|
|
--- |
|
|
license: cc-by-4.0 |
|
|
language: |
|
|
- en |
|
|
metrics: |
|
|
- accuracy |
|
|
base_model: facebook/roberta-large |
|
|
pipeline_tag: text-classification |
|
|
tags: |
|
|
- framing |
|
|
--- |
|
|
|
|
|
# Sentence Frame Classifier |
|
|
|
|
|
A RoBERTa-based model for detecting media frames at the sentence level. This model can classify sentences into 10 different frame categories and works across both news articles and reader comments. |
|
|
|
|
|
## Model Description |
|
|
|
|
|
This model was trained to identify media frames in text at the sentence level. It's based on the Media Frame Corpus [*Card et al. 2015*](https://aclanthology.org/P15-2072.pdf) and extends to online discussion contexts [*Hartmann et al., 2019*](https://arxiv.org/pdf/1904.03969), making it suitable for analyzing both professional journalism and user-generated content. |
|
|
|
|
|
**Key Features:** |
|
|
|
|
|
- Sentence-level frame classification |
|
|
- Cross-domain capability (news articles + comments) |
|
|
- 9 frame categories based on established political communication theory |
|
|
- Robust performance across different topics |
|
|
|
|
|
## Frame Categories |
|
|
|
|
|
The model classifies sentences into these 9 frame categories: |
|
|
|
|
|
- Economic — Economic costs, benefits, or implications |
|
|
- Morality — Moral or ethical considerations |
|
|
- Fairness and Equality — Issues of fairness, equality, or discrimination |
|
|
- Legality and Crime — Legal aspects, constitutionality, crime, and punishment |
|
|
- Political and Policies — Political processes, policy prescriptions, and evaluations |
|
|
- Security and Defense — Security threats, defense, or public safety |
|
|
- Health and Safety — Health risks, safety concerns, or medical implications |
|
|
- Cultural Identity — Cultural values, traditions, or identity issues |
|
|
- Public Opinion — Public sentiment, polls, or popular support |
|
|
- Other/None |
|
|
|
|
|
## Performance |
|
|
|
|
|
- Macro F1: 0.66 |
|
|
- Accuracy: 0.77 |
|
|
- Cross-topic generalization: Robust performance across different topics |
|
|
- Validation: Human-validated on 600 sentences |
|
|
|
|
|
## Usage |
|
|
|
|
|
```python |
|
|
from transformers import pipeline |
|
|
|
|
|
classifier = pipeline("text-classification", model="mattdr/sentence-frame-classifier") |
|
|
|
|
|
text = "The new policy will cost taxpayers millions of dollars while providing few benefits." |
|
|
result = classifier(text) |
|
|
print(result) |
|
|
# [{'label': 'Economic', 'score': 0.89}] |
|
|
|
|
|
examples = [ |
|
|
"This violates our constitutional rights and freedoms.", |
|
|
"The public strongly supports this initiative according to recent polls.", |
|
|
"We must protect our children from these dangerous substances." |
|
|
] |
|
|
|
|
|
for text in examples: |
|
|
result = classifier(text) |
|
|
print(f"Text: {text}") |
|
|
print(f"Frame: {result[0]['label']} (confidence: {result[0]['score']:.2f})") |
|
|
print() |
|
|
|
