Ontology boosted deep learning for disease name extraction from Twitter messages

• Main Authors: Mark Abraham Magumba, Peter Nabende, Ernest Mwebaze
• Format: Article
• Language: English
• Published: SpringerOpen 2018-09-01
• Series: Journal of Big Data
• Subjects: Epidemiology; Twitter; Sentiment analysis; Text classification; Concept ontology; Data mining
• Online Access: http://link.springer.com/article/10.1186/s40537-018-0139-2

Abstract This paper presents an ontology based deep learning approach for extracting disease names from Twitter messages. The approach relies on simple features obtained via conceptual representations of messages to obtain results that out-perform those from word level models. The significance of this development is that it can potentially reduce the cost of generating named entity recognition models by reducing the cost of annotating training data since ontology creation is a one-time cost as the conceptual level the ontology is meant to be fairly static and reusable. This is of great importance when it comes to social media text like Twitter messages where you have a large, unbounded lexicon with spatial and temporal variations and other inherent biases that make it logistically untenable to annotate a representative amount of text for general purpose models for live applications.