GeoTruth AI: A Geolocation-Based Fake News Detection and Verification System | IJCT Volume 13 – Issue 3 | IJCT-V13I3P11
International Journal of Computer Techniques
ISSN 2394-2231
Author
Parul Chaudhary, Vaibhav Chandra Pandey, Aashish Dwivedi, Ankit Singh
Abstract
Fake news presents one of the most critical challenges in the digital age, particularly as social media platforms, including WhatsApp, Telegram, Twitter (X), and Instagram, serve as primary sources for real-time information and simultaneous vectors for misinformation [1], [2]. GeoTruth AI is an intelligent, AI-driven system designed to detect, verify, and visualize fake news occurrences by leveraging both geolocation awareness and community participation [1], [3]. The system employs a hybrid approach, integrating Artificial Intelligence (AI), Natural Language Processing (NLP), and crowd-verification mechanisms to assign a dynamic trust score to every piece of news within a specific region [1], [4]. The system processes user input (text, images, or links) via a mobile app, web app, or integrated bots, where a multi-modal backend performs verification using machine-learning classifiers for textual analysis, image similarity, and metadata inspection [5], [4]. Authenticated local users contribute to the validation by casting votes (True / Fake / Misleading), which collectively refine the trust score and generate a real-time regional heatmap of information reliability [5], [6], [4]. GeoTruth AI aims to empower citizens and authorities by providing a transparent, collaborative, and location-aware solution, thereby contributing significantly to digital trust, responsible information sharing, and social stability through the fusion of AI technology and human intelligence [5], [7].
Keywords
Fake News Detection, Geolocation- Based Verification, Natural Language Processing ( NLP), Artificial Intelligence ( AI), Crowd Verification, Trust Score [1], [8].
Conclusion
The proposed system, GeoTruth AI: A Geolocation- Based Fake News Detection and Verification System, successfully integrates Artificial Intelligence, Natural Language Processing (NLP), Geolocation mapping, and Crowd Verification, forming a robust and modern digital information-validation framework. By fusing automated multimodal content analysis—supported by advanced machine learning and transformer models [1], [2], [3],
[15]—with essential community participation inspired by hybrid human–AI models [7], [8], [19], GeoTruth AI generates a region-specific Trust Score that accurately represents the authenticity of news within its geographical context.
The project demonstrates a feasible and scalable approach for using contemporary technologies to counter misinformation in real time, supported by multimodal fact-checking strategies highlighted in current research [4]–[6], [10], [14], [16], [17]. Its multi-platform design
—accessible through mobile, web, and direct integrations with WhatsApp, Telegram, Twitter (X), and Instagram—ensures broad societal impact, similar to the multi-channel solutions recommended in large-scale misinformation studies [11], [18]. By combining AI-driven detection with responsible human intelligence, GeoTruth AI not only provides a technically viable solution but also contributes meaningfully to the development of a trustworthy, community-oriented digital ecosystem. With continuous learning, data augmentation, and real-world user feedback— approaches supported by evolving multimodal detection frameworks [12], [13], [16]—the system is expected to evolve into a large-scale infrastructure capable of supporting truth verification, public awareness, and policy decision-making across regions.
References
[1]H. R. LekshmiAmmal and A. K. Madasamy, “A reasoning based explainable multimodal fake news detection for low resource language using large language models and transformers,” J. Big Data, vol. 12, no. 1, p. 46, Feb. 2025.
[2]H. Chen, Y. Yu, H. Guo, B. Hu, S. Hu, J. Hu, S. Lyu,
X. Wu, C.-S. Lin and X. Wang, “A self-learning multimodal approach for fake news detection,” Front. Artif. Intell., vol. 8, Art. 1665798, Nov. 2025.
[3]Lingzhi Shen, Yunfei Long, Xiaohao Cai, Imran Razzak, Guanming Chen, Kang Liu and Shoaib Jameel, “GAMED: Knowledge Adaptive Multi-Experts Decoupling for Multimodal Fake News Detection,” arXiv preprint, Dec. 2024.
