXiv. 2019;15. doi:10.48550/arXiv.1902.06673.
18. 18. Puertas E, Moreno Sandoval LG, Redondo J, Alvarado J, Pomares Quimbaya A. Detection of sociolinguistic features in digital social networks for the detection of communities. Springer. 2021;13(518-37). doi:10.1007/s12559-021-09818-9.
19. 19. Oliveira N, Medeiros D, Menezes D. A sensitive stylistic approach to identify fake news on social networking. IEEE. 2020;27(1250-4). doi:10.1109/LSP.2020.3008087.
20. 20. Hasan M, Maliha M, Arifuzzaman M. Sentiment analysis with NLP on Twitter data. IEEE. 2019;1-4. doi:10.1109/IC4ME247184.2019.9036670.
21. 21. Sarathchandra T, Jayawikrama D. A decentralized social network architecture. IEEE. 2021;251-7. doi:10.1109/SCSE53661.2021.9568334.
22. 22. Keshk M, Turnbull B, Moustafa N, Vatsalan D, Choo K-KR. A privacy-preserving-framework-based blockchain and deep learning for protecting smart power networks. IEEE. 2019;16(5110-8). doi:10.1109/TII.2019.2957140.
23. 23. Node.js Foundation. Node.js documentation. 2021 [cited 2025 Feb 6]. Available from: https://nodejs.org/docs/latest/api/.
24. 24. npm. npm documentation. 2021 [cited 2025 Feb 6]. Available from: https://docs.npmjs.com/.
25. 25. Ethereum Foundation. Solidity documentation. 2023 [cited 2025 Feb 6]. Available from: https://docs.soliditylang.org/en/v0.8.24/.
26. 26. Truffle Suite. Truffle documentation. 2022 [cited 2025 Feb 6]. Available from: https://trufflesuite.com/docs/.
27. 27. Truffle Suite. Ganache documentation. 2021 [cited 2025 Feb 6]. Available from: https://trufflesuite.com/docs/ganache/.
28. 28. Metamask. Metamask documentation. 2024 [cited 2025 Feb 6]. Available from: https://docs.metamask.io/.
29. 29. Moore R. Ethers. 2023 [cited 2025 Feb 6]. Available from: https://docs.ethers.org/v5/.
30. 30. Python Software Foundation. Python documentation. 2023 [cited 2025 Feb 6]. Available from: https://www.python.org/doc/.
31. 31. Sphinx. Flask documentation. 2010 [cited 2025 Feb 6]. Available from: https://flask.palletsprojects.com/en/3.0.x/.
32. 32. Siami-Namini S, Tavakoli N, Namin AS. The performance of LSTM and BiLSTM in forecasting time series. In: 2019 IEEE International Conference on Big Data (Big Data); 2019. p. 3285-92. doi:10.1109/bigdata47090.2019.9005997.
33. 33. Xu G, Meng Y, Qiu X, Yu Z, Wu X. Sentiment analysis of comment texts based on BiLSTM. IEEE Access. 2019;7:51522-32. doi:10.1109/ACCESS.2019.2909919.
34. 34. Andrews A, Oikonomou G, Armour S, Thomas P, Cattermole T. Granular IoT device identification using TF-IDF and cosine similarity. ACM Digit Libr. 2023;91-9. doi:10.1145/3605758.3623492.
35. 35. Lee S, Jo JY, Kim Y. Authentication system for stateless RESTful web service. J Comput Methods Sci Eng. 2017;17(S1):S21-34. doi:10.3233/JCM-16067.