Citation screening is an essential yet time-consuming step of the systematic review process. Screening automation using machine learning techniques can speed up constructing a systematic review. Current efforts in automation are limited in their capabilities as they either only suggest the decisions or require large annotated datasets before making the predictions. In this PhD thesis, we propose several approaches to improving the screening automation techniques to reduce reviewers' work. First, we want to propose a unified benchmarking method for the citation screening task. We will then explore different machine learning algorithms for conducting screening, focusing on using fewer annotated examples to maintain stable results across multiple reviews. Next, we intend to experiment with using external information coming from eligibility criteria sheets as a substitute for manual annotations. Finally, we would like to assess our approaches to literature reviews outside of the medical domain.