Talk by Professor Kenneth Benoit, London School of Economics and Political Science
Titel: PREDICTING LEFT-RIGHT POSITIONS FROM HAND-CODED CONTENT ANALYSIS USING MACHINE LEARNING
The Manifesto Project’s widely used left-right index of party policy positions (RILE), built from human-coded sentences from party manifestos, can be predicted using machine learning. We demonstrate this using some simple classifiers to show that using these conservative approaches as a baseline, performance is already as good as human coders. It works in multiple languages. Using transfer learning, we also show how a model trained on coded manifesto sentences can be used on new texts to predict left-right positions, and validate these with independent survey-based evidence.
Kenneth Benoit's current research focuses on computational, quantitative methods for processing large amounts of textual data, mainly political texts and social media. Current interest span from the analysis of big data, including social media, and methods of text mining. His substantive research in political science focuses on comparative party competition, the European Parliament, electoral systems, and the effects of campaign spending. His other methodological interests include general statistical methods for the social sciences, especially those relating to measurement. Recent data large-scale measurement projects in which he has been involved include estimating policy positions of political parties through crowd-sourced data, expert surveys, manifesto coding, and text analysis.
Join via Zoom:
Meeting ID: 683 7557 2787