TruthLens: An AI-Based Fake News Detection System
Author
Sneha Navale,Arpita Gunjal, Mrs. Manisha Patil, Mr. Nitin Joshi
Abstract
The rapid dissemination of online news motivates computational approaches for screening potentially misleading content. TruthLens is an academic project proposing an English-language binary news-text classifier and an accessible interface for presenting its predictions. The project materials identify the Kaggle Fake and Real News Dataset, distributed as Fake.csv and True.csv, as the intended data source. They document exploratory-analysis steps for inspecting file structure, missingness, duplicate records, class distribution and article length. The proposed modelling workflow cleans text, transforms it with term frequency–inverse document frequency (TF-IDF), and trains a supervised classifier, with Logistic Regression identified in the presentation as the preferred model. Accuracy, precision, recall, F1-score and a confusion matrix are specified for evaluation. A React-based interface, application backend, Python model API, PostgreSQL history and explainability are architectural intentions, not independently verified deployed features. Although the presentation names Logistic Regression as the best model, neither numerical test results nor model artefacts are supplied; accordingly, comparative superiority and predictive performance cannot yet be established. The contribution documented at this stage is a coherent design and preliminary data-analysis procedure, rather than a validated fake-news verification service. The paper specifies the missing experiments and implementation evidence required for a reproducible empirical submission.
Keywords
Fake News Detection; Natural Language Processing; TF-IDF; Logistic Regression; Text Classification; Explainability.
Full Text:
References
[1] K. Shu, D. Mahudeswaran, S. Wang, D. Lee, and H. Liu, “FakeNewsNet: A Data Repository with News Content, Social Context, and Spatiotemporal Information for Studying Fake News on Social Media,” Big Data, vol. 8, no. 3, pp. 171–188, 2020. doi: 10.1089/big.2020.0062.
[2] Athira A. B., S. D. Madhu Kumar, and A. M. Chacko, “Towards Smart Fake News Detection Through Explainable AI,” arXiv:2207.11490, 2022. https://arxiv.org/abs/2207.11490
[3] ISOT Research Group, University of Victoria, “Fake News Detection Datasets.” https://onlineacademiccommunity.uvic.ca/isot/datasets/ ; project-proposed Kaggle distribution: https://www.kaggle.com/datasets/clmentbisaillon/fake-and-real-news-dataset
[4] F. Pedregosa et al., “Scikit-learn: Machine Learning in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011. https://www.jmlr.org/papers/v12/pedregosa11a.html