Nlp improves prioritising urgent disaster messages in challenged networks
NLP-based Message Prioritisation for Opportunistic Routing: A Case Study of Nepal Earthquake Emergency Communication
Networking and Internet ArchitectureArtificial Intelligence
Summary
Communicating during disasters can be very hard, especially when internet or phone networks are unreliable. This paper looks at using computer understanding of language (NLP) to decide which emergency messages are most urgent. The authors used methods like BERT to sort messages based on how important they are during the 2015 Nepal earthquake. They found this can help prioritize message storage and sending when devices run out of space or connection, but it does not fix limits of network movement or contacts.
What this means in practice
- •For disaster response teams: Use improved NLP message classification to better prioritize urgent information when network resources are limited after emergencies.
- •For mobile network operators: Implement semantic message prioritisation in challenged network routing protocols to reduce critical message losses under buffer constraints.
Tested on one dataset.
Authors
Yihang Cao, Milena Radenkovic
Abstract
This dissertation investigates whether Natural Language Processing (NLP) based semantic message prioritisation can improve the treatment of urgent disaster messages in opportunistic emergency communication, using the 2015 Nepal earthquake as a case study. TF IDF with Logistic Regression and BERT are used to classify social media messages into nine humanitarian categories, which are mapped to four routing priorities from P1 to P4. These priorities are integrated into the ONE simulator within a controlled Kathmandu earthquake scenario using a modified Binary Spray and Wait router. BERT achieves higher priority accuracy and P1 recall than Logistic Regression, while reducing under prioritisation and severe priority errors. However, improved NLP performance does not produce uniform network gains. P1 delivery probability remains high and similar across routing conditions, and no consistent latency reduction is observed. The clearest difference appears under buffer pressure, where the BERT condition shows fewer observed ground truth P1 buffer losses than Logistic Regression. The results indicate that semantic prioritisation is most valuable when limited transmission and storage resources are contested, although it cannot overcome mobility and contact constraints in opportunistic networks.