Skip to Main content Skip to Navigation
Conference papers

Lexicométrie pour l’analyse qualitative : Pourquoi et comment résoudre le paradoxe ?

Christophe Lejeune 1 Aurélien Bénel 2
2 Tech-CICO - TECHnologies pour la Coopération, l’Interaction et les COnnaissances dans les collectifs
ICD - Institut Charles Delaunay, CNRS - Centre National de la Recherche Scientifique : FRE2732
Abstract : Using text statistics for qualitative analysis is surely a paradox-counting words in an approach where" numbers doesn't count". Hence, we were stunned by the repeated expectation of text mining features from the users of our qualitative analysis platform. Reluctant at first to methodological hybridizations that could be seen as flawed, we then had to admit that even the founders of qualitative analysis envisioned qualitative ways to use statistics. Counts cannot be regarded as proofs by qualitative analyzers, but as clues for an interpretation, as incentives to look closer at the materials. To achieve this goal, we designed a new visualization of text statistics, displayed in the text without any numbers nor tables.
Complete list of metadatas

https://hal-utt.archives-ouvertes.fr/hal-02923821
Contributor : Daniel Gavrysiak <>
Submitted on : Thursday, August 27, 2020 - 2:38:52 PM
Last modification on : Friday, August 28, 2020 - 3:27:33 AM

Identifiers

  • HAL Id : hal-02923821, version 1

Collections

HETIC | UTT | CNRS

Citation

Christophe Lejeune, Aurélien Bénel. Lexicométrie pour l’analyse qualitative : Pourquoi et comment résoudre le paradoxe ?. 11e journées internationales d'analyse statistique de données textuelles (JADT), Lexicometrica, 2012, Paris, France. ⟨hal-02923821⟩

Share

Metrics

Record views

10