Disease outbreak prediction using natural language processing: a review

Abstract

Research on disease outbreak prediction has suddenly received an enormous interest owing to the COVID-19 pandemic. Natural language processing using user-generated text data has proven to be quite effective for the same. Disease outbreaks that occur frequently can be easily predicted, but novel disease outbreaks are difficult to predict. This review work attempts to summarize the research concerning disease outbreaks and the use of datasets such as news headlines, tweets, and search engine queries using natural language processing techniques. Existing state-of-the-art systems have been analytically discussed with their contributions and limitations. This work is an insight into the existing research in the domain of disease outbreak prediction. A total of 146 articles were reviewed in this study, and results show that news and Twitter datasets are being used most to predict disease outbreaks. This research underlines the fact that numerous works are available in the literature based on specific outbreak-related Internet-sourced text data, viz. news, tweets, and search engine queries. However, this becomes a limitation for any disease outbreak prediction system as it can predict only specific disease outbreaks and motivates the development of systems capable of disease outbreak prediction without any bias.