@techreport{HerzogJankin, type = {Working Paper}, author = {Herzog, Alexander and Jankin, Slava}, title = {Database of Parliamentary Speeches in Ireland, 1919-2013}, series = {IEEE Proceedings of the 2017 International Conference on the Frontiers and Advances in Data Science (FADS)}, journal = {IEEE Proceedings of the 2017 International Conference on the Frontiers and Advances in Data Science (FADS)}, doi = {10.1109/FADS.2017.8253189}, pages = {29 -- 34}, abstract = {We present a database of parliamentary debates that contains the complete record of parliamentary speeches from D{\´a}il {\´E}ireann, the lower house and principal chamber of the Irish parliament, from 1919 to 2013. In addition, the database contains background information on all TDs (Teachta D{\´a}la, members of parliament), such as their party affiliations, constituencies and office positions. The current version of the database includes close to 4.5 million speeches from 1,178 TDs. The speeches were downloaded from the official parliament website and further processed and parsed. Background information on TDs was collected from the member database of the parliament website. Data on cabinet positions (ministers and junior ministers) was collected from the official website of the government. A record linkage algorithm and human coders were used to match TDs and ministers.}, language = {en} } @article{HerzogJankin, author = {Herzog, Alexander and Jankin, Slava}, title = {Intra-Cabinet Politics and Fiscal Governance in Times of Austerity}, series = {Political Science Research and Methods}, journal = {Political Science Research and Methods}, doi = {10.1017/psrm.2019.40}, pages = {1 -- 16}, abstract = {In the context of recent economic and financial crisis in Europe, questions about the power of the core executive to control fiscal outcomes are more important than ever. Why are some governments more effective in controlling spending while others fall prey to excessive overspending by individual cabinet ministers? We approach this question by lifting the veil of collective cabinet responsibility and focusing on intra-cabinet decision-making around budgetary allocation. Using the contributions of individual cabinet members during budget debates in Ireland, we estimate their positions on a latent dimension that represents their relative levels of support or opposition to the cabinet leadership. We find some evidence that ministers who are close to the finance minister receive a larger budget share, but under worsening macro-economic conditions closeness to the prime minister is a better predictor for budget allocations. Our results highlight potential fragility of the fiscal authority delegation mechanism in adverse economic environment.}, language = {en} } @article{BecharaHerzogJankin, author = {B{\´e}chara, Hannah and Herzog, Alexander and Jankin, Slava}, title = {Transfer learning for topic labeling: Analysis of the UK House of Commons speeches 1935-2014}, series = {Research and Politics}, volume = {April-June 2021}, journal = {Research and Politics}, doi = {10.1177/20531680211022206}, 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.}, language = {en} }