KOKKAI DOC: An LLM-driven framework for scaling parliamentary representatives

2025-05-11

AI Summary

This paper addresses three core challenges in quantifying legislators’ political positions: speech transcription noise, subjective bias from manually defined ideological dimensions, and the inability of static methods to capture position evolution over time. Methodologically, it introduces a large language model (LLM)-based framework for dynamic political positioning. It proposes a novel speech summarization–based denoising technique to enhance transcript quality; discovers multi-issue ideological axes automatically via unsupervised topic modeling and semantic similarity computation; and enables fine-grained diachronic tracking of party positions through temporal embedding alignment. Evaluated on Japanese Diet parliamentary transcripts, the framework achieves high agreement with expert annotations (Pearson’s *r* > 0.85). The system is publicly deployed at kokkaidoc.com, enabling real-time, transparent access to legislator positioning—thereby advancing data-driven democratic engagement.

Technology Category

• Natural Language Processing: Language Grounding & Multi-modal NLP
• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search

Abstract

This paper introduces an LLM-driven framework designed to accurately scale the political issue stances of parliamentary representatives. By leveraging advanced natural language processing techniques and large language models, the proposed methodology refines and enhances previous approaches by addressing key challenges such as noisy speech data, manual bias in selecting political axes, and the lack of dynamic, diachronic analysis. The framework incorporates three major innovations: (1) de-noising parliamentary speeches via summarization to produce cleaner, more consistent opinion embeddings; (2) automatic extraction of axes of political controversy from legislators' speech summaries; and (3) a diachronic analysis that tracks the evolution of party positions over time. We conduct quantitative and qualitative evaluations to verify our methodology. Quantitative evaluations demonstrate high correlation with expert predictions across various political topics, while qualitative analyses reveal meaningful associations between language patterns and political ideologies. This research aims to have an impact beyond the field of academia by making the results accessible by the public on teh web application: kokkaidoc.com. We are hoping that through our application, Japanese voters can gain a data-driven insight into the political landscape which aids them to make more nuanced voting decisions. Overall, this work contributes to the growing body of research that applies LLMs in political science, offering a flexible and reliable framework for scaling political positions from parliamentary speeches. But also explores the practical applications of the research in the real world to have real world impact.

Problem

• Scaling political stances from noisy parliamentary speech data
• Automating extraction of political controversy axes from speeches
• Tracking evolution of party positions over time dynamically

Innovation

• Denoising speeches via summarization for opinion embeddings
• Automatic extraction of political controversy axes
• Diachronic analysis tracking party position evolution