Skip to content

Latest commit

 

History

History
17 lines (10 loc) · 897 Bytes

README.md

File metadata and controls

17 lines (10 loc) · 897 Bytes

financial-sentiment-classifier

Model_USE is a pre-trained NLP model to analyze the sentiment of financial or economic commentary, tweet, or news. It is built upon Universal Sentence Encoder (USE) and fine-tuned for financial sentiment classification purposes. Financial Phrasebank's 'agreeall' dataset was used for fine-tuning.

Example Prompt: "However, the Euro 7 proposal is simply not the right way to do this, as it would have an extremely low environmental impact at an extremely high cost."

Predictin Output: [Negative: 0.99942374, Neutral: 0.00015279527, Positive: 0.00042358576]

Model Architecture

image