Epistemological Considerations of Text Mining: Implications for Systematic Literature Review

In the era of big data, the capacity to produce textual documents is increasing day by day. Our ability to generate large amounts of information has impacted our lives at both the individual and societal levels. Science has not escaped this evolution either, and it is often difficult to quickly and reliably "stand on the shoulders of giants". Text mining is presented as a promising mathematical solution. However, it has not yet convinced qualitative analysts who are usually wary of mathematical calculation. For this reason, this article proposes to rethink the epistemological principles of text mining, by returning to the qualitative analysis of its meaning and structure. It presents alternatives, applicable to the process of constructing lexical matrices for the analysis of a complex textual corpus. At the same time, the need for new multivariate algorithms capable of integrating these principles is discussed. We take a practical example in the use of text mining, by means of Multivariate Analysis of Variance Biplot (MANOVA-Biplot) when carrying out a systematic review of the literature. The article will show the advantages and disadvantages of exploring and analyzing a large set of publications quickly and methodically.