Update README.md

README.md

@@ -1,23 +1,47 @@
+# Multi-Task BERT Model for Fake News, Hate Speech, and Toxicity Detection
 
- 
- 
+## Model Description
+This model is a **multi-task learning framework** based on [BERT (bert-base-german-cased)](https://huggingface.co/bert-base-german-cased), designed to perform binary classification on three tasks simultaneously:
+1. Fake News Detection
+2. Hate Speech Detection
+3. Toxicity Detection
+
+The model utilizes a shared BERT encoder with task-specific fully connected layers for each classification task. It is fine-tuned on task-specific labeled datasets and supports input text in **German**.
+
+### Model Architecture
+- **Base Model:** bert-base-german-cased
+- **Classifier Heads:**
+  - Fully connected layers with 1 output unit for each task (fake news, hate speech, and toxicity).
+- **Activation Function:** Sigmoid activation for binary classification.
+
+## Intended Use
+This model is intended for applications in:
+- Social media monitoring
+- Content moderation
+- Research on online discourse in German
+
+### Example Use Case
+The model can analyze German text to predict whether it contains:
+- Fake news (1: True, 0: False)
+- Hate speech (1: True, 0: False)
+- Toxicity (1: True, 0: False)
+
+## Usage
+
+### Requirements
+```bash
+pip install torch transformers
+```
+
+### Code Example
+```python
 import torch
 from transformers import BertTokenizer, BertModel
 import torch.nn as nn
-import os
- 
-import gc
-torch.cuda.empty_cache()
-gc.collect()
-# Set the CUDA device
-os.environ["CUDA_VISIBLE_DEVICES"] = "3" 
- 
-device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-print(f"Using device: {device}")
- 
-# Initialize BERT tokenizer
+
+# Load the tokenizer
 tokenizer = BertTokenizer.from_pretrained('bert-base-german-cased')
- 
+
 # Define the Multi-Task Model
 class MultiTaskModel(nn.Module):
     def __init__(self):
@@ -27,7 +51,7 @@ class MultiTaskModel(nn.Module):
         self.fc_fake_news = nn.Linear(self.bert.config.hidden_size, 1)
         self.fc_hate_speech = nn.Linear(self.bert.config.hidden_size, 1)
         self.fc_toxicity = nn.Linear(self.bert.config.hidden_size, 1)
- 
+
     def forward(self, input_ids, attention_mask):
         outputs = self.bert(input_ids=input_ids, attention_mask=attention_mask)
         pooled_output = outputs[1]  # Get the pooled output
@@ -36,48 +60,54 @@ class MultiTaskModel(nn.Module):
         hate_speech_output = self.fc_hate_speech(pooled_output)
         toxicity_output = self.fc_toxicity(pooled_output)
         return fake_news_output, hate_speech_output, toxicity_output
- 
+
 # Function to load the model
-def load_model():
-    model = MultiTaskModel().to(device)  # Initialize the model
-    model.load_state_dict(torch.load('../../media/data/multiTaskTWONB1/multi_task_model.pt'))  # Alternatively Load the saved state from hugging face as well
-    model.eval()  # Set the model to evaluation mode
+def load_model(device):
+    model = MultiTaskModel().to(device)
+    model.load_state_dict(torch.load('path_to_your_model.pt'))
+    model.eval()
     return model
- 
-# Function to make predictions
-def predict(text, model):
-    # Tokenize and encode the input text
-    encoding = tokenizer(text, return_tensors='pt', padding='max_length', truncation=True, max_length=128)
-   
-    # Move input tensors to the same device as the model
-    input_ids = encoding['input_ids'].to(device)
-    attention_mask = encoding['attention_mask'].to(device)
-   
-    # Make predictions
-    with torch.no_grad():
-        outputs_fake_news, outputs_hate_speech, outputs_toxicity = model(input_ids, attention_mask)
-       
-    # Apply sigmoid to get probabilities and round to get binary predictions
+
+# Example Usage
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model = load_model(device)
+
+text_input = "Mir fallen nur Steuervorteile durch Gender Pay gap ein."
+encoding = tokenizer(text_input, return_tensors='pt', padding='max_length', truncation=True, max_length=128)
+
+input_ids = encoding['input_ids'].to(device)
+attention_mask = encoding['attention_mask'].to(device)
+
+# Predict
+with torch.no_grad():
+    outputs_fake_news, outputs_hate_speech, outputs_toxicity = model(input_ids, attention_mask)
     preds_fake_news = torch.sigmoid(outputs_fake_news).squeeze().round().cpu().numpy()
     preds_hate_speech = torch.sigmoid(outputs_hate_speech).squeeze().round().cpu().numpy()
     preds_toxicity = torch.sigmoid(outputs_toxicity).squeeze().round().cpu().numpy()
-   
-    return preds_fake_news, preds_hate_speech, preds_toxicity
- 
-# Load the model
-model = load_model()
- 
-# Example text input for prediction
-text_input = "Mir fallen nur Steuervorteile durch Gender Pay gap ein."
- 
-# Make predictions
-predictions = predict(text_input, model)
- 
-# Print the predictions
-print(f"Fake News Prediction: {predictions[0]}")
-print(f"Hate Speech Prediction: {predictions[1]}")
-print(f"Toxicity Prediction: {predictions[2]}")
-
-
-torch.cuda.empty_cache()
-gc.collect()
+
+print(f"Fake News Prediction: {preds_fake_news}")
+print(f"Hate Speech Prediction: {preds_hate_speech}")
+print(f"Toxicity Prediction: {preds_toxicity}")
+```
+
+## Dataset
+This model assumes fine-tuning on task-specific datasets for German text. Ensure the training datasets are labeled for fake news, hate speech, and toxicity.
+
+## Evaluation
+The model is evaluated using:
+- **Binary classification metrics:** F1-score, precision, recall, and accuracy.
+- Task-specific benchmarks using separate test sets for each task.
+
+## Limitations and Bias
+- **Language Support:** The model only supports German text.
+- **Dataset Bias:** Predictions may reflect biases present in the training data.
+- **Task-Specific Limitations:** Performance may degrade if the input text contains ambiguous or mixed classifications.
+
+## Citation
+If you use this model, please cite:
+```bibtex
+@article{example2025,
+  title={Multi-Task BERT Model for Fake News, Hate Speech, and Toxicity Detection},
+  author={Shivang Sinha},
+  year={2025}
+}