TOVA: Topic Visualization & Analysis
TOVA is a topic modeling platform with a plug-in architecture, supporting training and inference via CLI and web interface.
TOVA is a highly extensible topic modeling platform that supports both traditional and LLM-based models through a unified CLI and interactive web interface. It provides a comprehensive end-to-end workflow, allowing users to train models with full hyperparameter control, enrich topics with LLM-generated labels, and evaluate results using an interactive dashboard rich with visualizations and metrics. Additionally, TOVA offers robust features for running inference on new documents, built-in uncertainty quantification to estimate document-topic probabilities, and a flexible plug-in architecture that makes it easy to integrate new model classes.
Find Related Datasets
Search by Tags
Click any tag below to search for similar datasets
Complete Metadata
| @type | dcat:Dataset |
|---|---|
| accessLevel | public |
| accrualPeriodicity | irregular |
| bureauCode |
[ "006:55" ] |
| contactPoint |
{ "fn": "Juan Fung", "hasEmail": "mailto:juan.fung@nist.gov" } |
| description | TOVA is a topic modeling platform with a plug-in architecture, supporting training and inference via CLI and web interface. TOVA is a highly extensible topic modeling platform that supports both traditional and LLM-based models through a unified CLI and interactive web interface. It provides a comprehensive end-to-end workflow, allowing users to train models with full hyperparameter control, enrich topics with LLM-generated labels, and evaluate results using an interactive dashboard rich with visualizations and metrics. Additionally, TOVA offers robust features for running inference on new documents, built-in uncertainty quantification to estimate document-topic probabilities, and a flexible plug-in architecture that makes it easy to integrate new model classes. |
| distribution |
[ { "title": "TOVA.git", "format": "code repo", "accessURL": "https://github.com/usnistgov/TOVA", "description": "NIST GitHub repository for TOVA" }, { "title": "README", "format": "markdown", "mediaType": "text/markdown", "description": "Describes purpose of TOVA, functionality, setup and configuration, and troubleshooting", "downloadURL": "https://data.nist.gov/od/ds/mds2-4134/readme.md" } ] |
| identifier | ark:/88434/mds2-4134 |
| issued | 2026-07-29 |
| keyword |
[ "artificial intelligence", "content analysis", "grounded theory", "large language model", "natural language processing", "topic model", "unstructured text" ] |
| landingPage | https://data.nist.gov/od/id/mds2-4134 |
| language |
[ "en" ] |
| license | https://www.nist.gov/open/license |
| modified | 2026-06-10 00:00:00 |
| programCode |
[ "006:045" ] |
| publisher |
{ "name": "National Institute of Standards and Technology", "@type": "org:Organization" } |
| references |
[ "https://doi.org/10.18653/v1/2024.eacl-long.51", "https://doi.org/10.18653/v1/2025.acl-long.375" ] |
| theme |
[ "Information Technology:Computational science", "Information Technology:Software research" ] |
| title | TOVA: Topic Visualization & Analysis |
