Publication Date

Spring 2023

Degree Type

Master's Project

Degree Name

Master of Science (MS)


Computer Science

First Advisor

Robert Chun

Second Advisor

Fabio Di Troia

Third Advisor

Anudeep Varma Datla


bidirectional encoder representations from transformers, bidirectional long short-term memory, convolutional layers, embeddings, neural networks, convolution neural network


Digital networking sites such as Twitter give a global platform for users to discuss and express their own experiences with others. People frequently use social media to share their daily experiences, local news, and activities with others. Many rescue services and agencies frequently monitor this sort of data to identify crises and limit the danger of loss of life. During a natural catastrophe, many tweets are made in reference to the tragedy, making it a hot topic on Twitter. Tweets containing natural disaster phrases but do not discuss the event itself are not informational and should be labeled as non-disaster tweets. Convolutional layers and domain-specific word embeddings are key to traditional tweet categorization models for crisis response. The objective of our research is to evaluate the efficacy of neural networks in categorizing tweets by utilizing both general-purpose and specific to a domain word embeddings to augment their performance. The prior techniques yield a singular embedding of a word extracted from a specific document.. To address the aforementioned issue, this research offers a classification hybrid model based on Bidirectional Encoder Representations from Transformers (BERT), Bidirectional Long Short-Term Memory (BiLSTM), and Convolution Neural Network (CNN) (BERT-BiLSTM-CNN).