soujanyaporia/multimodal-sentiment-analysis

Attention-based multimodal fusion for sentiment analysis

49
/ 100
Emerging

This project helps researchers and data scientists understand the emotional tone behind user-generated video content. By analyzing text, audio, and visual cues from video utterances, it identifies overall sentiment (like positive, negative, or neutral). You feed it raw video features, and it outputs sentiment classifications for each video.

366 stars. No commits in the last 6 months.

Use this if you need to classify sentiment from user-generated videos by combining information from spoken words, vocal tone, and visual expressions.

Not ideal if you need to analyze sentiment from text-only data or require real-time processing, as this is a research-focused implementation.

Sentiment Analysis Video Content Analysis Emotion Recognition User-Generated Content Social Media Analytics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

366

Forks

74

Language

Python

License

MIT

Last pushed

Apr 08, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/soujanyaporia/multimodal-sentiment-analysis"

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