Systematic Literature Review Search Query Refinement Pipeline: Incremental Enrichment and Adaptation

Systematic literature reviews (SLRs) are at the heart of evidence-based research, collecting and integrating empirical evidence regarding specific research questions. A leading step in the search for relevant evidence is composing Boolean search queries, which are still at the core of how information retrieval systems work to perform an advanced literature search. Building these queries thus requires going from the general aims of the research questions into actionable search terms that are combined into potentially complex Boolean expressions. Researchers are thus tasked with the daunting and challenging task of building and refining search queries in their quest for sufficient coverage and proper representation of the literature. In this paper, we propose an adaptive Boolean query generation and refinement pipeline for SLR search. Our approach utilizes a reinforcement learning technique to learn the optimal modifications for a query based on the feedback collecting from the researchers about the query retrieval performance. Empirical evaluations with 10 SLR datasets showed our approach to achieve comparable performance to that of queries manually composed by SLR authors.