Nikelroid/multimodal-sentiment-classification

A multimodal deep learning framework that fuses visual features from EfficientNet and textual features from BERT to classify sentiment in image-text conversations using the MSCTD dataset.

32
/ 100
Emerging

This project helps social media analysts and brand managers understand public opinion by automatically classifying sentiment in image-text conversations. It takes social media posts that combine images and text, processes both the visual cues (like faces) and the written content, and outputs a classification of the sentiment as positive, negative, or neutral. This helps anyone needing to quickly gauge the emotional tone of online discussions.

Use this if you need to analyze the emotional tone of social media posts or online dialogues where both images and text are important for understanding the full context.

Not ideal if your sentiment analysis only involves text, or if you need to analyze sentiment in data types other than image-text pairs.

social-media-listening brand-reputation customer-feedback public-opinion-analysis digital-marketing
No License No Package No Dependents
Maintenance 6 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 13 / 25

How are scores calculated?

Stars

9

Forks

2

Language

Jupyter Notebook

License

Last pushed

Nov 21, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Nikelroid/multimodal-sentiment-classification"

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