NORMA eResearch @NCI Library

Infectious Disease Surveillance with GLEPI: A Natural Language Processing and Deep Learning System

Adekola, Emmanuel (2020) Infectious Disease Surveillance with GLEPI: A Natural Language Processing and Deep Learning System. Masters thesis, Dublin, National College of Ireland.

[img]
Preview
PDF (Master of Science)
Download (1MB) | Preview
[img]
Preview
PDF (Configuration manual)
Download (2MB) | Preview

Abstract

Currently, the prevailing discussions on infectious disease outbreak surveillance are centred on mining unstructured data sources and reducing false notifications. Mining microblogs and other internet-based resources for infectious disease surveillance in an accurate and timely manner has become pertinent due to recent public health concerns. In this paper, we implemented three deep learning-based frameworks to the natural language processing of microblog data to establish the best combination of techniques for infectious disease surveillance. We implemented LSTM, CNN and bi-directional LSTM frameworks. Our bi-directional LSTM model performed best with a 12.4% and 10.5% higher accuracy score than that of our LSTM and CNN models respectively. In our bid to establish the best combination of techniques/parameters, we carried out an in-depth investigation on how number of epochs, dropout rate, and word embedding methods in our models affect performance. Finally, we deploy GLEPI, a deep learning based NLP framework that uses a bi-directional LSTM model to predict the validity of infectious disease related corpus.
Keywords: Natural Language Processing, Deep Learning, Neural Network, Sentiment Analysis, Infectious Disease

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science

Q Science > QA Mathematics > Computer software
T Technology > T Technology (General) > Information Technology > Computer software

R Medicine > RA Public aspects of medicine
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Dan English
Date Deposited: 18 Jan 2021 15:57
Last Modified: 18 Jan 2021 15:57
URI: http://norma.ncirl.ie/id/eprint/4380

Actions (login required)

View Item View Item