New Method for Using AI-Enhanced Social Media Communication for Disaster Relief Supply Chains

Leveraging AI and social media can significantly enhance communication between disaster victims and aid providers, improving response efficiency and effectiveness

A recent study published in the International Journal of Production Research demonstrates how leveraging social media platforms with artificial intelligence (AI) can significantly enhance communication between disaster victims and external aid providers. This research, led by Vishwa Vijay Kumar, a Ph.D. candidate at The University of Alabama in Huntsville (UAH), addresses the critical issue of supply chain disruptions during the COVID-19 pandemic, providing a framework for future disaster response improvements.

The collaborative research team includes fellow UAH researchers Dr. Avimanyu Sahoo and Dr. Sampson Gholston, and Kumar’s mentor, Dr. Siva K. Balasubramanian from the Illinois Institute of Technology. Their work focused on analysing Twitter data from two significant periods during the pandemic: the initial outbreak in the United States (March–April 2020) and the surge of the delta variant in India (May–June 2021).

During these times, disruptions in healthcare supply chains led to severe shortages of essential medical equipment. The analysis of 3.9 million tweets revealed critical information about supply chain bottlenecks, enabling the team to develop a four-step process and AI algorithms to parse and categorise tweets into “imperative” (actionable) and “non-imperative” (non-actionable) information. This classification was crucial in identifying and coordinating aid for those in urgent need.

Kumar’s personal background deeply influenced his research. “I was born and raised in the countryside of India, in Sitamarhi, Bihar, near the Nepal border, where natural disasters such as floods from the Himalayan rivers are frequent,” he recalls. “These floods can spread over miles, trapping thousands of people in their homes who need urgent help for health care and food, as well as rescue operations. From a young age, I was driven to develop a framework that would enable people in need to communicate their requirements to the world and relevant authorities so they coordinate to assist disaster victims on time.”

The pandemic exposed significant vulnerabilities in global healthcare supply chains, necessitating efficient resource allocation and real-time information dissemination. “This situation reignited my early motivation to explore how social media and AI could be harnessed for faster disaster response and to mitigate health and supply challenges during crises,” Kumar explains. He collaborated with Dr. Sahoo to explore this innovative approach.

The research not only addressed immediate concerns but also laid the groundwork for future studies. The team identified several areas for further investigation, including improving the geo-location of social media posts, forecasting vaccine and supply availability, and applying their methods to other disaster scenarios like hurricanes and earthquakes.

Looking ahead, the researchers plan to develop a platform that can scan social media posts during disasters, generating real-time reports on demand and supply issues and geo-locating individuals requesting help. This tool could revolutionise disaster response, providing timely and accurate information to aid providers.

This study underscores the potential of AI-enhanced social media analysis in transforming disaster response and supply chain management. By harnessing these technologies, we can ensure that critical aid reaches those in need more efficiently and effectively, mitigating the impact of future crises.

For a more comprehensive understanding of this research, the full paper “Mitigating healthcare supply chain challenges under disaster conditions: a holistic AI-based analysis of social media data” is available in the International Journal of Production Research.

Staff Writer

Our in-house science writing team has prepared this content specifically for Lab Horizons

Leave a Reply

Your email address will not be published. Required fields are marked *