6 Aug 2024 | Francisco Bolaños*, Angelo Salatino1, Francesco Osborne1,2, Enrico Mottai
This paper provides a comprehensive review of the application of Artificial Intelligence (AI) in Systematic Literature Reviews (SLRs). SLRs are rigorous methodologies that assess and integrate prior research on specific topics, and they are known for being time-consuming and resource-intensive. The paper examines how AI techniques are applied in the semi-automation of SLRs, focusing on the screening and extraction phases. It analyzes 21 leading SLR tools using a framework that combines 23 traditional features with 11 AI features. Additionally, it discusses 11 recent tools that leverage large language models for literature searching and academic writing assistance. The study highlights three primary research challenges: integrating advanced AI solutions, improving usability, and developing a standardized evaluation framework. The paper proposes best practices to ensure more robust evaluations in terms of performance, usability, and transparency. Overall, the review offers insights into AI-enhanced SLR tools, providing a foundation for the development of next-generation AI solutions in this field.This paper provides a comprehensive review of the application of Artificial Intelligence (AI) in Systematic Literature Reviews (SLRs). SLRs are rigorous methodologies that assess and integrate prior research on specific topics, and they are known for being time-consuming and resource-intensive. The paper examines how AI techniques are applied in the semi-automation of SLRs, focusing on the screening and extraction phases. It analyzes 21 leading SLR tools using a framework that combines 23 traditional features with 11 AI features. Additionally, it discusses 11 recent tools that leverage large language models for literature searching and academic writing assistance. The study highlights three primary research challenges: integrating advanced AI solutions, improving usability, and developing a standardized evaluation framework. The paper proposes best practices to ensure more robust evaluations in terms of performance, usability, and transparency. Overall, the review offers insights into AI-enhanced SLR tools, providing a foundation for the development of next-generation AI solutions in this field.