Classification-of-topics-associated-with-responses-to-parliament-debates-and-proceedings-

Abstract This project aims to develop a classification system for topics discussed in responses to parliament debates and proceedings. By categorizing these topics, we can gain insights into the key areas of focus and identify patterns in parliamentary discussions. The classification system includes the following categories: Legislation and Policy, Economy and Finance, Governance and Administration, Foreign Affairs and Diplomacy, Social Issues, Infrastructure and Development, Security and Defense, Justice and Legal Affairs, Public Health, and Education and Research. These categories cover a wide range of subjects that are commonly debated in parliamentary settings. By applying machine learning techniques and natural language processing algorithms to parliamentary responses, we can automatically classify and analyze the topics discussed, providing valuable information for policymakers, researchers, and the general public. Keywords:
parliament debates, proceedings, topic classification, legislation, policy, economy, finance, governance, administration, foreign affairs, diplomacy, social issues, infrastructure, development, security, defense, justice, legal affairs, public health, education, research Introduction This project aims to develop an automated system for classifying topics discussed in parliament debates and proceedings. By analyzing and categorizing these topics, valuable insights can be extracted from parliamentary data more efficiently. The project focuses on scraping data from the Zambia National Assembly website using the Beautiful Soup library. The collected data is then preprocessed to prepare it for classification. The classification system will utilize machine learning and natural language processing algorithms to assign relevant categories to the topics discussed in parliamentary responses. Various models will be trained and evaluated using performance metrics to ensure accuracy. The classification categories include legislation and policy, economy and finance, governance and administration, foreign affairs and diplomacy, social issues, infrastructure and development, security and defense, justice and legal affairs, public health, and education and research. The project's outcomes will provide valuable insights into key topics in parliamentary debates, enabling stakeholders to navigate and understand the political landscape better. This information can support policymakers, researchers, and the public in making informed decisions and conducting comprehensive studies. Ultimately, the developed classification system will automate analysis, unlock insights, and facilitate evidence-based decision-making in response to parliament debates and proceedings. Aim/Problem Formulation & Background Work The aim of this project is to develop an automated classification system that can categorize topics associated with responses to parliament debates and proceedings. By automatically classifying these topics, we can efficiently analyze and extract valuable insights from the vast amount of parliamentary data. The project focuses on the dataset created by scraping the Zambia National Assembly website, specifically the debates and proceedings section accessible through the URL: https://www.parliament.gov.zm/publications/debates-list. The web scraping process was performed using the Beautiful Soup library, a powerful Python tool for extracting data from HTML and XML documents.