Ontology Driven Disease Incidence Detection on Twitter

TL;DR

This paper presents an ontology-based method for detecting disease incidence on Twitter, improving relevance and generalization over keyword-based approaches by using conceptual representations and machine learning.

Contribution

It introduces an ontological framework for disease detection on social media, enabling more accurate and adaptable classification across various diseases compared to prior keyword methods.

Findings

Ontology-based approach outperforms keyword methods in relevance and accuracy

Conceptual training improves model generalization to new diseases

Word vectors learned from concepts enhance detection performance

Abstract

In this work we address the issue of generic automated disease incidence monitoring on twitter. We employ an ontology of disease related concepts and use it to obtain a conceptual representation of tweets. Unlike previous key word based systems and topic modeling approaches, our ontological approach allows us to apply more stringent criteria for determining which messages are relevant such as spatial and temporal characteristics whilst giving a stronger guarantee that the resulting models will perform well on new data that may be lexically divergent. We achieve this by training learners on concepts rather than individual words. For training we use a dataset containing mentions of influenza and Listeria and use the learned models to classify datasets containing mentions of an arbitrary selection of other diseases. We show that our ontological approach achieves good performance on this task using a variety of Natural Language Processing Techniques. We also show that word vectors can be learned directly from our concepts to achieve even better results.