license: cc-by-sa-4.0
language:
- es
metrics:
- accuracy
pipeline_tag: text-classification
tags:
- partypress
- political science
- parties
- press releases
widget:
- text: >-
"Los soldados españoles que están en Afganistán cuentan con las máximas
medidas de seguridad para su protección" Jesús Cuadrado, portavoz
socialista en la Comisión de Defensa del Congreso, ha enviado esta tarde,
en nombre del PSOE, un mensaje de apoyo y solidaridad a los soldados
heridos hoy en Afganistán y a sus familias, así como a sus compañeros en
esta misión internacional. Cuadrado ha resaltado el “enorme sacrificio”
que supone para los soldados una misión de estas características. Un
sacrificio “que está al servicio de todo los españoles”, ha explicado,
“porque contribuyen a la creación de un Estado”, en un lugar que ha sido
usado hasta el momento por los terroristas para cometer atentados en su
país y en resto del mundo. Gracias al trabajo de “nuestros soldados”, ha
añadido, “ahora hay un ejército compuesto por militares afganos y hay una
policía”. Así, “el trabajo de los militares españoles está al servicio de
España y de los demás países”, que participan en esta misión por mandato
de la OTAN, ha recordado. “Es uno de los trabajos más solidarios y
comprometidos que se pueden hacer en el mundo”, ha resaltado el portavoz
socialista. La seguridad de nuestras tropas, una prioridad absoluta “La
seguridad al cien por cien es imposible”, ha admitido Cuadrado. Así lo ha
señalado en numerosas ocasiones tanto el Ministerio de Defensa como el
resto del Gobierno. “Los riesgos que asumimos allí son muy elevados y,
precisamente por eso, durante estos años, el Gobierno ha hecho de la
seguridad de nuestras tropas una prioridad absoluta”. Cuadrado ha
recordado que “todos los blindados que utilizan los militares españoles en
Afganistán han sido renovados”. Los soldados españoles, en concreto,
cuentan con 67 RG31 y 131 blindados tipo Lince. También se ha construido
una nueva base y se ha dotado, a todo el material que utilizan, de las más
modernas medidas de seguridad, así como de unos servicios sanitarios de
alto nivel. “Igualmente, es conocido que se ha ido mejorando el sistema de
transporte de nuestras tropas con las mejores medidas de seguridad”,
concluyó el portavoz en la Comisión de Defensa.
PARTYPRESS monolingual Spain
Fine-tuned model, based on dccuchile/bert-base-spanish-wwm-uncased. Used in Erfort et al. (2023), building on the PARTYPRESS database. For the downstream task of classyfing press releases from political parties into 23 unique policy areas we achieve a performance comparable to expert human coders.
Model description
The PARTYPRESS monolingual model builds on dccuchile/bert-base-spanish-wwm-uncased but has a supervised component. This means, it was fine-tuned using texts labeled by humans. The labels indicate 23 different political issue categories derived from the Comparative Agendas Project (CAP):
| Code | Issue |
|---|---|
| 1 | Macroeconomics |
| 2 | Civil Rights |
| 3 | Health |
| 4 | Agriculture |
| 5 | Labor |
| 6 | Education |
| 7 | Environment |
| 8 | Energy |
| 9 | Immigration |
| 10 | Transportation |
| 12 | Law and Crime |
| 13 | Social Welfare |
| 14 | Housing |
| 15 | Domestic Commerce |
| 16 | Defense |
| 17 | Technology |
| 18 | Foreign Trade |
| 19.1 | International Affairs |
| 19.2 | European Union |
| 20 | Government Operations |
| 23 | Culture |
| 98 | Non-thematic |
| 99 | Other |
Model variations
There are several monolingual models for different countries, and a multilingual model. The multilingual model can be easily extended to other languages, country contexts, or time periods by fine-tuning it with minimal additional labeled texts.
Intended uses & limitations
The main use of the model is for text classification of press releases from political parties. It may also be useful for other political texts.
The classification can then be used to measure which issues parties are discussing in their communication.
How to use
This model can be used directly with a pipeline for text classification:
>>> from transformers import pipeline
>>> tokenizer_kwargs = {'padding':True,'truncation':True,'max_length':512}
>>> partypress = pipeline("text-classification", model = "cornelius/partypress-monolingual-spain", tokenizer = "cornelius/partypress-monolingual-spain", **tokenizer_kwargs)
>>> partypress("Your text here.")
Limitations and bias
The model was trained with data from parties in Spain. For use in other countries, the model may be further fine-tuned. Without further fine-tuning, the performance of the model may be lower.
The model may have biased predictions. We discuss some biases by country, party, and over time in the release paper for the PARTYPRESS database. For example, the performance is highest for press releases from Ireland (75%) and lowest for Poland (55%).
Training data
The PARTYPRESS multilingual model was fine-tuned with about 3,000 press releases from parties in Spain. The press releases were labeled by two expert human coders.
For the training data of the underlying model, please refer to dccuchile/bert-base-spanish-wwm-uncased
Training procedure
Preprocessing
For the preprocessing, please refer to dccuchile/bert-base-spanish-wwm-uncased
Pretraining
For the pretraining, please refer to dccuchile/bert-base-spanish-wwm-uncased
Fine-tuning
We fine-tuned the model using about 3,000 labeled press releases from political parties in Spain.
Training Hyperparameters
The batch size for training was 12, for testing 2, with four epochs. All other hyperparameters were the standard from the transformers library.
Framework versions
- Transformers 4.28.0
- TensorFlow 2.12.0
- Datasets 2.12.0
- Tokenizers 0.13.3
Evaluation results
Fine-tuned on our downstream task, this model achieves the following results in a five-fold cross validation that are comparable to the performance of our expert human coders. Please refer to Erfort et al. (2023)
BibTeX entry and citation info
@article{erfort_partypress_2023,
author = {Cornelius Erfort and
Lukas F. Stoetzer and
Heike Klüver},
title = {The PARTYPRESS Database: A new comparative database of parties’ press releases},
journal = {Research and Politics},
volume = {10},
number = {3},
year = {2023},
doi = {10.1177/20531680231183512},
URL = {https://doi.org/10.1177/20531680231183512}
}
Erfort, C., Stoetzer, L. F., & Klüver, H. (2023). The PARTYPRESS Database: A new comparative database of parties’ press releases. Research & Politics, 10(3). https://doi.org/10.1177/20531680231183512
Further resources
Github: cornelius-erfort/partypress
Research and Politics Dataverse: Replication Data for: The PARTYPRESS Database: A New Comparative Database of Parties’ Press Releases
Acknowledgements
Research for this contribution is part of the Cluster of Excellence "Contestations of the Liberal Script" (EXC 2055, Project-ID: 390715649), funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany's Excellence Strategy. Cornelius Erfort is moreover grateful for generous funding provided by the DFG through the Research Training Group DYNAMICS (GRK 2458/1).
Contact
Cornelius Erfort
Humboldt-Universität zu Berlin