Transfer learning for topic labeling: Analysis of the UK House of Commons speeches 1935–2014

Abstract

Topic models are widely used in natural language processing, allowing researchers to estimate the underlying themes in a collection of documents. Most topic models require the additional step of attaching meaningful labels to estimated topics, a process that is not scalable, suffers from human bias, and is difficult to replicate. We present a transfer topic labeling method that seeks to remedy these problems, using domain-specific codebooks as the knowledge base to automatically label estimated topics. We demonstrate our approach with a large-scale topic model analysis of the complete corpus of UK House of Commons speeches from 1935 to 2014, using the coding instructions of the Comparative Agendas Project to label topics. We evaluated our results using human expert coding and compared our approach with more current state-of-the-art neural methods. Our approach was simple to implement, compared favorably to expert judgments, and outperformed the neural networks model for a majority of the topics we estimated.