sedflix/unsacmt

Unsupervised Sentiment Analysis for Code-mixed Data

27
/ 100
Experimental

This project helps social media analysts and brand managers understand public opinion expressed in conversations that mix multiple languages, like Hindi and English. It takes social media posts, comments, or customer feedback that contain code-mixed text as input. The output is a sentiment score (positive, negative, or neutral) for each piece of text, helping identify trends or specific issues. Anyone monitoring public sentiment or customer feedback in multilingual online environments would find this useful.

No commits in the last 6 months.

Use this if you need to analyze the emotional tone of text written in a blend of two or more languages, without requiring pre-labeled training data.

Not ideal if your data is purely monolingual or if you require fine-grained emotion detection beyond general sentiment.

social-media-analysis brand-reputation customer-feedback multilingual-communication public-opinion
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 8 / 25
Community 15 / 25

How are scores calculated?

Stars

8

Forks

4

Language

Jupyter Notebook

License

Last pushed

Feb 04, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/embeddings/sedflix/unsacmt"

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