Multilingual Political Issue Classifier

This model classifies political party press releases according to the primary issue they address. The classification scheme is very similar to the Comparative Agendas Project (see: https://www.comparativeagendas.net/, with the exception that the 'environmental' category includes climate change policies. The model was fine tuned using a training dataset of 15k press releases that were labelled using zero-shot classification with GPT-4. The issue scheme is as follows:

CATEGORY SUMMARIES

Macroeconomics Covers broad economic policy topics like interest rates, inflation, unemployment, taxes, budgets, monetary and industrial policy. Also includes wage/price control and other macroeconomic matters.
Civil Rights Focuses on discrimination (racial, gender, age, disability), voting rights, freedom of speech, privacy, and minority protections. Also includes anti-government groups and other civil rights topics.
Health Encompasses healthcare reform, insurance, medical facilities and liability, workforce, and public health efforts. Covers topics from mental health and child health to drug abuse, R&D, and disease prevention.
Agriculture Addresses farm subsidies, food safety, marketing, animal/crop disease, fisheries, and agricultural R&D. Also includes general agriculture policy and rural development.
Labor Covers job safety, training, benefits, labor standards, unions, and youth/migrant employment. Also includes pensions and employment policies.
Education Includes all education levels from early childhood to higher education, as well as special education, vocational training, and education quality initiatives. Also includes R&D and underserved student support.
Environment and climate change Deals with water and air pollution, waste disposal, hazardous materials, conservation, endangered species, and indoor/outdoor environmental safety. Includes recycling, R&D, and land preservation.
Energy Focuses on energy sources like nuclear, coal, oil, renewables, and electricity. Includes energy efficiency, conservation, and related R&D.
Immigration Covers immigration laws, refugee policy, and citizenship issues.
Transportation Addresses infrastructure, public transit, highways, air and rail travel, maritime transport, and transportation R&D.
Law and Crime Includes crime control, enforcement, courts, prisons, drug crime, family law, juvenile justice, and terrorism. Also covers agencies, white-collar crime, and child abuse.
Social Welfare Focuses on programs for low-income families, elderly and disabled assistance, child care, and volunteer organizations. Encompasses general welfare policies.
Housing Covers public housing, community and rural development, housing for veterans, elderly, and the homeless. Includes affordability and urban planning.
Domestic Commerce Includes banking, finance, small business, consumer protection, corporate governance, and commerce-related R&D. Also covers insurance, tourism, and bankruptcy.
Defense Encompasses military policy, readiness, procurement, personnel, nuclear arms, foreign operations, and civil defense. Covers contractors, intelligence, and environmental compliance.
Technology Covers space exploration, telecommunications, computing, broadcasting, and cybersecurity. Also includes scientific research, tech development, and commercial use of space.
Foreign Trade Deals with trade agreements, tariffs, exports/imports, competitiveness, and exchange rates. Also includes international business and investment policy.
International Affairs Includes diplomacy, foreign aid, developing countries, human rights, global organizations, and international finance. Also covers terrorism, embassies, and treaties.
Government Operations Addresses bureaucracy, procurement, civil service, campaigns, tax enforcement, and census data. Also includes scandals, national holidays, and intergovernmental relations.
Public Lands Covers parks, indigenous issues, forest and land management, water resources, and U.S. territories. Focuses on conservation and federal land use.
Culture Encompasses general cultural policies, likely including funding, preservation, and promotion of cultural initiatives.

NOTE ABOUT ISSUE LABELS: The issue numbers used above do not match the CAP codebook (or the issue number that the model assigns). The labels from the model are as follows, where the floats are the CAP labels (see: https://www.comparativeagendas.net/ and the ints are the model labels:

{19.0: 17, 7.0: 6, 4.0: 3, 5.0: 4, 16.0: 14, 13.0: 11, 12.0: 10, 3.0: 2, 6.0: 5, 9.0: 8, 1.0: 0, 17.0: 15, 8.0: 7, 20.0: 18, 14.0: 12, 18.0: 16, 2.0: 1, 10.0: 9, 23.0: 20, 15.0: 13, 21.0: 19}

Countries/languages included in fine-tuning

The countries included are: Poland, Germany, Ireland, Netherlands, Slovenia, Denmark, Hungary, Austria, Sweden, Bulgaria, Spain, Croatia, Finland, United Kingdom, Greece, Switzerland, Estonia, France, Portugal, Cyprus, Slovakia, Italy, Czech Republic, and Belgium.

Accuracy

The model achieves a weighted F1 score of 0.86.

Citation

The data collection efforts of the press releases were originally from the following work. The two lead authors created the model in additional collaboration.

@article{dickson2024going,
  title={Going against the grain: Climate change as a wedge issue for the radical right},
  author={Dickson, Zachary P and Hobolt, Sara B},
  journal={Comparative Political Studies},
  pages={00104140241271297},
  year={2024},
  publisher={SAGE Publications Sage CA: Los Angeles, CA}
}

and

@article{erfort2023partypress,
  title={The PARTYPRESS Database: A new comparative database of parties’ press releases},
  author={Erfort, Cornelius and Stoetzer, Lukas F and Kl{\"u}ver, Heike},
  journal={Research \& Politics},
  volume={10},
  number={3},
  pages={20531680231183512},
  year={2023},
  publisher={SAGE Publications Sage UK: London, England}
}