Automating Systematic Literature Reviews with Natural Language Processing and Text Mining: a Systematic Literature Review

TL;DR

This paper systematically reviews how natural language processing and text mining techniques are used to automate various steps of systematic literature reviews, highlighting current achievements, challenges, and future research directions.

Contribution

It provides a comprehensive analysis of existing automation methods in SLRs, identifying gaps and proposing areas for further development in NLP and text mining applications.

Findings

Automation techniques are mainly applied in study selection and quality assessment.

Significant gaps exist in automating data extraction and synthesis.

Recent advances have increased automation but challenges remain in accuracy and scope.

Abstract

Objectives: An SLR is presented focusing on text mining based automation of SLR creation. The present review identifies the objectives of the automation studies and the aspects of those steps that were automated. In so doing, the various ML techniques used, challenges, limitations and scope of further research are explained. Methods: Accessible published literature studies that primarily focus on automation of study selection, study quality assessment, data extraction and data synthesis portions of SLR. Twenty-nine studies were analyzed. Results: This review identifies the objectives of the automation studies, steps within the study selection, study quality assessment, data extraction and data synthesis portions that were automated, the various ML techniques used, challenges, limitations and scope of further research. Discussion: We describe uses of NLP/TM techniques to support increased automation of systematic literature reviews. This area has attracted increase attention in the last decade due to significant gaps in the applicability of TM to automate steps in the SLR process. There are significant gaps in the application of TM and related automation techniques in the areas of data extraction, monitoring, quality assessment and data synthesis. There is thus a need for continued progress in this area, and this is expected to ultimately significantly facilitate the construction of systematic literature reviews.