A Comparison of Machine Learning Algorithms Applied to American Legislature Polarization

TL;DR

This paper compares three machine learning algorithms to measure American state legislature polarization, finding neural networks outperform support vector machines and linear regression, emphasizing accessible data's role in civic responsibility.

Contribution

It introduces a novel, open-source approach to measuring legislature polarization using machine learning, with a focus on transparency and public data.

Findings

Neural network regression outperforms other algorithms in prediction accuracy.

Support vector machine and ordinary least squares are less effective.

Accessible data sources are crucial for civic engagement and transparency.

Abstract

We present a novel approach to the measurement of American state legislature polarization with an experimental comparison of three different machine learning algorithms. Our approach strictly relies on public data sources and open source software. The results suggest that artificial neural network regression has the best outcome compared to both support vector machine and ordinary least squares regression in the prediction of both state House and state Senate legislature polarization. In addition to the technical outcomes of our study, broader implications are assessed as a means of highlighting the importance of accessible information for the higher purpose of promoting civic responsibility.