hcmlab/nova

NOVA is a tool for annotating and analyzing behaviours in social interactions. It supports Annotators using Machine Learning already during the coding process. Further it features both, discrete labels and continuous scores and a visuzalization of streams recorded with the SSI Framework.

57
/ 100
Established

Built on the SSI Framework ecosystem, NOVA enables collaborative annotation workflows where human annotators and ML models iterate together—training SVMs or neural networks on partial sessions to predict remaining data, then refining models with human feedback. The tool supports cross-format compatibility, importing annotations from ELAN and ANVIL while exporting to standard formats, and integrates with the DISCOVER server for running computational analysis modules directly within the UI. Frame-level discrete labeling and continuous value annotations are both supported with a customizable multi-person interface.

189 stars.

No Package No Dependents
Maintenance 10 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

189

Forks

38

Language

C#

License

GPL-3.0

Last pushed

Feb 24, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/hcmlab/nova"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.