Enhancing literature research processes: A glance at an approach based on latent semantic indexing

Abstract

Literature search as a fundamental, complex and time-consuming step in a literature research process is part of many established scientific methods. It is still predominantly supported by search techniques based on conventional termmatching methods. We address the lack of semantic approaches in this context by proposing an enhancement of the literature research process with a prototype of our Tool for Semantic Indexing and Similarity Queries (TSISQ), which is based on latent semantic indexing (LSI). Its applicability is evaluated in two cases. Results indicate that our approach can help to save valuable time discovering relevant literature in a desired research field or to increase the comprehensiveness of a review by identifying sources that otherwise would not have been considered. The target audience for our findings includes researchers who need to efficiently gain an overview of a research field, deepen their knowledge and refine the theoretical foundations of their research.