declare-lab/conv-emotion

This repo contains implementation of different architectures for emotion recognition in conversations.

51
/ 100
Established

This project helps customer service teams, social media analysts, or mental health support systems understand the emotional tone of conversations. By inputting conversation transcripts with speaker information, it identifies emotions like 'angry' or 'surprise' for each utterance. The output is a clear emotional breakdown of the dialogue, enabling users to better gauge sentiment and respond appropriately.

1,502 stars. No commits in the last 6 months.

Use this if you need to automatically detect and analyze emotions within multi-turn dialogues to understand customer sentiment, conversational dynamics, or emotional states.

Not ideal if you're looking for a simple keyword-based sentiment analyzer or if your primary need is to detect emotions from single, isolated sentences rather than full conversations.

customer-sentiment conversation-analysis social-listening dialogue-understanding emotional-intelligence-systems
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

1,502

Forks

341

Language

Python

License

MIT

Last pushed

Mar 10, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/declare-lab/conv-emotion"

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