You can deploy this model and start earning money today!

luerhard/
PopBERT

Name: PopBERT
Rating: 2.5 (468 reviews)

Views

No views yet

PopBERT

PopBERT is a model for German-language populism detection in political speeches within the German Bundestag, based on the deepset/gbert-large model: https://huggingface.co/deepset/gbert-large

It is a multilabel model trained on a manually curated dataset of sentences from the 18th and 19th legislative periods. In addition to capturing the foundational dimensions of populism, namely "anti-elitism" and "people-centrism," the model was also fine-tuned to identify the underlying ideological orientation as either "left-wing" or "right-wing."

Helpful code and analyses are stored in a GitHub repo: github.com/luerhard/PopBERT

Prediction

The model outputs a Tensor of length 4. The table connects the position of the predicted probability to its dimension.

Index	Dimension
0	Anti-Elitism
1	People-Centrism
2	Left-Wing Host-Ideology
3	Right-Wing Host-Ideology

Usage Example

python

import torch
from transformers import AutoModelForSequenceClassification
from transformers import AutoTokenizer

# load tokenizer
tokenizer = AutoTokenizer.from_pretrained("luerhard/PopBERT")

# load model
model = AutoModelForSequenceClassification.from_pretrained("luerhard/PopBERT")

# define text to be predicted
text = (
    "Das ist Klassenkampf von oben, das ist Klassenkampf im Interesse von "
    "Vermögenden und Besitzenden gegen die Mehrheit der Steuerzahlerinnen und "
    "Steuerzahler auf dieser Erde."
)

# encode text with tokenizer
encodings = tokenizer(text, return_tensors="pt")

# predict
with torch.inference_mode():
    out = model(**encodings)

# get probabilties
probs = torch.nn.functional.sigmoid(out.logits)
print(probs.detach().numpy())

[[0.8765146 0.34838045 0.983123 0.02148379]]

Performance

To maximize performance, it is recommended to use the following thresholds per dimension:

[0.415961, 0.295400, 0.429109, 0.302714]

Using these thresholds, the model achieves the following performance on the test set:

Dimension	Precision	Recall	F1
Anti-Elitism	0.81	0.88	0.84
People-Centrism	0.70	0.73	0.71
Left-Wing Ideology	0.69	0.77	0.73
Right-Wing Ideology	0.68	0.66	0.67
---	---	---	---
micro avg	0.75	0.80	0.77
macro avg	0.72	0.76	0.74