Back

Review Protocol: A Scoping Review of Natural Language Processing Technologies for Public Health in Africa

Hu, S.; Oppong, A.; Mogo, E.; Barford, A.; Occhini, G.; Collins, C.; Korhonen, A.

2024-07-03 health informatics
10.1101/2024.07.02.24309815 medRxiv
Show abstract

Natural Language Processing (NLP) is the field of research for a range of computational techniques that enable computers to process human languages, thereby facilitating a variety of tasks such as text analysis and language generation. Recent advancements in NLP have shown great potential in transforming public health delivery by enhancing accessibility, personalisation, and timeliness for both the public and healthcare providers. However, the application of these technologies in African communities is often confined by the limitation of digital resources, such as the scarcity of large-scale, domain-specific datasets, particularly in healthcare. This scoping review aims to systematically explore the landscape of NLP technologies for public health in Africa, identifying the available technologies, factors influencing their availability, and the gaps that need addressing. This review protocol is guided by the PRISMA-P statement. The search strategy will be executed on MEDLINE via PubMed, ACL Anthology, Scopus, IEEE Xplor, and ACM digital library, spanning from 2013 to 2024, and grey literature. The results and analysis will help to illustrate the current state of NLP applications in African public health settings and identify critical areas where investment and development are needed.

Matching journals

The top 2 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.