Update README.dm

README.md

@@ -1,206 +1,335 @@
 ---
 library_name: transformers
-tags: []
+tags:
+- group-detection
+- political-science
+- multilingual
+- multilabel-classification
+- deberta
+- group-appeals
+language:
+- en
+- de
+- nl
+- da
+- fr
+- es
+- it
+- sv
+base_model: microsoft/mdeberta-v3-base
 ---
 
-# Model Card for Model ID
+# Model Card for mDeBERTa Group Detection
 
-This model takes the various social groups that might be mentioned in political speech, and assigns them to different meaningful groups. It allows the same text string to belong to multiple social groups, for example "girls" are mapped to both "women" and "children"
-
-See Dolinsky et al (2025) for more information on social group categories and Horne et al (2025) for details on training, relation to other models, and use cases.
-
-📊 Evaluation Results: {'eval_loss': 0.023458, 'eval_accuracy': 0.994933, 'eval_f1': 0.894393, 'eval_precision': 0.0.897170, 'eval_recall': 0.891632, 'eval_runtime': 5.9184, 'eval_samples_per_second': 232.831, 'eval_steps_per_second': 29.231, 'epoch': 29.914368650217707}
-
-
-LEARNING_RATE = 1.9432557585419205e-05
-WEIGHT_DECAY = 0.11740203810285466
-WARMUP_RATIO = 0.018423412349675528
+A multilingual group classification model fine-tuned for classifying social group tokens into meaningful social groups categories in political text.
 
 ## Model Details
 
 ### Model Description
 
-<!-- Provide a longer summary of what this model is. -->
-
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+This model is a fine-tuned mDeBERTa-v3-base that performs multilabel classification to classify social group tokens mentioned in political text into meaningful social groups categories. The model can classify a token into multiple group categories simultaneously to support intersectionality, and was trained on political manifesto data.
 
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
+- **Developed by:** Will Horne, Alona O. Dolinsky and Lena Maria Huber
+- **Model type:** Multilabel Sequence Classification
+- **Language(s) (NLP):** English, German (multilingual)
+- **Finetuned from model:** microsoft/mdeberta-v3-base
 
-### Model Sources [optional]
+### Model Sources
 
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+- **Repository:** rwillh11/mdeberta_groups_2.0
+- **Base Model:** [microsoft/mdeberta-v3-base](https://huggingface.co/microsoft/mdeberta-v3-base)
 
 ## Uses
 
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
 ### Direct Use
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
+The model is designed for researchers analyzing political discourse to automatically classify **social group tokens or phrases** into meaningful social group categories. It takes individual group mentions (e.g., "workers", "students", "citizens") as input and outputs predictions for 44 different group categories:
 
-### Downstream Use [optional]
+- Adults, Caregivers, Children, Citizens, Civil servants, Consumers
+- Crime victims, Criminals, Education professionals, Elderly people
+- Employees and workers, Employers and business owners, Ethnic and national communities
+- Families, Farmers, Health professionals, Homeless people, Homeowners and landowners
+- Investors and stakeholders, Landlords, Law enforcement personnel, LGBTQI
+- Lower class, Manual and service workers, Men, Middle class, Migrants and refugees
+- Military personnel, Patients, People with disabilities, Politicians, Religious communities
+- Road users, Rural communities, Sociocultural professionals, Students, Taxpayers
+- Tenants, Unemployed, Upper class, White collar workers, Women, Young people
+- and a residual category of "Other"
 
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+### Downstream Use
 
-[More Information Needed]
+This model can be integrated into larger political text analysis pipelines for:
+- **Step 2 of group analysis**: After extracting group mentions from text, classify them into meaningful categories
+- Political manifestos analysis and group categorization
+- Comparative political research across countries and languages
+- Social group representation studies with consistent categorization
 
 ### Out-of-Scope Use
 
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
+This model should not be used for:
+- **Detecting group mentions within full text** (this model classifies pre-identified group tokens)
+- General entity recognition or named entity recognition tasks
+- Processing full sentences or paragraphs directly
+- Real-time social media monitoring without human oversight
+- Making decisions about individuals or groups
+- Content moderation without additional validation
 
 ## Bias, Risks, and Limitations
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+### Technical Limitations
+- Trained specifically on political manifesto text; performance may vary on other text types
+- Limited to 44 predefined group categories
+- Multilabel predictions may have dependencies between group categories
 
-[More Information Needed]
+### Bias Considerations
+- Training data consists of political manifestos from specific countries and time periods
+- May reflect biases present in political discourse of training data
 
 ### Recommendations
 
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+Users should be aware that this model:
+- Is designed for research purposes in political science
+- Should be validated on specific domains before deployment
+- May require human oversight for sensitive applications
+- Performance may vary across different types of groups and political contexts
 
