CornellNLP / ConvoKit
ConvoKit is a toolkit for extracting conversational features and analyzing social phenomena in conversations. It includes several large conversational datasets along with scripts exemplifying the use of the toolkit on these datasets.
Why this job: works in the areas we cover, but does not say which job it does
What it does
This toolkit contains tools to extract conversational features and analyze social phenomena in conversations, using a single unified interface inspired by (and compatible with) scikit-learn. Several large conversational datasets are included together with scripts exemplifying the use of the toolkit on these datasets. The latest version is 4.1.2 (released June 26, 2026); follow the project on GitHub to keep track of updates.
Get started
No single install command. Read the steps in the README (opens in new tab)
- Maintenance
- Active
- Last commit 28 days ago
- Stars
- 654
- +1 this week
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v5.0.0
- Released 27 days ago
- Built with
- Jupyter Notebook
- 70% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 77% closed
- 26 still open
- Pull requests
- 197 merged
- 15 waiting
- Releases
- 22
- 4 in the last year
- Contributing guide (opens in new tab)
- No security policy
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| elevenlabs / elevenlabs-python | 3,181 | 2 days ago | MIT | No downloads |
| RingBDStack / SocialED | 594 | 43 days ago | BSD-2-Clause | No downloads |
| CSSLab / maia-chess | 1,269 | 5 months ago | GPL-3.0 | No downloads |
More: languages, topics and project record
Languages
- Jupyter Notebook 70%
- Python 29%
- CSS 1%
- JavaScript <1%
Topics
- nlp
- toolkit
- machine-learning
- dataset
- dialogs
- computational-social-science
- conversational-ai
- conversations
- conversational-analysis
Project record
- JobOther AI tools
- StatusListed
- Commits1,536
- Forks142
- Watching29
- Stars in 28 days+5
- CreatedMar 14, 2016
- First seen by usNov 7, 2026
- CheckedNov 8, 2026