A novel application of machine learning and zero-shot classification methods for automated abstract screening in systematic reviews

Zero-shot classification refers to assigning a label to a text (sentence, paragraph, whole paper) without prior training. This is possible by teaching the system how to codify a question and find its answer in the text. In many domains, especially health sciences, systematic reviews are evidence-based syntheses of information related to a specific topic. Producing them is demanding and time-consuming in terms of collecting, filtering, evaluating and synthesising large volumes of literature, which require significant effort performed by experts. One of its most demanding steps is abstract screening, which requires scientists to sift through various abstracts of relevant papers and include or exclude papers based on pre-established criteria. This process is time-consuming and subjective and requires a consensus between scientists, which may not always be possible. With the recent advances in machine learning and deep learning research, especially in natural language processing, it becomes possible to automate or semi-automate this task. This paper proposes a novel application of traditional machine learning and zero-shot classification methods for automated abstract screening for systematic reviews. Extensive experiments were carried out using seven public datasets. Competitive results were obtained in terms of accuracy, precision and recall across all datasets, which indicate that the burden and the human mistake in the abstract screening process might be reduced.