 ## How to Get Started with the Model
 
-Use the code below to get started with the model.
+### Recommended Usage (Pipeline)
 
-[More Information Needed]
+```python
+from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification
 
-## Training Details
+# Load model and tokenizer
+model_repo = "rwillh11/mdeberta_groups_2.0"
+tokenizer = AutoTokenizer.from_pretrained("microsoft/mdeberta-v3-base")
+model = AutoModelForSequenceClassification.from_pretrained(model_repo)
 
-### Training Data
+# Create pipeline for multilabel classification
+classifier = pipeline(
+    "text-classification",
+    model=model,
+    tokenizer=tokenizer,
+    return_all_scores=True,
+    device=0  # Use GPU if available
+)
 
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+# Example usage - classify group tokens/phrases
+group_tokens = ["students", "workers", "teachers", "citizens", "elderly people"]
 
-[More Information Needed]
+# Get predictions
+predictions = classifier(group_tokens)
 
-### Training Procedure
+# Process results with 0.5 threshold
+for token, prediction in zip(group_tokens, predictions):
+    predicted_labels = [label_score['label'] for label_score in prediction if label_score['score'] > 0.5]
+    print(f"'{token}' → {predicted_labels}")
+```
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+### Manual Implementation
 
-#### Preprocessing [optional]
+```python
+from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import torch
 
-[More Information Needed]
+# Load model and tokenizer
+model_name = "rwillh11/mdeberta_groups_2.0"
+tokenizer = AutoTokenizer.from_pretrained("microsoft/mdeberta-v3-base")
+model = AutoModelForSequenceClassification.from_pretrained(model_name)
 
+# Example group tokens
+group_tokens = ["workers", "citizens", "students"]
 
-#### Training Hyperparameters
+for token in group_tokens:
+    # Tokenize
+    inputs = tokenizer(token, return_tensors="pt", truncation=True, max_length=128)
 
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+    # Get predictions
+    with torch.no_grad():
+        outputs = model(**inputs)
+        predictions = torch.sigmoid(outputs.logits)
 
-#### Speeds, Sizes, Times [optional]
+    # Apply threshold (0.5) to get binary predictions
+    binary_predictions = (predictions > 0.5).cpu().numpy()
 
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+    # Get predicted label indices
+    predicted_indices = [i for i, pred in enumerate(binary_predictions[0]) if pred]
+    print(f"'{token}' predicted categories: {predicted_indices}")
+```
 
-[More Information Needed]
+## Training Details
 
-## Evaluation
+### Training Data
+
+The model was trained on political manifesto data containing:
+- **Languages:** English and German
+- **Text Type:** Political manifesto sentences and group mentions
+- **Labels:** Multiple social group categories (multilabel classification)
+- **Source:** `final_group_train.csv`
+- **Training Size:** 2,454 examples (80% split)
+- **Validation Size:** 614 examples (20% split)
+- **Data processing:** MultiLabelBinarizer for one-hot encoding of group labels
+
+### Training Procedure
+
+#### Preprocessing
+- Texts tokenized using mDeBERTa tokenizer with max length 128
+- Multilabel binarization using scikit-learn's MultiLabelBinarizer
+- Each text can have multiple group labels simultaneously
+
+#### Training Hyperparameters (Optimal from Optuna)
+- **Training regime:** Mixed precision training with gradient accumulation
+- **Optimizer:** AdamW
+- **Learning rate:** 1.9432557585419205e-05 (optimized via Optuna)
+- **Weight decay:** 0.11740203810285466 (optimized via Optuna)
+- **Warmup ratio:** 0.018423412349675528 (optimized via Optuna)
+- **Epochs:** 30
+- **Batch size:** 8 (train and eval)
+- **Gradient accumulation steps:** 2
+- **Trials:** 7 Optuna trials for hyperparameter optimization
+- **Metric for selection:** F1 Score
+- **Seed:** 42 (partial deterministic training - only Transformers seed set)
+- **Pruning:** MedianPruner with 5 warmup steps
+
+#### Training Infrastructure
+- **Hardware:** CUDA-enabled GPU (Google Colab)
+- **Framework:** Transformers, PyTorch
+- **Hyperparameter optimization:** Optuna with MedianPruner
+- **Early stopping:** MedianPruner with 5 warmup steps
 
-<!-- This section describes the evaluation protocols and provides the results. -->
+## Evaluation
 
 ### Testing Data, Factors & Metrics
 
 #### Testing Data
+- 20% holdout from original dataset
+- Multilingual political manifesto sentences with group annotations
 
