La "mise en variables" des textes : mythe ou réalité ?

Abstract

Turning Texts into Variables, Myth or Reality: The statistical analysis of responses to open questions is the subject of many controversies between supporters and critics, but also among supporters concerning the choice of methods of analysis and of data construction. With an example, we focus our attention on two controversies: the interest of using open questions; the use of techniques for transforming corpora of texts (normalization and lemmatization). The pertinence of open questions is established, but tuming texts into variables remains a delicate task in textual analysis and requires reflexive considerations necessary particularly in the interpretation of results.