Home

Validation of Additive Trees in Textual Data Analysis

---

Correspondence Analysis + Additive Trees + Bootstrap, with Python

Implementation based on the example of William Shakespeare's 154 sonnets

---

Downloadable package containing all the Python code files

Loading the compressed Python code file [folder: "BASIC_TextPanorama.zip"]

---

The software presented here is designed to visualize a collection of texts (poems, songs, interviews). This collection is further partitioned into text categories. Taking William Shakespeare’s 154 sonnets as our running example, the texts are classified into eight main themes—a classification accepted by several scholars of the work. This standalone program does not rely on existing CA (Correspondence Analysis) software.

The theoretical principles and basic methodology are presented in the paper: "Validation of Simultaneous Additive Trees in Textual Data Visualization" L. Lebart (JADT_2026 : 18th International Conference on Statistical Analysis of Textual Data, Palermo, Italy, 8–10 July 2026. Conference Proceedings: Editors: Antonella Plaia, Mariangela Sciandra, Alessandro Albano: . Validation of Simultaneous Additive Trees in Textual Data Visualization (2026). [For more details and colored displays: . Validation of S.A.T... (Presentation)(2026)]

---

Downloadable package containing the 3 data files

Loading compressed data files [folder: "DATA_Shakespeare.zip"]

---

  Overview, example, and commented code

Click below to access the general presentation of TextPanorama and get started using the "Sonnets" example.

[Description_TextPanoramaE]: Introduction to the software and practical implementation using the "Shakespeare's Sonnets" example.  

---

Home