Update README.md

README.md

@@ -1,51 +1,29 @@
 ---
 license: mit
 ---
-## Moritz-Pfeifer Space
+## CentralBankRoBERTa
 
-Welcome to the Moritz-Pfeifer space, where we present two powerful models for audience classification and sentiment analysis.
+CentralBankRoBERTA is a large language model. It combines an economic agent classifier that distinguishes five basic macroeconomic agents with a binary sentiment classifier that identifies the emotional content of sentences in central bank communications.
 
-### AudienceClassifier
-
-Model: Moritz-Pfeifer/AudienceClassifier
-
-#### Overview
-
-The AudienceClassifier model is designed to classify the target audience of a given text. It can determine whether the text is suitable for children, teenagers, adults, or other specific age groups. This model is based on a state-of-the-art deep learning architecture and has been fine-tuned on a diverse and extensive dataset to provide accurate predictions.
-
-#### Intended Use
-
-The AudienceClassifier model is intended to be used in various applications where content categorization based on target audiences is essential. It can be incorporated into content moderation systems, social media platforms, or any platform that requires filtering content based on age-appropriateness.
-
-#### Performance
-
-- Accuracy: 95%
-- F1 Score: 0.94
-- Precision: 0.92
-- Recall: 0.96
-
-### SentimentClassifier
-
-Model: Moritz-Pfeifer/SentimentClassifier
 
 #### Overview
 
-The SentimentClassifier model is designed to analyze the sentiment expressed in a given text. It can determine whether the text conveys a positive, negative, or neutral sentiment. This model leverages powerful natural language processing techniques and has been trained on a large dataset covering diverse domains.
+The AudienceClassifier model is designed to classify the target audience of a given text. It can determine whether the text is adressing households, firms, the financial sector, the government or the central bank itself. This model is based on a state-of-the-art deep learning architecture and has been fine-tuned on a diverse and extensive dataset to provide accurate predictions.
 
 #### Intended Use
 
-The SentimentClassifier model can be used in a wide range of applications, such as sentiment analysis in social media monitoring, customer feedback analysis, and market sentiment tracking. It provides valuable insights into how people feel about certain topics, products, or services.
+The AudienceClassifier model is intended to be used in various applications where content categorization based on target audiences is essential. 
 
 #### Performance
 
-- Accuracy: 92%
-- F1 Score: 0.91
-- Precision: 0.90
-- Recall: 0.92
+- Accuracy: 93%
+- F1 Score: 0.93
+- Precision: 0.93
+- Recall: 0.93
 
 ### Usage
 
-You can use these models in your own applications by leveraging the Hugging Face Transformers library. Below is a Python code snippet demonstrating how to load and use the AudienceClassifier and SentimentClassifier models:
+You can use these models in your own applications by leveraging the Hugging Face Transformers library. Below is a Python code snippet demonstrating how to load and use the AudienceClassifier model:
 
 ```python
 from transformers import pipeline
@@ -53,13 +31,6 @@ from transformers import pipeline
 # Load the AudienceClassifier model
 audience_classifier = pipeline("text-classification", model="Moritz-Pfeifer/AudienceClassifier")
 
-# Load the SentimentClassifier model
-sentiment_classifier = pipeline("text-classification", model="Moritz-Pfeifer/SentimentClassifier")
-
 # Perform audience classification
 audience_result = audience_classifier("Your text goes here.")
 print("Audience Classification:", audience_result[0]['label'])
-
-# Perform sentiment analysis
-sentiment_result = sentiment_classifier("Your text goes here.")
-print("Sentiment Analysis:", sentiment_result[0]['label'])