[4]T.-V. La, M.-H. Nguyen and M.-S. Dao, “KGAlign: Joint Semantic-Structural Knowledge Encoding for Multimodal Fake News Detection,” arXiv preprint, May 2025.
[5]Y. Liu, Y. Liu, Z. Li, R. Yao, Y. Zhang and D. Wang, “Modality Interactive Mixture-of-Experts for Fake News Detection (MIMoE-FND),” arXiv preprint, Jan. 2025.
[6]“A multi-level fusion-based framework for multimodal fake news classification using semantic feature extraction,” Int. J. Mach. Learn. & Cybernetics, vol. 16, pp. 6531–6560, May 2025.
[7]“Multi-modal fake news detection: A comprehensive survey on deep learning technology, advances, and challenges,” J. King Saud Univ. Comput. Inf. Sci., 2025, Article 306.
[8]F. A. Alshuwaier and F. A. Alsulaiman, “Fake News Detection Using Machine Learning and Deep Learning Algorithms: A Comprehensive Review and Future Perspectives,” Computers, vol. 14, no. 9, p. 394, 2025.
[9]Shweta Kumari and M. P. Singh, “A Deep Learning Multimodal Framework for Fake News Detection,” Eng. Technol. Appl. Sci. Res., vol. 14, no. 5, pp. 16527– 16533, Oct. 2024.
[10]S. Saraswathi, S. Jeevithaa, K. Vishwabharathy and
D. Eyuvaraj, “Deep Learning Multimodal Methods to Detect Fake News,” J. Trends Comput. Sci. Smart Technol., vol. 6, no. 2, pp. 139–152, Jun. 2024.
[11]Y. Xing, C. Zhai, Z. Che, H. Pan, K. Li, B. Zhang,
Z. Yao and X. Si, “A multimodal fake news detection model based on bidirectional semantic enhancement and adversarial network under Web 3.0,” Electronics, vol. 14, no. 18, p. 3652, 2025.
[12]K. Karnan and L. R. Aravind Babu, “Cross Modal-FT Net: A Multimodal Fake News Detection Framework using Text, Images and User Behavior,” Int.
J. Eng. Sci. Inf. Technol., vol. 5, no. 4, pp. 453–461, 2025.
[13]“Enhancing Fake News Detection: A Multi-Modal Approach Integrating Reinforcement Learning, Random Forest, and LSTM,” Turkish Journal of Engineering & 2025 Issue, Oct. 2025. [14]“Exploring machine learning for fake news detection: techniques, tools, challenges, and future research directions,” Discover Appl. Sci., vol. 7, art. 873, 2025.
[15]“Pretrained transformers for multimodal fake news detection: Explainability using SHapley Additive exPlanations for contributions from text, image, and image captions,” Eng. Appl. Artif. Intell., vol. 162, Part D, 112590, Dec. 2025.
[16]“Multimodal fake news detection through data augmentation-based contrastive learning,” Applied Soft Computing, vol. 136, 110125, 2023.
[17]“A multifaceted reasoning network for explainable fake news detection,” Information Processing & Management, vol. 61, no. 6, 103822, Nov. 2024.
[18]“Deep Learning for Fake News Detection: Analysing Facebook’s Misinformation Networks,” Procedia Comput. Sci., vol. 265, pp. 199–208, 2025.
[19]M. Zidan, A. Sleem, A. Nabil & M. El-Henawy, “Multimodal Fake News Detection: A Survey of Text and Visual Content Integration Methods,” Int. J. Computers & Inf. Sci., vol. 7, 2025.
How to Cite This Paper
Parul Chaudhary, Vaibhav Chandra Pandey, Aashish Dwivedi, Ankit Singh (2026). GeoTruth AI: A Geolocation-Based Fake News Detection and Verification System. International Journal of Computer Techniques, 13(2). ISSN: 2394-2231.
Related Posts:
