Update README.md

README.md

@@ -1,78 +1,48 @@
-# GordonAI
-
-GordonAI is an AI package designed for sentiment analysis, emotion detection, and fact-checking classification. The models are pre-trained on three languages: **Italian**, **English**, and **Spanish**. 
-
-## Features
-
-- **Sentiment Analysis**: Classifies text into three categories: **positive**, **negative**, and **neutral**.
-- **Emotion Detection**: Identifies the six basic emotions defined by Paul Ekman (1992): **joy**, **sadness**, **fear**, **anger**, **surprise**, **disgust** (plus **neutral**).
-- **Fact-Checking Classification**: Classifies text into **disinformation**, **hoax**, **fake news**, or **true news**.
-
-## Installation 
-
-You can install the package using `pip`. Simply run the following command:
-
-```bash
-pip install GordonAI
-```
-
-## Usage
-
-### Sentiment Analysis
-
-You can use the `SentimentAnalyzer` to predict the sentiment of a text. The analyzer classifies texts as positive, negative, or neutral.
-
-```python
-from GordonAI.models import SentimentAnalyzer
-# Initialize the sentiment analyzer
-analyzer = SentimentAnalyzer()
-# Predict sentiment of a list of texts
-result = analyzer.predict(["This is a great product!", "This is a terrible mistake."])
-# Output the predictions
-print(result)
-```
-
-### Emotion Detection
-
-You can use the `EmotionAnalyzer` to predict the emotion of a text. The analyzer classifies texts as joy, sadness, fear, anger, surprise, disgust or neutral.
-
-```python
-from GordonAI.models import EmotionAnalyzer
-# Initialize the emotion analyzer
-emotion_analyzer = EmotionAnalyzer()
-# Predict emotions of a list of texts
-result = emotion_analyzer.predict(["I'm so happy today!", "I'm feeling really sad."])
-# Output the predictions
-print(result)
-```
-
-### Fact-Checking Classification
-You can use the `FactAnalyzer`  to predict whether a texts or a claim falls into categories like disinformation, fake news, hoax, or true news.
-
-```python
-from GordonAI.models import FactAnalyzer
-# Initialize the emotion analyzer
-fact_analyzer  = FactAnalyzer()
-# Predict emotions of a list of texts
-result = fact_analyzer.predict(["This news story is about a real event.", "This news article is based on fake information."])
-# Output the predictions
-print(result)
-```
-
-## Requirements
-Python >= 3.9
-transformers
-torch
-
-You can install the dependencies using:
-```bash
-pip install transformers torch
-```
-
-## Acknowledgments
-
-This package is part of the work for my doctoral thesis. I would like to thank **NeoData** and **Università di Catania** for their valuable contributions to the development of this project.
-
-
-
-
+---
+license: mit
+language:
+- en
+- it
+- es
+base_model:
+- microsoft/mdeberta-v3-base
+pipeline_tag: text-classification
+---
+# GordonAI
+
+GordonAI is an AI package designed for sentiment analysis, emotion detection, and fact-checking classification. The models are pre-trained on three languages: **Italian**, **English**, and **Spanish**. 
+
+## Features
+
+This model has been trained for emotion detection and can categorize text into one of the six basic the six basic emotions defined by Paul Ekman (1992): **Joy**, **Sadness**, **Fear**, **Anger**, **Surprise**, **Disgust**, and **Neutral**.
+
+The model is based on the pre-trained version of mdeberta-v3-base from Microsoft and has been fine-tuned on an emotion detection dataset to adapt to recognizing emotional expressions in text..
+
+## Usage
+
+You can use `GordonAI` to predict the emotion of a text.
+
+```python
+from transformers import pipeline
+
+# Load the pipeline for text classification
+classifier = pipeline("text-classification", model="VinMir/GordonAI-emotion_detection")
+
+# Use the model to classify the emotion of a text
+result = classifier("I love this!")
+print(result)
+```
+
+## Requirements
+Python >= 3.9
+transformers
+torch
+
+You can install the dependencies using:
+```bash
+pip install transformers torch
+```
+
+## Acknowledgments
+
+This package is part of the work for my doctoral thesis. I would like to thank **NeoData** and **Università di Catania** for their valuable contributions to the development of this project.