AI-Powered Web Application For Lassa Fever Surveillance Using Social Media Data And News Report

Lassa fever remains a critical public health concern in West Africa, particularly in Nigeria, due to its high fatality rate and limited real-time surveillance mechanisms. This research presents the design and development of an AI-powered web application for real-time Lassa fever surveillance using social media data and news reports. The system aims to detect early indicators of outbreaks by analyzing unstructured online data through Natural Language Processing (NLP) and Machine Learning (ML) techniques. The methodology comprised data collection via APIs from platforms such as Twitter and News API, preprocessing through cleaning, tokenization, and TF-IDF vectorization, and classification using multiple ML models including Logistic Regression, Naïve Bayes, Random Forest, Gradient Boosting, and Support Vector Machine (SVM). Performance evaluation using metrics such as Accuracy, Precision, Recall, F1-Score, and ROC-AUC revealed that the Random Forest Classifier achieved the best overall performance with 93% accuracy, 93% precision, 88% recall, an F1-score of 90%, and a ROC-AUC of 96.15%. The model was deployed as a Flask-based API integrated with a ReactJS frontend and Supa base backend, offering a scalable, real-time monitoring platform capable of filtering misinformation and providing actionable insights for public health authorities. The results demonstrate the feasibility of leveraging AI and social media analytics for epidemic intelligence and early outbreak detection. The system contributes to improving public health surveillance infrastructure by providing an adaptable, data-driven approach for real-time disease monitoring and predictive outbreak analysis.