Screening articles for systematic reviews with ChatGPT

Systematic reviews (SRs) provide valuable evidence for guiding new research directions. However, the manual effort involved in selecting articles for inclusion in an SR is error-prone and time-consuming. While screening articles has traditionally been considered challenging to automate, the advent of large language models offers new possibilities. In this paper, we discuss the effect of using ChatGPT on the SR process. In particular, we investigate the effectiveness of different prompt strategies for automating the article screening process using five real SR datasets. Our results show that ChatGPT can reach up to 82% accuracy. The best performing prompts specify exclusion criteria and avoid negative shots. However, prompts should be adapted to different corpus characteristics. •Assess accuracy of ChatGPT to autonomously screen articles in systematic reviews.•General prompt template that can be parameterized for different systematic reviews.•Curated datasets of real systematic reviews in software engineering.•Empirical evaluation of different prompt strategies on the datasets.•Recommendations for next-generation systematic review tools relying on large language models.