Policy Dimensionality and Legislative Activity in Parliamentary Democracies.

We introduce a new automated method for identifying policy positions and saliencies from political texts. Political scientists use remarkably context-free, incomplete and invariant estimates of political parties' positions for testing dy- namic, policy-focused theories of parliamentary politics. Currently, we lack party position estimates on policy dimensions covering the full scope of parliamentary activity. Scholars must therefore make strong assumptions about the nature of the policy space when calculating ideological variables. This reduces sample sizes and increases the risk of selection bias. Our method "smart tags" political texts by using keywords from legislative databases. Positions and saliencies can then be estimated on the tagged subset of policy-relevant sentences. We apply our method to analyze the legislative positions and policy saliencies of political par- ties in the German parliament. We show that these estimates vary over time and across portfolios — variation which cannot be produced using existing methods. We believe our method simplifies preference estimation and increases construct validity of policy preference measures used to the evaluate policy-focused theories. ..PAT.-Unpublished Manuscript [ABSTRACT FROM AUTHOR]