-<!-- This should link to a Dataset Card if possible. -->
+#### Factors
+The model was evaluated across:
+- **Languages:** English and German text
+- **Group categories:** 44 different social group types
+- **Multilabel performance:** Ability to predict multiple groups per text
 
-[More Information Needed]
+#### Metrics
+Primary metrics used for evaluation:
+- **F1 Score:** Primary optimization metric for multilabel classification
+- **Accuracy:** Overall prediction accuracy
+- **Precision:** Precision across all labels
+- **Recall:** Recall across all labels
 
-#### Factors
+### Results
 
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+**Best Model Performance (Trial 4, Epoch 27):**
+- **Accuracy:** 0.9942
+- **F1 Score:** 0.8537
+- **Precision:** 0.8633
+- **Recall:** 0.8443
 
-[More Information Needed]
+The model demonstrates strong performance in multilabel group detection with consistent results across hyperparameter trials and excellent convergence during training.
 
-#### Metrics
+Additional validation on held-out sets return the following micro-averaged metrics excluding the residual category "other":
 
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+**English**
+- **Precision:** 0.894
+- **Recall:** 0.868
+- **F1 Micro:** 0.881
 
-[More Information Needed]
+**German (using texts translated from English)**
+- **Precision:** 0.853
+- **Recall:** 0.823
+- **F1 Micro:** 0.838
 
-### Results
+**Dutch (using texts translated from English)**
+- **Precision:** 0.833
+- **Recall:** 0.789
+- **F1 Micro:** 0.817
 
-[More Information Needed]
+**Danish (using texts translated from English)**
+- **Precision:** 0.845
+- **Recall:** 0.789
+- **F1 Micro:** 0.816
 
-#### Summary
+**Spanish (using texts translated from English)**
+- **Precision:** 0.838
+- **Recall:** 0.792
+- **F1 Micro:** 0.815
 
+**French (using texts translated from English)**
+- **Precision:** 0.841
+- **Recall:** 0.802
+- **F1 Micro:** 0.821
 
+**Italian (using texts translated from English)**
+- **Precision:** 0.837
+- **Recall:** 0.788
+- **F1 Micro:** 0.811
 
-## Model Examination [optional]
+**Swedish (using texts translated from English)**
+- **Precision:** 0.837
+- **Recall:** 0.774
+- **F1 Micro:** 0.804
 
-<!-- Relevant interpretability work for the model goes here -->
+## Model Examination
 
-[More Information Needed]
+The model uses a standard multilabel classification approach:
+- Sigmoid activation for independent probability prediction per group
+- Binary cross-entropy loss for multilabel training
+- Threshold of 0.5 for binary predictions
+- Supports detection of multiple groups simultaneously in a single text
 
 ## Environmental Impact
 
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+Training involved hyperparameter optimization with 7 trials, each training for 30 epochs.
 
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
+- **Hardware Type:** CUDA-enabled GPU (Google Colab)
+- **Hours used:** Approximately 37-38 hours per trial (6 complete trials ≈ 4.5 hours each, ~27 total hours)
+- **Cloud Provider:** Google Colab
+- **Compute Region:** Variable
+- **Carbon Emitted:** Not precisely measured
+- **Training Date:** February 24, 2025
 
-## Technical Specifications [optional]
+## Technical Specifications
 
 ### Model Architecture and Objective
-
-[More Information Needed]
+- **Base Architecture:** mDeBERTa-v3-base (278M parameters)
+- **Task:** Multilabel sequence classification for group detection
+- **Input:** Political text (max length 128 tokens)
+- **Output:** Multi-dimensional binary vector for group presence
+- **Objective:** Binary cross-entropy loss with F1 score optimization
+- **Activation:** Sigmoid for independent probability prediction per group
+- **Threshold:** 0.5 for binary predictions
 
 ### Compute Infrastructure
 
-[More Information Needed]
-
 #### Hardware
-
-[More Information Needed]
+- GPU-accelerated training (CUDA)
+- Mixed precision training support
 
 #### Software
+- Transformers library
+- PyTorch framework
+- Optuna for hyperparameter optimization
+- scikit-learn for metrics and multilabel encoding
 
-[More Information Needed]
-
-## Citation [optional]
+## Citation
 
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+If you use this model in your research, please cite:
 
 **BibTeX:**
+```bibtex
+@misc{mdeberta_groups_detection,
+  title={mDeBERTa Group Detection Model for Political Text Analysis},
+  author={Will Horne and Alona O. Dolinsky and Lena Maria Huber},
+  year={2024},
+  note={Multilingual model for detecting social groups in political discourse}
+}
+```
 
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
+## Model Card Authors
 
-[More Information Needed]
+Research team studying group appeals in political discourse.
 
 ## Model Card Contact
 
-[More Information Needed]
+For questions about this model, please contact the research team through appropriate academic channels.