Visualization of Extremely Sparse Contingency Table by Taxicab Correspondence Analysis: A Case Study of Textual Data

TL;DR

This paper explores taxicab correspondence analysis as a robust method for visualizing extremely sparse contingency tables, demonstrated through a textual dataset of sacred book fragments and compared with other dimension reduction techniques.

Contribution

It introduces taxicab correspondence analysis as a novel, robust visualization method for sparse contingency tables, especially in textual data contexts.

Findings

Taxicab correspondence analysis effectively visualizes sparse textual data.

Compared favorably with t-SNE, UMAP, PHATE in case study.

Provides insights into sparse contingency table visualization.

Abstract

We present an overview of taxicab correspondence analysis, a robust variant of correspondence analysis, for visualization of extremely sparse ontingency tables. In particular we visualize an extremely sparse textual data set of size 590 by 8265 concerning fragments of 8 sacred books recently introduced by Sah and Fokou\'e (2019) and studied quite in detail by (12 + 1) dimension reduction methods (t-SNE, UMAP, PHATE,...) by Ma, Sun and Zou (2022).