xndien2004/Multimodal-Sarcasm-Detection-for-UITC2024

The Multimodal Sarcasm Detection System detects sarcasm in multimedia content using image-caption generation and NLP. It achieved 1st place in UITC2024 by classifying sarcasm into four categories: image, text, multi sarcasm, and not sarcasm.

21
/ 100
Experimental

This system helps analyze social media posts, news articles, or other multimedia content to identify sarcastic expressions. It takes an image and its accompanying text, then outputs a classification indicating whether the content is sarcastic and, if so, whether the sarcasm is primarily in the image, text, or both. Content analysts, brand managers, or social listening specialists can use this to better understand sentiment and tone in online discussions.

No commits in the last 6 months.

Use this if you need to automatically detect sarcasm in posts that combine images and text, categorizing the type of sarcasm present.

Not ideal if you only need to analyze plain text for sarcasm without any accompanying visual content.

social-listening sentiment-analysis content-moderation brand-reputation media-analysis
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 7 / 25

How are scores calculated?

Stars

23

Forks

2

Language

Jupyter Notebook

License

Last pushed

Mar 21, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/xndien2004/Multimodal-Sarcasm-Detection-for-UITC2024"

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