Clean Roget

By Eliana Mugar

A computational humanities and semantic analysis platform built from Roget’s Thesaurus.

Browse

Readable Thesaurus

Explore the cleaned Roget hierarchy in class, section, head, and part-of-speech sections.

Tool

Analyze Text

Paste text and generate a Roget-based semantic profile with top heads, POS patterns, and class distributions.

Compare

Compare Texts or Authors

Compare two uploaded or pasted texts by semantic heads, class distributions, and stylistic ontology patterns.

Corpus

Compare Corpora

Upload multiple files for two authors or collections and compare aggregate semantic fingerprints.

Cluster

Semantic Clustering

Upload multiple texts and group them by Roget-based semantic similarity.

Graph

Semantic Network

Explore Roget semantic heads as an interactive network connected by shared terms.

JSON

Roget Terms JSON

Machine-readable term-level export for applications, search, and semantic analysis.

CSV

Roget Terms CSV

Flat term-level export preserving Roget’s semantic hierarchy, part-of-speech labels, and conceptual categories.

JSON

Clean Semantic Blocks

Structured semantic blocks preserving Roget’s original class, section, and head organization before term-level expansion.

About

About Clean Roget

Learn about Roget’s Thesaurus, the source text, and the computational humanities goals behind this project.