Published May 5, 2026 | Version 1.0

VeriNet: AI Misinformation Detection and Trust Scoring System

  • 1. Sanjivani K.B.P. Polytechnic, Kopargaon
  • 2. Saint Monica International School, Vaijapur

Description

This paper presents VeriNet, an advanced artificial intelligence-based framework designed for automated misinformation detection and trust scoring of digital textual content. The exponential growth of online information and social media platforms has significantly increased the spread of misleading and false information, creating a need for reliable, scalable, and intelligent verification systems. VeriNet aims to address this challenge by combining machine learning techniques with natural language processing (NLP) to assess the credibility of textual data.

The proposed system follows a structured pipeline consisting of data acquisition, preprocessing, feature engineering, model training, classification, and trust score computation. During preprocessing, textual data is cleaned, tokenized, and normalized to ensure consistency and quality. Feature extraction techniques such as Term Frequency–Inverse Document Frequency (TF-IDF), n-grams, and semantic embeddings are utilized to capture both syntactic and contextual information from the text.

VeriNet employs supervised learning algorithms for classification, including models such as Logistic Regression, Support Vector Machines, and ensemble-based approaches, to distinguish between credible and non-credible content. In addition, the system incorporates sentiment analysis and contextual pattern recognition to enhance detection accuracy. A dedicated trust scoring module is introduced to quantify the reliability of information by combining model predictions, confidence scores, and content-based heuristics.

The architecture of VeriNet is modular and scalable, enabling integration with real-world applications such as social media monitoring systems, news verification platforms, and automated content moderation tools. The system is designed to support continuous learning and adaptation, allowing it to evolve with emerging misinformation patterns.

Experimental evaluation demonstrates that VeriNet achieves competitive performance in terms of accuracy, precision, recall, and F1-score on benchmark datasets related to fake news detection. The results highlight the effectiveness of combining multiple machine learning techniques with NLP-based feature extraction for robust misinformation detection.

This research contributes to the domain of intelligent information verification by proposing a comprehensive framework that not only detects misinformation but also provides an interpretable trust scoring mechanism. The findings emphasize the importance of AI-driven approaches in enhancing the credibility and reliability of digital information ecosystems.

Files

VeriNet AI Misinformation Detection and Trust Scoring System Published Research Paper.pdf

Files (686.3 kB)

Additional details

Software

Development Status
Active

References

  • 1. Shu, K., Sliva, A., Wang, S., Tang, J., & Liu, H. (2017). Fake news detection on social media. ACM SIGKDD Explorations Newsletter, 19(1), 22–36. 2. Allcott, H., & Gentzkow, M. (2017). Social media and fake news in the 2016 election. Journal of Economic Perspectives, 31(2), 211–236. 3. Shao, C., Ciampaglia, G. L., Varol, O., Flammini, A., & Menczer, F. (2018). The spread of low-credibility content by social bots. Nature Communications, 9(1), 4787. 4. Wang, W. Y. (2017). "Liar, liar pants on fire": A new benchmark dataset for fake news detection. ACL. 5. Wang, Y., Ma, F., Jin, Z., Wang, Y., & Tang, J. (2019). EANN: Event adversarial neural networks for multi-modal fake news detection. KDD. 6. Vosoughi, S., Roy, D., & Aral, S. (2018). The spread of true and false news online. Science, 359(6380), 1146–1151. 7. Jurafsky, D., & Martin, J. H. (2021). Speech and language processing (3rd ed.). Pearson Education. 8. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press. 9. Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. NAACL. 10. Vaswani, A., et al. (2017). Attention is all you need. Advances in Neural Information Processing Systems. 11. Zhou, X., & Zafarani, R. (2020). A survey of fake news: Fundamental theories, detection methods, and opportunities. ACM Computing Surveys, 53(5), 1–40. 12. Shu, K., Mahudeswaran, D., Wang, S., Lee, D., & Liu, H. (2019). FakeNewsNet: A data repository with news content, social context, and spatiotemporal information for studying fake news. Big Data, 7(2), 118–130.