CBRS: Cognitive Blood Request System with Bilingual Dataset and Dual-Layer Filtering for Multi-Platform Social Streams

TL;DR

CBRS is a multi-platform system that filters and parses blood donation requests from social media using a novel multilingual dataset, achieving high accuracy and efficiency with advanced language models.

Contribution

Introduces a dual-layer filtering architecture and a multilingual dataset for blood request detection, improving robustness and performance over existing methods.

Findings

Achieves 99% accuracy and precision in filtering blood requests.

Llama-3.2-3B model attains 92% zero-shot parsing accuracy, surpassing baseline models.

Reduces input token usage by 35 times compared to GPT-4o-mini and others.

Abstract

Urgent blood donation seeking posts and messages on social media often go unnoticed due to the overwhelming volume of daily communications. Traditional app-based systems, reliant on manual input, struggle to reach users in low-resource settings, delaying critical responses. To address this, we introduce the Cognitive Blood Request System (CBRS), a multi-platform framework that efficiently filters and parses blood donation requests from social media streams using a cost-efficient dual-layered architecture. To do so, we curate a novel dataset of 11K parsed blood donation request messages in Bengali, English, and transliterated Bengali, capturing the linguistic diversity of real social media communications. The inclusion of adversarial negatives further enhances the robustness of our model. CBRS achieves an impressive 99% accuracy and precision in filtering, surpassing benchmark methods. In the parsing task, our LoRA finetuned Llama-3.2-3B model achieves 92% zero-shot accuracy, surpassing the base model by 41.54% and exceeding the few-shot performance of GPT-4o-mini, Gemini-2.0-Flash, and other LLMs, while resulting in a 35X reduction in input token usage. This work lays a robust foundation for scalable, inclusive information extraction in time-sensitive, object-focused tasks. Our code, dataset, and trained models are publicly available at [https://github.com/aaniksahaa/CBRS](https://github.com/aaniksahaa/CBRS).