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

2026-04-17

AI Summary

This study addresses the critical challenge of overlooked emergency blood donation requests on social media due to information overload and the delayed response of conventional manual systems in resource-constrained regions. To tackle this, the authors propose CBRS, a multi-platform framework featuring a two-stage filtering architecture for efficiently identifying and parsing blood donation appeals. Key contributions include the creation of the first 11K-sample dataset encompassing Bengali, English, and transliterated texts; the introduction of adversarial negative samples to enhance model robustness; and the use of LoRA-finetuned Llama-3.2-3B to achieve high-precision zero-shot information extraction with minimal token consumption. Experimental results demonstrate 99% accuracy and precision in filtering tasks and 92% zero-shot accuracy in parsing, substantially outperforming models like GPT-4o-mini while reducing input tokens by a factor of 35.

Technology Category

• Natural Language Processing: Information Extraction
• Machine Learning: Large Multimodal Models (LMMs)
• Application Domains: Humanities & Computational Social Science

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Web Mining and Content Analysis: Large pretrained models with web data
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

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).

Problem

• blood donation requests
• social media streams
• information extraction
• low-resource settings
• urgent communication

Innovation

• dual-layer filtering
• bilingual dataset
• LoRA fine-tuning
• zero-shot parsing
• social stream extraction