In this research, we explore semi-supervised learning based classifiers to identify articles that can be included when creating medical systematic reviews (SRs). Specifically, we perform comparative study of various semi-supervised learning algorithm, and identify the best technique that is suited for SRs creation. We also aim to identify whether semisupervised learning technique with few labeled samples produce meaningful work saving for SRs creation. Through an empirical study, we demonstrate that semi-supervised classifiers are viable for selecting articles for systematic reviews and situations when only a few numbers of training samples are available.
Timsina, P., Liu, J., El-Gayar, O., & Shang, Y. (2016, January). Using semi-supervised learning for the creation of medical systematic review: An exploratory analysis. In 2016 49th Hawaii International Conference on System Sciences (HICSS) (pp. 1195-1203). IEEE.